diff --git a/.gitattributes b/.gitattributes
index a6344aac8c09253b3b630fb776ae94478aa0275b..a9dd0db0471e247ae1f13b00b4187f85f3130e73 100644
--- a/.gitattributes
+++ b/.gitattributes
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+sf_log.txt filter=lfs diff=lfs merge=lfs -text
diff --git a/.summary/0/events.out.tfevents.1703704421.rhmmedcatt-proliant-ml350-gen10 b/.summary/0/events.out.tfevents.1703704421.rhmmedcatt-proliant-ml350-gen10
new file mode 100644
index 0000000000000000000000000000000000000000..281fc393c4f3996439b7a7499aad851feba40b93
--- /dev/null
+++ b/.summary/0/events.out.tfevents.1703704421.rhmmedcatt-proliant-ml350-gen10
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2febc9488351e317549a78a764fe414a955c04011f96e0cae6db581c4e538f4c
+size 22296707
diff --git a/.summary/1/events.out.tfevents.1703704421.rhmmedcatt-proliant-ml350-gen10 b/.summary/1/events.out.tfevents.1703704421.rhmmedcatt-proliant-ml350-gen10
new file mode 100644
index 0000000000000000000000000000000000000000..6558120f3573b3460338539674fae1d2ed50099c
--- /dev/null
+++ b/.summary/1/events.out.tfevents.1703704421.rhmmedcatt-proliant-ml350-gen10
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4720fc77ace2105d899dc244d62137f592fa27419688316fdd01c47b0a288e75
+size 10513946
diff --git a/README.md b/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..a8ab8217f65be88322ea6b0296c78a722040c9f0
--- /dev/null
+++ b/README.md
@@ -0,0 +1,189 @@
+---
+library_name: sample-factory
+tags:
+- deep-reinforcement-learning
+- reinforcement-learning
+- sample-factory
+model-index:
+- name: APPO
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: mujoco_reacher
+      type: mujoco_reacher
+    metrics:
+    - type: mean_reward
+      value: -4.70 +/- 1.34
+      name: mean_reward
+      verified: false
+---
+
+## About the Project
+
+This project is an attempt to maximise performance of high sample throughput APPO RL models in Atari environments in as carbon efficient a manner as possible using a single, not particularly high performance single machine. It is about demonstrating the generalisability of on-policy algorithms to create good performance quickly (by sacrificing sample efficiency) while also proving that this route to RL production is accessible to even hobbyists like me (I am a gastroenterologist not a computer scientist). 
+
+In terms of throughput I am managing to reach throughputs of 2,500 - 3,000 across both policies using sample factory using two Quadro P2200's (not particularly powerful GPUs) each loaded up about 60% (3GB). Previously using the stable baselines 3 (sb3) implementation of PPO it would take about a week to train an atari agent to 100 million timesteps synchronously. By comparison the sample factory async implementation takes only just over 2 hours to achieve the same result. That is about 84 times faster with only typically a 21 watt burn per GPU. I am thus very grateful to Alex Petrenko and all the sample factory team for their work on this.
+
+## Project Aims
+
+This model as with all the others in the benchmarks was trained initially asynchronously un-seeded to 10 million steps for the purposes of setting a sample factory async baseline for this model on this environment but only 3/57 made it anywhere near sota performance. 
+
+I then re-trained the models with 100 million timesteps- at this point 2 environments maxed out at sota performance (Pong and Freeway) with four approaching sota performance - (atlantis, boxing, tennis and fishingderby.) =6/57 near sota. 
+
+The aim now is to try and reach state-of-the-art (SOTA) performance on a further block of atari environments using up to 1 billion training timesteps initially with appo. I will flag the models with SOTA when they reach at or near these levels. 
+
+After this I will switch on V-Trace to see if the Impala variations perform any better with the same seed (I have seeded '1234')
+
+
+## About the Model
+
+The hyperparameters used in the model are described in my shell script on my fork of sample-factory: https://github.com/MattStammers/sample-factory. Given that https://huggingface.co/edbeeching has kindly shared his parameters, I saved time and energy by using many of his tuned hyperparameters to reduce carbon inefficiency:
+```
+hyperparameters =  {
+  "help": false,
+  "algo": "APPO",
+  "env": "atari_asteroid",
+  "experiment": "atari_asteroid_APPO",
+  "train_dir": "./train_atari",
+  "restart_behavior": "restart",
+  "device": "gpu",
+  "seed": 1234,
+  "num_policies": 2,
+  "async_rl": true,
+  "serial_mode": false,
+  "batched_sampling": true,
+  "num_batches_to_accumulate": 2,
+  "worker_num_splits": 1,
+  "policy_workers_per_policy": 1,
+  "max_policy_lag": 1000,
+  "num_workers": 16,
+  "num_envs_per_worker": 2,
+  "batch_size": 1024,
+  "num_batches_per_epoch": 8,
+  "num_epochs": 4,
+  "rollout": 128,
+  "recurrence": 1,
+  "shuffle_minibatches": false,
+  "gamma": 0.99,
+  "reward_scale": 1.0,
+  "reward_clip": 1000.0,
+  "value_bootstrap": false,
+  "normalize_returns": true,
+  "exploration_loss_coeff": 0.0004677351413,
+  "value_loss_coeff": 0.5,
+  "kl_loss_coeff": 0.0,
+  "exploration_loss": "entropy",
+  "gae_lambda": 0.95,
+  "ppo_clip_ratio": 0.1,
+  "ppo_clip_value": 1.0,
+  "with_vtrace": true,
+  "vtrace_rho": 1.0,
+  "vtrace_c": 1.0,
+  "optimizer": "adam",
+  "adam_eps": 1e-05,
+  "adam_beta1": 0.9,
+  "adam_beta2": 0.999,
+  "max_grad_norm": 0.0,
+  "learning_rate": 0.0003033891184,
+  "lr_schedule": "linear_decay",
+  "lr_schedule_kl_threshold": 0.008,
+  "lr_adaptive_min": 1e-06,
+  "lr_adaptive_max": 0.01,
+  "obs_subtract_mean": 0.0,
+  "obs_scale": 255.0,
+  "normalize_input": true,
+  "normalize_input_keys": [
+    "obs"
+  ],
+  "decorrelate_experience_max_seconds": 0,
+  "decorrelate_envs_on_one_worker": true,
+  "actor_worker_gpus": [],
+  "set_workers_cpu_affinity": true,
+  "force_envs_single_thread": false,
+  "default_niceness": 0,
+  "log_to_file": true,
+  "experiment_summaries_interval": 3,
+  "flush_summaries_interval": 30,
+  "stats_avg": 100,
+  "summaries_use_frameskip": true,
+  "heartbeat_interval": 10,
+  "heartbeat_reporting_interval": 60,
+  "train_for_env_steps": 100000000,
+  "train_for_seconds": 10000000000,
+  "save_every_sec": 120,
+  "keep_checkpoints": 2,
+  "load_checkpoint_kind": "latest",
+  "save_milestones_sec": 1200,
+  "save_best_every_sec": 5,
+  "save_best_metric": "reward",
+  "save_best_after": 100000,
+  "benchmark": false,
+  "encoder_mlp_layers": [
+    512,
+    512
+  ],
+  "encoder_conv_architecture": "convnet_atari",
+  "encoder_conv_mlp_layers": [
+    512
+  ],
+  "use_rnn": false,
+  "rnn_size": 512,
+  "rnn_type": "gru",
+  "rnn_num_layers": 1,
+  "decoder_mlp_layers": [],
+  "nonlinearity": "relu",
+  "policy_initialization": "orthogonal",
+  "policy_init_gain": 1.0,
+  "actor_critic_share_weights": true,
+  "adaptive_stddev": false,
+  "continuous_tanh_scale": 0.0,
+  "initial_stddev": 1.0,
+  "use_env_info_cache": false,
+  "env_gpu_actions": false,
+  "env_gpu_observations": true,
+  "env_frameskip": 4,
+  "env_framestack": 4,
+  "pixel_format": "CHW"
+}
+
+  ```
+
+
+    
+A(n) **APPO** impala model trained on the **mujoco_reacher** environment.
+
+This model was trained using Sample-Factory 2.0: https://github.com/alex-petrenko/sample-factory. Sample factory is a 
+high throughput on-policy RL framework. I have been using 
+Documentation for how to use Sample-Factory can be found at https://www.samplefactory.dev/
+
+
+## Downloading the model
+
+After installing Sample-Factory, download the model with:
+```
+python -m sample_factory.huggingface.load_from_hub -r MattStammers/APPO-mujoco_reacher
+```
+
+    
+## Using the model
+
+To run the model after download, use the `enjoy` script corresponding to this environment:
+```
+python -m sf_examples.mujoco.enjoy_mujoco --algo=APPO --env=mujoco_reacher --train_dir=./train_dir --experiment=APPO-mujoco_reacher
+```
+
+
+You can also upload models to the Hugging Face Hub using the same script with the `--push_to_hub` flag.
+See https://www.samplefactory.dev/10-huggingface/huggingface/ for more details
+    
+## Training with this model
+
+To continue training with this model, use the `train` script corresponding to this environment:
+```
+python -m sf_examples.mujoco.train_mujoco --algo=APPO --env=mujoco_reacher --train_dir=./train_dir --experiment=APPO-mujoco_reacher --restart_behavior=resume --train_for_env_steps=10000000000
+```
+
+Note, you may have to adjust `--train_for_env_steps` to a suitably high number as the experiment will resume at the number of steps it concluded at.
+    
\ No newline at end of file
diff --git a/checkpoint_p0/best_001267192_324460544_reward_-3.848.pth b/checkpoint_p0/best_001267192_324460544_reward_-3.848.pth
new file mode 100644
index 0000000000000000000000000000000000000000..8f5637f6a672c84b00b47cf58c1722ae9478d6ed
--- /dev/null
+++ b/checkpoint_p0/best_001267192_324460544_reward_-3.848.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03832db38d05e2856dcbb4fb47dbca78d64035003e10184fc8495a41f809e503
+size 75263
diff --git a/checkpoint_p0/checkpoint_001952264_499859456.pth b/checkpoint_p0/checkpoint_001952264_499859456.pth
new file mode 100644
index 0000000000000000000000000000000000000000..12c432e683a832e77e044037f8d2afc2459b821a
--- /dev/null
+++ b/checkpoint_p0/checkpoint_001952264_499859456.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:407be72801f2743a8f9b4b370e532e43ddd71b3344cbaa7776afa8516c869eea
+size 75527
diff --git a/checkpoint_p0/checkpoint_001952840_500006912.pth b/checkpoint_p0/checkpoint_001952840_500006912.pth
new file mode 100644
index 0000000000000000000000000000000000000000..0e9bc35ef0cd4778d08e02d2c8146aa0bf0a3099
--- /dev/null
+++ b/checkpoint_p0/checkpoint_001952840_500006912.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f06cd41ca087fc506da554bfd09fce66875ea29dfab97da0e166aced2fec78da
+size 75527
diff --git a/checkpoint_p0/milestones/checkpoint_000046024_11788288.pth b/checkpoint_p0/milestones/checkpoint_000046024_11788288.pth
new file mode 100644
index 0000000000000000000000000000000000000000..7c41ec6d9a0de2d495813c50b8827b3871e6b965
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_000046024_11788288.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:421e0cfadc70861936c972a89b4ef2f735b9157c02761bc8cfb1cfbb56387111
+size 76207
diff --git a/checkpoint_p0/milestones/checkpoint_000092584_23707648.pth b/checkpoint_p0/milestones/checkpoint_000092584_23707648.pth
new file mode 100644
index 0000000000000000000000000000000000000000..8494ac327c9bc90a31aec648c169ebe7e1814fee
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_000092584_23707648.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd3b26b33fe07edc82162cbe705032e5786c5d415b38d34674a90d378a53567d
+size 76207
diff --git a/checkpoint_p0/milestones/checkpoint_000138976_35586048.pth b/checkpoint_p0/milestones/checkpoint_000138976_35586048.pth
new file mode 100644
index 0000000000000000000000000000000000000000..e99d2a3a4120029a437b2bc83bbf5ca40b109e1e
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_000138976_35586048.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:912093d9597a4222b4142be4dae60dc61ac8807af9c349995245fdcbedc90a2d
+size 76207
diff --git a/checkpoint_p0/milestones/checkpoint_000185280_47439872.pth b/checkpoint_p0/milestones/checkpoint_000185280_47439872.pth
new file mode 100644
index 0000000000000000000000000000000000000000..c9f5f5513ffe805100b7c53537c0f49180b15e18
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_000185280_47439872.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af83501c6672119391c61449d853571e72a2acdc11373e64b0a8a7137e607f4a
+size 76207
diff --git a/checkpoint_p0/milestones/checkpoint_000231848_59367424.pth b/checkpoint_p0/milestones/checkpoint_000231848_59367424.pth
new file mode 100644
index 0000000000000000000000000000000000000000..e8745d7690c921fb8abb8c6c899448d4b8a1ccea
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_000231848_59367424.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec4315d79001c02ea6f6b27699bb723d2e641e079dd0cfd885c6e8e7dfcd5356
+size 76207
diff --git a/checkpoint_p0/milestones/checkpoint_000278168_71237632.pth b/checkpoint_p0/milestones/checkpoint_000278168_71237632.pth
new file mode 100644
index 0000000000000000000000000000000000000000..f835e750ccaaf2e00b1ae893c40466660bb62882
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_000278168_71237632.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65013027844e7dd5331582ea44ac0c9ae4b1f7b2d15740ebdf98f2b3e6a428e9
+size 76207
diff --git a/checkpoint_p0/milestones/checkpoint_000324464_83091456.pth b/checkpoint_p0/milestones/checkpoint_000324464_83091456.pth
new file mode 100644
index 0000000000000000000000000000000000000000..113158a2ec45e1b1badd9f7305841a0e98e289d3
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_000324464_83091456.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:941f9cda7c74a70a1eb3beb9c45598e6b1c58f5fb099c993b579bace3516d18e
+size 76207
diff --git a/checkpoint_p0/milestones/checkpoint_000370952_94994432.pth b/checkpoint_p0/milestones/checkpoint_000370952_94994432.pth
new file mode 100644
index 0000000000000000000000000000000000000000..dde4dc20ff99a29331054694aec1147a5d27690e
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_000370952_94994432.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b81feb0012b4f6be4bafb6f4d94b251c44cb5b55b81bba3cb2eca9fe031c99b7
+size 76207
diff --git a/checkpoint_p0/milestones/checkpoint_000416456_106643456.pth b/checkpoint_p0/milestones/checkpoint_000416456_106643456.pth
new file mode 100644
index 0000000000000000000000000000000000000000..ec363bd8ee45e3335d57b785aab6f09b787f3b31
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_000416456_106643456.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:440fbc2879c6491fb138258edebbacdede3fc49ef3238e89590ab98d46969c53
+size 76251
diff --git a/checkpoint_p0/milestones/checkpoint_000462152_118341632.pth b/checkpoint_p0/milestones/checkpoint_000462152_118341632.pth
new file mode 100644
index 0000000000000000000000000000000000000000..b6a98e52086a157a5fd0f931d1b9288f97ea6db5
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_000462152_118341632.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e83620a65c35d98ae3e7ebedfd8d94d12b2321267768bad181b431addf235eac
+size 76251
diff --git a/checkpoint_p0/milestones/checkpoint_000508536_130220032.pth b/checkpoint_p0/milestones/checkpoint_000508536_130220032.pth
new file mode 100644
index 0000000000000000000000000000000000000000..ad5bccb7bdbc670f2ed64589d492e9df0909f2b5
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_000508536_130220032.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fcdf7d45319daf21f5eb1cc62779c69de265c2821899fe7af002eaa92b20f74
+size 76251
diff --git a/checkpoint_p0/milestones/checkpoint_000554808_142065664.pth b/checkpoint_p0/milestones/checkpoint_000554808_142065664.pth
new file mode 100644
index 0000000000000000000000000000000000000000..6b3a0979007949ed0c572aedf29ebf0e55180b54
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_000554808_142065664.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c6b0db1b9800d68d3cff804230ad2b518e505ff53324f6299e2d7621a753a0e
+size 76251
diff --git a/checkpoint_p0/milestones/checkpoint_000600912_153870336.pth b/checkpoint_p0/milestones/checkpoint_000600912_153870336.pth
new file mode 100644
index 0000000000000000000000000000000000000000..aa41d1c2e0336181cca88db28ea49f9470169b60
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_000600912_153870336.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9f7f732c42731b40a3cd06b882716720d4a7124b8c5fa18c8aaab9fd3b02501
+size 76251
diff --git a/checkpoint_p0/milestones/checkpoint_000647328_165756928.pth b/checkpoint_p0/milestones/checkpoint_000647328_165756928.pth
new file mode 100644
index 0000000000000000000000000000000000000000..2852ef445e0012af766961702f8c67bdf99f24ea
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_000647328_165756928.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4c0b0dad022171c270a9337d30da4deaa7821092b8289efe1273d5aab73baff
+size 76251
diff --git a/checkpoint_p0/milestones/checkpoint_000692216_177258496.pth b/checkpoint_p0/milestones/checkpoint_000692216_177258496.pth
new file mode 100644
index 0000000000000000000000000000000000000000..e71d94900a6039e848bea5f165217104adf44f64
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_000692216_177258496.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0a9cb8631efcd9a1f17223f0040082e75c523331c894747d12ddf09a70794f6
+size 76251
diff --git a/checkpoint_p0/milestones/checkpoint_000738520_189112320.pth b/checkpoint_p0/milestones/checkpoint_000738520_189112320.pth
new file mode 100644
index 0000000000000000000000000000000000000000..6acaec7af6eb8e915c8f5e231d3dcc26e1c80a2a
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_000738520_189112320.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30d5b9eb1ddb6c52186ef7b468016e42f2da2db2293c977f2d0a4ffba9758cb6
+size 76251
diff --git a/checkpoint_p0/milestones/checkpoint_000784776_200957952.pth b/checkpoint_p0/milestones/checkpoint_000784776_200957952.pth
new file mode 100644
index 0000000000000000000000000000000000000000..12cb1498cdd4de8be7cae19e8c814989557a49b8
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_000784776_200957952.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91c326ef8c9655e8190ac4c673bedf12f1ed93ce96a05856afa84c537af8e183
+size 76251
diff --git a/checkpoint_p0/milestones/checkpoint_000831400_212893696.pth b/checkpoint_p0/milestones/checkpoint_000831400_212893696.pth
new file mode 100644
index 0000000000000000000000000000000000000000..56997acb6bebac5e97699c0cd0a82323f74d6bee
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_000831400_212893696.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d999a86897209291b83a059520b8a5094f769b52f48912c2e0d23be3f7195916
+size 76251
diff --git a/checkpoint_p0/milestones/checkpoint_000877704_224747520.pth b/checkpoint_p0/milestones/checkpoint_000877704_224747520.pth
new file mode 100644
index 0000000000000000000000000000000000000000..4ca14945fc08aed87eb740bd0fa50eef7ee0f59b
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_000877704_224747520.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d92be2b8c29f025d92b28f15870672152febde60b1944ba7ead52346cca3b22
+size 76251
diff --git a/checkpoint_p0/milestones/checkpoint_000923848_236560384.pth b/checkpoint_p0/milestones/checkpoint_000923848_236560384.pth
new file mode 100644
index 0000000000000000000000000000000000000000..e063a533557ee6205c8c5c740be3608e79801ab8
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_000923848_236560384.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65e16f9459487c963e7d68445c921714d87d92a4294aaa6735486fd1fe167e69
+size 76251
diff --git a/checkpoint_p0/milestones/checkpoint_000970208_248430592.pth b/checkpoint_p0/milestones/checkpoint_000970208_248430592.pth
new file mode 100644
index 0000000000000000000000000000000000000000..b4b25b3cddab61e10ddbb1a724b3339165baa87f
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_000970208_248430592.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b28b7c52b4685b0ebf25fdba4c6301ccdea329e9c4a766961115db60f444ee70
+size 76251
diff --git a/checkpoint_p0/milestones/checkpoint_001016256_260218880.pth b/checkpoint_p0/milestones/checkpoint_001016256_260218880.pth
new file mode 100644
index 0000000000000000000000000000000000000000..492dc6600e721780ddcb5864a011d11c93d5e9f0
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_001016256_260218880.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcde031585cae527fbbb4c08aa47cc7b033f2ce32913bf5a7e84f4710959e818
+size 76251
diff --git a/checkpoint_p0/milestones/checkpoint_001062560_272072704.pth b/checkpoint_p0/milestones/checkpoint_001062560_272072704.pth
new file mode 100644
index 0000000000000000000000000000000000000000..cdd2b2b16b9343cb61bba01cc78985689f748f04
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_001062560_272072704.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f118daad157822d628f44c3acb0d533cf8a7707cb9e7d7d3cbfeb14a511a75d0
+size 76251
diff --git a/checkpoint_p0/milestones/checkpoint_001108888_283934720.pth b/checkpoint_p0/milestones/checkpoint_001108888_283934720.pth
new file mode 100644
index 0000000000000000000000000000000000000000..50e8f3c0048732485e006cb3e7eb1cefd7960e56
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_001108888_283934720.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4f126ef067868e45c5bcac57114fd88934b1901911551d6baae96078834fc74
+size 76251
diff --git a/checkpoint_p0/milestones/checkpoint_001155192_295788544.pth b/checkpoint_p0/milestones/checkpoint_001155192_295788544.pth
new file mode 100644
index 0000000000000000000000000000000000000000..c7578fe4ea4028126f160eb011fba4c7dbcf21a0
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_001155192_295788544.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84b5e9a7581e8c56736ca053b2c32fb954a784039d3598a7cc33110ff9beedac
+size 76251
diff --git a/checkpoint_p0/milestones/checkpoint_001201784_307716096.pth b/checkpoint_p0/milestones/checkpoint_001201784_307716096.pth
new file mode 100644
index 0000000000000000000000000000000000000000..f47d17ac467bbbaafc1cf082d180b7bf9640c538
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_001201784_307716096.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4da8a6daa078fdbef35ad06dd312f4093559b91dc9ac95ed2b837f13fce8ad56
+size 76251
diff --git a/checkpoint_p0/milestones/checkpoint_001248056_319561728.pth b/checkpoint_p0/milestones/checkpoint_001248056_319561728.pth
new file mode 100644
index 0000000000000000000000000000000000000000..a18ec720f6a2406fcd7634b45cd4a9369f2aa074
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_001248056_319561728.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7dac6f8402e3ef522134b7f4e436e208021721aacd84e72ea4663ed3641d4d5
+size 76251
diff --git a/checkpoint_p0/milestones/checkpoint_001294328_331407360.pth b/checkpoint_p0/milestones/checkpoint_001294328_331407360.pth
new file mode 100644
index 0000000000000000000000000000000000000000..a49c5b7e5a22f0024ff6d516e4d60d203f985e2a
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_001294328_331407360.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6e2f1bfc32940489e81b1c3efc1c5a8a6af913353e0a65e9db5dc663d0cf5e1
+size 76251
diff --git a/checkpoint_p0/milestones/checkpoint_001340480_343228416.pth b/checkpoint_p0/milestones/checkpoint_001340480_343228416.pth
new file mode 100644
index 0000000000000000000000000000000000000000..ff1ca5f66ae96b5c23f1997d9cdd688856f7b280
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_001340480_343228416.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f69f6519bfed721cc43dc5d86ed70dd6702088f24bf6b710cfb4cd352fca28e
+size 76251
diff --git a/checkpoint_p0/milestones/checkpoint_001387024_355147776.pth b/checkpoint_p0/milestones/checkpoint_001387024_355147776.pth
new file mode 100644
index 0000000000000000000000000000000000000000..3fc7e41d96437f7f670d52485bb70d71668c35cf
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_001387024_355147776.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56212a97bb6ca8bbf3af93527eafd25f2e1a4e1d62723ec9d0531143111aada9
+size 76251
diff --git a/checkpoint_p0/milestones/checkpoint_001433328_367001600.pth b/checkpoint_p0/milestones/checkpoint_001433328_367001600.pth
new file mode 100644
index 0000000000000000000000000000000000000000..36d3a7ae2938b66aa14802a1309a19bd9723bf9c
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_001433328_367001600.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e75c7524eb658fef7458086c88927471e7cd49844dd49456e955ac7068c8073
+size 76251
diff --git a/checkpoint_p0/milestones/checkpoint_001479544_378839040.pth b/checkpoint_p0/milestones/checkpoint_001479544_378839040.pth
new file mode 100644
index 0000000000000000000000000000000000000000..5e8992bb9894f9c00dd86394f1b3d1ec90d72d49
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_001479544_378839040.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b59e789358f89a9c9b4db0764b54deedd825a15c38e05cc9765b598f3ea791f
+size 76251
diff --git a/checkpoint_p0/milestones/checkpoint_001525848_390692864.pth b/checkpoint_p0/milestones/checkpoint_001525848_390692864.pth
new file mode 100644
index 0000000000000000000000000000000000000000..9f2a617ea81e0c17f19993bf28fde31535e511a2
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_001525848_390692864.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6ed68aa60ee5830c43f43746cb0da03cd4b0cad8592c47da25b621b3819767c
+size 76251
diff --git a/checkpoint_p0/milestones/checkpoint_001572504_402636800.pth b/checkpoint_p0/milestones/checkpoint_001572504_402636800.pth
new file mode 100644
index 0000000000000000000000000000000000000000..bd393e8eeabe6550083c58e85351ac1d15804c9b
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_001572504_402636800.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9352c8a5a8f5201c4b5968b6955c2e8a1be3e3edff857ae465d4fc98ded35de
+size 76251
diff --git a/checkpoint_p0/milestones/checkpoint_001618904_414515200.pth b/checkpoint_p0/milestones/checkpoint_001618904_414515200.pth
new file mode 100644
index 0000000000000000000000000000000000000000..c1362a08b66118a4545fdf7110572f3b8438dd65
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_001618904_414515200.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f965f1953c35e8bb63afbe0a696ad5698cca9266bf4c520f60c019d8c7d8eccb
+size 76251
diff --git a/checkpoint_p0/milestones/checkpoint_001665080_426336256.pth b/checkpoint_p0/milestones/checkpoint_001665080_426336256.pth
new file mode 100644
index 0000000000000000000000000000000000000000..e18adc882691169be5b1caf717ee04e69d8d874f
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_001665080_426336256.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c4ed6045df1d34eaed9b591a9e6069ca207a78f49ce86cbadf5b2fe97779ecf
+size 76251
diff --git a/checkpoint_p0/milestones/checkpoint_001711592_438247424.pth b/checkpoint_p0/milestones/checkpoint_001711592_438247424.pth
new file mode 100644
index 0000000000000000000000000000000000000000..b009b5e686fc018c610935724c3ed9a231aa816e
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_001711592_438247424.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb4fbef5cf9442420f950cd89e5856564a83b87bc2e362962f5692444bb216e7
+size 76251
diff --git a/checkpoint_p0/milestones/checkpoint_001757832_450084864.pth b/checkpoint_p0/milestones/checkpoint_001757832_450084864.pth
new file mode 100644
index 0000000000000000000000000000000000000000..a940504a6a51927e191771ec3b08099f3e59e88c
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_001757832_450084864.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:161e4ca43e2a6f203d6e992bd4ce0e526a052e83c3c809ddc6ce432a1f6ae863
+size 76251
diff --git a/checkpoint_p0/milestones/checkpoint_001804136_461938688.pth b/checkpoint_p0/milestones/checkpoint_001804136_461938688.pth
new file mode 100644
index 0000000000000000000000000000000000000000..44df8f4aa756ec922357194a1b1d015b09e03337
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_001804136_461938688.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2bc8250a144a0071ec4cd9d3ba64b16c07209a7aab708ee8740e61c7ec2cb715
+size 76251
diff --git a/checkpoint_p0/milestones/checkpoint_001850376_473776128.pth b/checkpoint_p0/milestones/checkpoint_001850376_473776128.pth
new file mode 100644
index 0000000000000000000000000000000000000000..31129408a94ffdf9c7f17c19c76d48d617d4eec3
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_001850376_473776128.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50325433435f738441bb844afa605ae1db643664df80e75b43cdfb7779077a86
+size 76251
diff --git a/checkpoint_p0/milestones/checkpoint_001896680_485629952.pth b/checkpoint_p0/milestones/checkpoint_001896680_485629952.pth
new file mode 100644
index 0000000000000000000000000000000000000000..5a53dfb33e3bb2281a6aa0b266df0a53f378a755
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_001896680_485629952.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b253cf6683ff563566ac71d1fc0bc5317926ef05523b3968bb8f2d55eddc2ea3
+size 76251
diff --git a/checkpoint_p0/milestones/checkpoint_001943080_497508352.pth b/checkpoint_p0/milestones/checkpoint_001943080_497508352.pth
new file mode 100644
index 0000000000000000000000000000000000000000..dbe1fd7565c554c653933fa50147d73e1f989342
--- /dev/null
+++ b/checkpoint_p0/milestones/checkpoint_001943080_497508352.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1137d7c55e8792c16c8f826e9c9aefa720dd734619b3b26014cbc78f7031c77d
+size 76251
diff --git a/checkpoint_p1/best_001902208_487022592_reward_-4.084.pth b/checkpoint_p1/best_001902208_487022592_reward_-4.084.pth
new file mode 100644
index 0000000000000000000000000000000000000000..a1b76db18ef1f0746acefe6928a4dfc4674ea67a
--- /dev/null
+++ b/checkpoint_p1/best_001902208_487022592_reward_-4.084.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a94aff8fa757f5414d947dcfa1ceaaa9d8741d9571ac58a05ddd4de417497516
+size 75263
diff --git a/checkpoint_p1/checkpoint_001954784_500908032.pth b/checkpoint_p1/checkpoint_001954784_500908032.pth
new file mode 100644
index 0000000000000000000000000000000000000000..286ce5ea327e87c1a69e501d0a884a9908b176bc
--- /dev/null
+++ b/checkpoint_p1/checkpoint_001954784_500908032.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63e77dd2472ec9f81604c43bc04d939df6eb8bbb4574e32602363793613176ce
+size 75527
diff --git a/checkpoint_p1/checkpoint_001955088_501063680.pth b/checkpoint_p1/checkpoint_001955088_501063680.pth
new file mode 100644
index 0000000000000000000000000000000000000000..d2c6b6903407329b74963ee0269dd31d76115bf0
--- /dev/null
+++ b/checkpoint_p1/checkpoint_001955088_501063680.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b5af05ac83617e531c35e40d426a4c38dbef9875e020f5c02b5ff96f05e39ca
+size 75527
diff --git a/checkpoint_p1/milestones/checkpoint_000046128_11812864.pth b/checkpoint_p1/milestones/checkpoint_000046128_11812864.pth
new file mode 100644
index 0000000000000000000000000000000000000000..96a095c67bdb4179e04543a975d7c6c4a824ee6d
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_000046128_11812864.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d0e5887a25560589603f2ce3e4164b3d8f390ae93c92893c8e82362325dc5dc
+size 76207
diff --git a/checkpoint_p1/milestones/checkpoint_000092464_23674880.pth b/checkpoint_p1/milestones/checkpoint_000092464_23674880.pth
new file mode 100644
index 0000000000000000000000000000000000000000..c4d6da882dfe8c6d01173d5db80b81cfe3dfa61c
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_000092464_23674880.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d69f40ace3b51903afdd823bc1ad540578ae4ca1c736f222ae9b523df0d006b
+size 76207
diff --git a/checkpoint_p1/milestones/checkpoint_000139072_35610624.pth b/checkpoint_p1/milestones/checkpoint_000139072_35610624.pth
new file mode 100644
index 0000000000000000000000000000000000000000..c0356d2f5817e6107d9c21da891d840364a1af70
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_000139072_35610624.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7802b5d5a6278a01f4cd94075fdcd6bdb0600ef70b63671ac3e941cb2b92c238
+size 76207
diff --git a/checkpoint_p1/milestones/checkpoint_000185600_47521792.pth b/checkpoint_p1/milestones/checkpoint_000185600_47521792.pth
new file mode 100644
index 0000000000000000000000000000000000000000..e10265283107e775972f681b4cffc4cc0ef4361d
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_000185600_47521792.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0216856e7cc25e642f2788fba96e3ad177e8f2fca8b3a42c696925d2a1b5766b
+size 76207
diff --git a/checkpoint_p1/milestones/checkpoint_000232112_59432960.pth b/checkpoint_p1/milestones/checkpoint_000232112_59432960.pth
new file mode 100644
index 0000000000000000000000000000000000000000..9830b17f982b6f237cdedc53de1872b6ce803e42
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_000232112_59432960.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7869f5df9ad969d8edf350cbef322f4bcfb64fcb6198951b052a6d8a0f765b3a
+size 76207
diff --git a/checkpoint_p1/milestones/checkpoint_000278688_71360512.pth b/checkpoint_p1/milestones/checkpoint_000278688_71360512.pth
new file mode 100644
index 0000000000000000000000000000000000000000..d5603e2666b546438fc56f0e1c39f2fbbe3b144e
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_000278688_71360512.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f86b983b4f12941d5bd9a6d5c4b87a447e389d56406681a70f7a708c8ed614d
+size 76207
diff --git a/checkpoint_p1/milestones/checkpoint_000325072_83238912.pth b/checkpoint_p1/milestones/checkpoint_000325072_83238912.pth
new file mode 100644
index 0000000000000000000000000000000000000000..c3018686e0ecd47eb5b87da4081215c8be8b68c5
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_000325072_83238912.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6d122b9d255d3f572f4d9f7ed507d8dd70e63983c97bd7326a5f3f89f3d32b6
+size 76207
diff --git a/checkpoint_p1/milestones/checkpoint_000371696_95182848.pth b/checkpoint_p1/milestones/checkpoint_000371696_95182848.pth
new file mode 100644
index 0000000000000000000000000000000000000000..32a87702d653ecc2ca0009fd72d137be32cf2cbc
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_000371696_95182848.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4fc37787827a20ca4dfe3cd6fe29e1225d65090473f5f07a7e052d214721a8f
+size 76207
diff --git a/checkpoint_p1/milestones/checkpoint_000417744_106971136.pth b/checkpoint_p1/milestones/checkpoint_000417744_106971136.pth
new file mode 100644
index 0000000000000000000000000000000000000000..fb758a164df8f498bf685556df59af03f901e7d8
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_000417744_106971136.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45085f4f31142302eb2f5cd4df6d2969bea6d52de970feefe2dc9242b33b9882
+size 76251
diff --git a/checkpoint_p1/milestones/checkpoint_000463600_118710272.pth b/checkpoint_p1/milestones/checkpoint_000463600_118710272.pth
new file mode 100644
index 0000000000000000000000000000000000000000..ea8d9a06831e036e16b47ccf46674d97534f53bd
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_000463600_118710272.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:558eadfeff0543dcb02d54b654d90357f70676b828015a55ff88114f25d195b3
+size 76251
diff --git a/checkpoint_p1/milestones/checkpoint_000509872_130555904.pth b/checkpoint_p1/milestones/checkpoint_000509872_130555904.pth
new file mode 100644
index 0000000000000000000000000000000000000000..703737a5b9c596a51a340d370adcea7981cffcb2
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_000509872_130555904.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c49697a47eb66d77b204edb619d4b34b201e2444c0e411be780891169940dc1e
+size 76251
diff --git a/checkpoint_p1/milestones/checkpoint_000556400_142467072.pth b/checkpoint_p1/milestones/checkpoint_000556400_142467072.pth
new file mode 100644
index 0000000000000000000000000000000000000000..c9f19f2f99861f16d9ba4a17c73677df11c08b8f
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_000556400_142467072.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54dca4abed9e2bbc9cb9c73100a4c3818ae476b8d5991f3867807c30de451ff7
+size 76251
diff --git a/checkpoint_p1/milestones/checkpoint_000602896_154370048.pth b/checkpoint_p1/milestones/checkpoint_000602896_154370048.pth
new file mode 100644
index 0000000000000000000000000000000000000000..ec038a701099f0157d3a3b00a7ed083d290e7c67
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_000602896_154370048.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87f610f90cfa750a978e83622d182bf2ed6d6363bea3ab0ab93897193ebead85
+size 76251
diff --git a/checkpoint_p1/milestones/checkpoint_000649224_166232064.pth b/checkpoint_p1/milestones/checkpoint_000649224_166232064.pth
new file mode 100644
index 0000000000000000000000000000000000000000..d7ba43bf689b893d5a7e66bcfd902ab42cf02f87
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_000649224_166232064.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a6d6f9e19cbb0c762d41a3f0983a16d21bd8cefde34fb0a57a70c35d1667c1c
+size 76251
diff --git a/checkpoint_p1/milestones/checkpoint_000694024_177700864.pth b/checkpoint_p1/milestones/checkpoint_000694024_177700864.pth
new file mode 100644
index 0000000000000000000000000000000000000000..de3cbb7afd0665473e2afbffc1f99e9bcc93fe0f
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_000694024_177700864.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38305d571bdf1b1959b6026b3e6633f2e28bbc92fc9b9ed7ae4472f624906589
+size 76251
diff --git a/checkpoint_p1/milestones/checkpoint_000740456_189595648.pth b/checkpoint_p1/milestones/checkpoint_000740456_189595648.pth
new file mode 100644
index 0000000000000000000000000000000000000000..608e494d12da2a89f935c53f278e5e576efcddc0
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_000740456_189595648.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:484c8ce934c89afa570f75e8d7453fc8538363f9c6c524d7228b0553c502e463
+size 76251
diff --git a/checkpoint_p1/milestones/checkpoint_000786920_201490432.pth b/checkpoint_p1/milestones/checkpoint_000786920_201490432.pth
new file mode 100644
index 0000000000000000000000000000000000000000..c85205ed71610c0e8b54d74ca3cbc18c76f0670b
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_000786920_201490432.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac7be4d6f71cba34cae20024304d1a7f5be7b9ec13002ba8662653a94497d5c6
+size 76251
diff --git a/checkpoint_p1/milestones/checkpoint_000833312_213368832.pth b/checkpoint_p1/milestones/checkpoint_000833312_213368832.pth
new file mode 100644
index 0000000000000000000000000000000000000000..298e430c75ba273ab5838f2a3414f5b78a298e9d
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_000833312_213368832.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad1a02938349647d33b0ad7323b6e7f9c44ca145db26508b1b9af602960fb1e8
+size 76251
diff --git a/checkpoint_p1/milestones/checkpoint_000879904_225296384.pth b/checkpoint_p1/milestones/checkpoint_000879904_225296384.pth
new file mode 100644
index 0000000000000000000000000000000000000000..4e455d9cad29026fdeabeea7d1ef3bfdc2bbdcd1
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_000879904_225296384.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c240611bc39a9467ad2259c7bab5811ab4e1573bd923c564d5fde7cdfa959a12
+size 76251
diff --git a/checkpoint_p1/milestones/checkpoint_000926272_237166592.pth b/checkpoint_p1/milestones/checkpoint_000926272_237166592.pth
new file mode 100644
index 0000000000000000000000000000000000000000..0645b578393f2ba204a9998dc69482d1c0dc533b
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_000926272_237166592.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fefade4bfde911df17c6c9b1c20795d58b5fe3102d9247f8640601da1b69f459
+size 76251
diff --git a/checkpoint_p1/milestones/checkpoint_000972448_248987648.pth b/checkpoint_p1/milestones/checkpoint_000972448_248987648.pth
new file mode 100644
index 0000000000000000000000000000000000000000..3085e2d54b97480fa13be03467ea81ccc6a1b7b5
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_000972448_248987648.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd66856cfd8f724d588cedae001610c0a1e92604b517bdf012fff5a405b33be3
+size 76251
diff --git a/checkpoint_p1/milestones/checkpoint_001018816_260857856.pth b/checkpoint_p1/milestones/checkpoint_001018816_260857856.pth
new file mode 100644
index 0000000000000000000000000000000000000000..5bad66f30a5b66c14f330693458bb82322ac00ff
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_001018816_260857856.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78ef3443813428264feae7a1df61fb8fe3d96b75c7203e84bada07034270f966
+size 76251
diff --git a/checkpoint_p1/milestones/checkpoint_001065272_272752640.pth b/checkpoint_p1/milestones/checkpoint_001065272_272752640.pth
new file mode 100644
index 0000000000000000000000000000000000000000..62e63a4e7660a3e5b84505b8fd5a09bdf461ee6d
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_001065272_272752640.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e952d8231df09f976f8fd5c085fc3428e6c5f493779176f92310d54d3f3580b9
+size 76251
diff --git a/checkpoint_p1/milestones/checkpoint_001111888_284688384.pth b/checkpoint_p1/milestones/checkpoint_001111888_284688384.pth
new file mode 100644
index 0000000000000000000000000000000000000000..69d9902114645dd7874053676aaef0118a77e8b0
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_001111888_284688384.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:352bd35ca36ecdffa442c51fd2e6672e76c5f23b9b4b66934286ae19c62ec1ea
+size 76251
diff --git a/checkpoint_p1/milestones/checkpoint_001158280_296566784.pth b/checkpoint_p1/milestones/checkpoint_001158280_296566784.pth
new file mode 100644
index 0000000000000000000000000000000000000000..7cd6790134b734d8877ce903f30e352d06289dd1
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_001158280_296566784.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f83403a2423ef5764fc15a7ab21c6d8b7f8e0c9312082a34dce408f72c5d508a
+size 76251
diff --git a/checkpoint_p1/milestones/checkpoint_001204776_308469760.pth b/checkpoint_p1/milestones/checkpoint_001204776_308469760.pth
new file mode 100644
index 0000000000000000000000000000000000000000..76d193003f6b406b8b52e78530715f0f93145a6b
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_001204776_308469760.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bec16083bd7c583ace2dce9ec5aefb7e1a759368aae388ab753b398efd5cb565
+size 76251
diff --git a/checkpoint_p1/milestones/checkpoint_001251240_320364544.pth b/checkpoint_p1/milestones/checkpoint_001251240_320364544.pth
new file mode 100644
index 0000000000000000000000000000000000000000..8e19ad0ab7f7baaba6ff643cde4949395ed38464
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_001251240_320364544.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24481b0bdff9cd598b57d7ce1bf75bba716bc6a632c0bf75402d5cb68f812ca5
+size 76251
diff --git a/checkpoint_p1/milestones/checkpoint_001297672_332251136.pth b/checkpoint_p1/milestones/checkpoint_001297672_332251136.pth
new file mode 100644
index 0000000000000000000000000000000000000000..94bc5217aa64b9e0f9cc420572b3a1cddcb86449
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_001297672_332251136.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3348ea153f015e760f623e27c285b545856a0b44dd281ee7898ab90bed0790fa
+size 76251
diff --git a/checkpoint_p1/milestones/checkpoint_001343928_344096768.pth b/checkpoint_p1/milestones/checkpoint_001343928_344096768.pth
new file mode 100644
index 0000000000000000000000000000000000000000..baaaee21a62ebd7a0a9be0f69e512fcd45b5395b
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_001343928_344096768.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65624f2bc2bac405e84575f5c3fdaafcd67f2c8dd649340268bf8a7d1c453643
+size 76251
diff --git a/checkpoint_p1/milestones/checkpoint_001390264_355958784.pth b/checkpoint_p1/milestones/checkpoint_001390264_355958784.pth
new file mode 100644
index 0000000000000000000000000000000000000000..a6ae270d9bf3add58431a897e845ca33b75a41b2
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_001390264_355958784.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa6797aedcbfc441b9f23f2c5c583c8c5d170f28717f73c57ae8c45ed7e2f3c1
+size 76251
diff --git a/checkpoint_p1/milestones/checkpoint_001436568_367812608.pth b/checkpoint_p1/milestones/checkpoint_001436568_367812608.pth
new file mode 100644
index 0000000000000000000000000000000000000000..784e505819fc7f2c1068fbef944333ea06b3f6fe
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_001436568_367812608.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15c524637aee4b7b877258eb411e5a99fcc7751d97ef9d953aad3e7612d3988d
+size 76251
diff --git a/checkpoint_p1/milestones/checkpoint_001483000_379699200.pth b/checkpoint_p1/milestones/checkpoint_001483000_379699200.pth
new file mode 100644
index 0000000000000000000000000000000000000000..4b6a5c7c0133497b38fe0e572a26555ddc7fcf32
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_001483000_379699200.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2ff97da2804eca2e552fc8bfab6c053794ab12f4e0ee48a01ebda015d649cdf
+size 76251
diff --git a/checkpoint_p1/milestones/checkpoint_001529624_391634944.pth b/checkpoint_p1/milestones/checkpoint_001529624_391634944.pth
new file mode 100644
index 0000000000000000000000000000000000000000..56d86687043d8df15313157ed17b674f72bef8e9
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_001529624_391634944.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b15e1c2d760f4a691e5865a9c8c80b582589c4fbc65d70ff9584444f3018a78
+size 76251
diff --git a/checkpoint_p1/milestones/checkpoint_001576056_403521536.pth b/checkpoint_p1/milestones/checkpoint_001576056_403521536.pth
new file mode 100644
index 0000000000000000000000000000000000000000..0176afe364413a960055670ae36bd1a162df698c
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_001576056_403521536.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12c39031e81f5fe473d996c6109959640e301ce9275ab4f3512c493efa071f27
+size 76251
diff --git a/checkpoint_p1/milestones/checkpoint_001622552_415424512.pth b/checkpoint_p1/milestones/checkpoint_001622552_415424512.pth
new file mode 100644
index 0000000000000000000000000000000000000000..a85c9215318bd2deeb6ec423c0045a37a786f8a5
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_001622552_415424512.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06f9ce04742e4b313d63d1716c5463d0ceccccba1c87a295a606a48f6d204785
+size 76251
diff --git a/checkpoint_p1/milestones/checkpoint_001669032_427327488.pth b/checkpoint_p1/milestones/checkpoint_001669032_427327488.pth
new file mode 100644
index 0000000000000000000000000000000000000000..68c1bafa3f6bf010ad8fde3d59e867c951ee4faf
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_001669032_427327488.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5645a4cdf1200be5663014464f3783e580f26beb182cf4a88ee30703c9c1cd8
+size 76251
diff --git a/checkpoint_p1/milestones/checkpoint_001715496_439222272.pth b/checkpoint_p1/milestones/checkpoint_001715496_439222272.pth
new file mode 100644
index 0000000000000000000000000000000000000000..be2e510a95ec0794d1debac82e6af0dba356cec5
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_001715496_439222272.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4bfe1d8a481aa075c506a9916feba1e912211d817db01260fc6126ebcc060a1a
+size 76251
diff --git a/checkpoint_p1/milestones/checkpoint_001762120_451158016.pth b/checkpoint_p1/milestones/checkpoint_001762120_451158016.pth
new file mode 100644
index 0000000000000000000000000000000000000000..df259703642fb521ef4c344948906004c1921c4f
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_001762120_451158016.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c58c59d97640470b2290a69e964dae43cb72fd6bf08f50fa8f635640710914e
+size 76251
diff --git a/checkpoint_p1/milestones/checkpoint_001808256_462970880.pth b/checkpoint_p1/milestones/checkpoint_001808256_462970880.pth
new file mode 100644
index 0000000000000000000000000000000000000000..7d258cfd6c48f1cc92de939d9e3be55810565924
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_001808256_462970880.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a09f0fe18de5954928cf736bfc9b12d08403db317e46863e0566e4aa8cfefdcd
+size 76251
diff --git a/checkpoint_p1/milestones/checkpoint_001854336_474767360.pth b/checkpoint_p1/milestones/checkpoint_001854336_474767360.pth
new file mode 100644
index 0000000000000000000000000000000000000000..36ed5242ed9d68a2c77766c8b517deae3179e882
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_001854336_474767360.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6d53151b273b6673878963714cc759950ba62ce2c58cd4ce3171b32167a9a10
+size 76251
diff --git a/checkpoint_p1/milestones/checkpoint_001900832_486670336.pth b/checkpoint_p1/milestones/checkpoint_001900832_486670336.pth
new file mode 100644
index 0000000000000000000000000000000000000000..2e0d77d15f2a0f6efc95aa5b923caaf4812d3c85
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_001900832_486670336.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6f225b8b264b191c4570325eb2cd012196f83425a7ff1bb5450123829afe18a
+size 76251
diff --git a/checkpoint_p1/milestones/checkpoint_001947232_498548736.pth b/checkpoint_p1/milestones/checkpoint_001947232_498548736.pth
new file mode 100644
index 0000000000000000000000000000000000000000..c4f72f06dc44c7da057678dbcfe5b60a3fe9cec7
--- /dev/null
+++ b/checkpoint_p1/milestones/checkpoint_001947232_498548736.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:802b689b0bb105f992bf01b0f7de0128f531ab6ce6af725825d7aa9287973a85
+size 76251
diff --git a/config.json b/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..dbe8da69a5ef473e4047ae5fd0d410aa0b8d7dd1
--- /dev/null
+++ b/config.json
@@ -0,0 +1,164 @@
+{
+  "help": false,
+  "algo": "APPO",
+  "env": "mujoco_reacher",
+  "experiment": "mujoco_reacher_APPO",
+  "train_dir": "./train_mujoco",
+  "restart_behavior": "resume",
+  "device": "gpu",
+  "seed": 1234,
+  "num_policies": 2,
+  "async_rl": true,
+  "serial_mode": false,
+  "batched_sampling": true,
+  "num_batches_to_accumulate": 2,
+  "worker_num_splits": 2,
+  "policy_workers_per_policy": 1,
+  "max_policy_lag": 1000,
+  "num_workers": 16,
+  "num_envs_per_worker": 8,
+  "batch_size": 1024,
+  "num_batches_per_epoch": 8,
+  "num_epochs": 4,
+  "rollout": 64,
+  "recurrence": 1,
+  "shuffle_minibatches": false,
+  "gamma": 0.99,
+  "reward_scale": 1,
+  "reward_clip": 1000.0,
+  "value_bootstrap": true,
+  "normalize_returns": true,
+  "exploration_loss_coeff": 0.0004677351413,
+  "value_loss_coeff": 1.3,
+  "kl_loss_coeff": 0.1,
+  "exploration_loss": "entropy",
+  "gae_lambda": 0.95,
+  "ppo_clip_ratio": 0.2,
+  "ppo_clip_value": 1.0,
+  "with_vtrace": false,
+  "vtrace_rho": 1.0,
+  "vtrace_c": 1.0,
+  "optimizer": "adam",
+  "adam_eps": 1e-06,
+  "adam_beta1": 0.9,
+  "adam_beta2": 0.999,
+  "max_grad_norm": 0.0,
+  "learning_rate": 0.0003033891184,
+  "lr_schedule": "linear_decay",
+  "lr_schedule_kl_threshold": 0.008,
+  "lr_adaptive_min": 1e-06,
+  "lr_adaptive_max": 0.01,
+  "obs_subtract_mean": 0.0,
+  "obs_scale": 1.0,
+  "normalize_input": true,
+  "normalize_input_keys": [
+    "obs"
+  ],
+  "decorrelate_experience_max_seconds": 0,
+  "decorrelate_envs_on_one_worker": true,
+  "actor_worker_gpus": [],
+  "set_workers_cpu_affinity": true,
+  "force_envs_single_thread": false,
+  "default_niceness": 0,
+  "log_to_file": true,
+  "experiment_summaries_interval": 3,
+  "flush_summaries_interval": 30,
+  "stats_avg": 100,
+  "summaries_use_frameskip": false,
+  "heartbeat_interval": 10,
+  "heartbeat_reporting_interval": 60,
+  "train_for_env_steps": 500000000,
+  "train_for_seconds": 10000000000,
+  "save_every_sec": 15,
+  "keep_checkpoints": 2,
+  "load_checkpoint_kind": "latest",
+  "save_milestones_sec": 1200,
+  "save_best_every_sec": 5,
+  "save_best_metric": "reward",
+  "save_best_after": 100000,
+  "benchmark": false,
+  "encoder_mlp_layers": [
+    64,
+    64
+  ],
+  "encoder_conv_architecture": "convnet_simple",
+  "encoder_conv_mlp_layers": [
+    512
+  ],
+  "use_rnn": false,
+  "rnn_size": 512,
+  "rnn_type": "gru",
+  "rnn_num_layers": 1,
+  "decoder_mlp_layers": [],
+  "nonlinearity": "tanh",
+  "policy_initialization": "torch_default",
+  "policy_init_gain": 1.0,
+  "actor_critic_share_weights": true,
+  "adaptive_stddev": false,
+  "continuous_tanh_scale": 0.0,
+  "initial_stddev": 1.0,
+  "use_env_info_cache": false,
+  "env_gpu_actions": false,
+  "env_gpu_observations": true,
+  "env_frameskip": 1,
+  "env_framestack": 1,
+  "pixel_format": "CHW",
+  "use_record_episode_statistics": false,
+  "with_wandb": true,
+  "wandb_user": "matt-stammers",
+  "wandb_project": "mujoco_APPO",
+  "wandb_group": "mujoco_reacher",
+  "wandb_job_type": "SF",
+  "wandb_tags": [
+    "mujoco"
+  ],
+  "with_pbt": false,
+  "pbt_mix_policies_in_one_env": true,
+  "pbt_period_env_steps": 5000000,
+  "pbt_start_mutation": 20000000,
+  "pbt_replace_fraction": 0.3,
+  "pbt_mutation_rate": 0.15,
+  "pbt_replace_reward_gap": 0.1,
+  "pbt_replace_reward_gap_absolute": 1e-06,
+  "pbt_optimize_gamma": false,
+  "pbt_target_objective": "true_objective",
+  "pbt_perturb_min": 1.1,
+  "pbt_perturb_max": 1.5,
+  "command_line": "--algo=APPO --env=mujoco_reacher --experiment=mujoco_reacher_APPO --num_policies=2 --restart_behavior=resume --train_dir=./train_mujoco --train_for_env_steps=500000000 --seed=1234 --num_workers=16 --num_envs_per_worker=8 --num_batches_per_epoch=8 --worker_num_splits=2 --async_rl=true --batched_sampling=true --batch_size=1024 --max_grad_norm=0 --learning_rate=0.0003033891184 --heartbeat_interval=10 --heartbeat_reporting_interval=60 --save_milestones_sec=1200 --num_epochs=4 --exploration_loss_coeff=0.0004677351413 --summaries_use_frameskip=False --with_wandb=true --wandb_user=matt-stammers --wandb_project=mujoco_APPO --wandb_group=mujoco_reacher --wandb_job_type=SF --wandb_tags=mujoco",
+  "cli_args": {
+    "algo": "APPO",
+    "env": "mujoco_reacher",
+    "experiment": "mujoco_reacher_APPO",
+    "train_dir": "./train_mujoco",
+    "restart_behavior": "resume",
+    "seed": 1234,
+    "num_policies": 2,
+    "async_rl": true,
+    "batched_sampling": true,
+    "worker_num_splits": 2,
+    "num_workers": 16,
+    "num_envs_per_worker": 8,
+    "batch_size": 1024,
+    "num_batches_per_epoch": 8,
+    "num_epochs": 4,
+    "exploration_loss_coeff": 0.0004677351413,
+    "max_grad_norm": 0.0,
+    "learning_rate": 0.0003033891184,
+    "summaries_use_frameskip": false,
+    "heartbeat_interval": 10,
+    "heartbeat_reporting_interval": 60,
+    "train_for_env_steps": 500000000,
+    "save_milestones_sec": 1200,
+    "with_wandb": true,
+    "wandb_user": "matt-stammers",
+    "wandb_project": "mujoco_APPO",
+    "wandb_group": "mujoco_reacher",
+    "wandb_job_type": "SF",
+    "wandb_tags": [
+      "mujoco"
+    ]
+  },
+  "git_hash": "5fff97c2f535da5987d358cdbe6927cccd43621e",
+  "git_repo_name": "not a git repository",
+  "wandb_unique_id": "mujoco_reacher_APPO_20231227_191338_259733"
+}
\ No newline at end of file
diff --git a/git.diff b/git.diff
new file mode 100644
index 0000000000000000000000000000000000000000..9cf0f6792bd54243f70657987210adf15e33d282
--- /dev/null
+++ b/git.diff
@@ -0,0 +1,3470 @@
+diff --git a/train_dir/Standup/.summary/0/events.out.tfevents.1695118333.rhmmedcatt-ProLiant-ML350-Gen10 b/train_dir/Standup/.summary/0/events.out.tfevents.1695118333.rhmmedcatt-ProLiant-ML350-Gen10
+deleted file mode 100644
+index ce9a72a..0000000
+Binary files a/train_dir/Standup/.summary/0/events.out.tfevents.1695118333.rhmmedcatt-ProLiant-ML350-Gen10 and /dev/null differ
+diff --git a/train_dir/Standup/.summary/0/events.out.tfevents.1695118395.rhmmedcatt-ProLiant-ML350-Gen10 b/train_dir/Standup/.summary/0/events.out.tfevents.1695118395.rhmmedcatt-ProLiant-ML350-Gen10
+deleted file mode 100644
+index 85ffbb3..0000000
+Binary files a/train_dir/Standup/.summary/0/events.out.tfevents.1695118395.rhmmedcatt-ProLiant-ML350-Gen10 and /dev/null differ
+diff --git a/train_dir/Standup/.summary/0/events.out.tfevents.1695118777.rhmmedcatt-ProLiant-ML350-Gen10 b/train_dir/Standup/.summary/0/events.out.tfevents.1695118777.rhmmedcatt-ProLiant-ML350-Gen10
+deleted file mode 100644
+index 6b68289..0000000
+Binary files a/train_dir/Standup/.summary/0/events.out.tfevents.1695118777.rhmmedcatt-ProLiant-ML350-Gen10 and /dev/null differ
+diff --git a/train_dir/Standup/.summary/1/events.out.tfevents.1695118395.rhmmedcatt-ProLiant-ML350-Gen10 b/train_dir/Standup/.summary/1/events.out.tfevents.1695118395.rhmmedcatt-ProLiant-ML350-Gen10
+deleted file mode 100644
+index 7e65434..0000000
+Binary files a/train_dir/Standup/.summary/1/events.out.tfevents.1695118395.rhmmedcatt-ProLiant-ML350-Gen10 and /dev/null differ
+diff --git a/train_dir/Standup/.summary/1/events.out.tfevents.1695118777.rhmmedcatt-ProLiant-ML350-Gen10 b/train_dir/Standup/.summary/1/events.out.tfevents.1695118777.rhmmedcatt-ProLiant-ML350-Gen10
+deleted file mode 100644
+index e2184e2..0000000
+Binary files a/train_dir/Standup/.summary/1/events.out.tfevents.1695118777.rhmmedcatt-ProLiant-ML350-Gen10 and /dev/null differ
+diff --git a/train_dir/Standup/README.md b/train_dir/Standup/README.md
+index 59b4eea..2dc15b6 100644
+--- a/train_dir/Standup/README.md
++++ b/train_dir/Standup/README.md
+@@ -5,7 +5,7 @@ tags:
+ - reinforcement-learning
+ - sample-factory
+ model-index:
+-- name: APPO
++- name: ATD3
+   results:
+   - task:
+       type: reinforcement-learning
+@@ -15,12 +15,12 @@ model-index:
+       type: mujoco_standup
+     metrics:
+     - type: mean_reward
+-      value: 160842.81 +/- 49335.32
++      value: 157750.89 +/- 30990.47
+       name: mean_reward
+       verified: false
+ ---
+ 
+-A(n) **APPO** model trained on the **mujoco_standup** environment.
++A(n) **ATD3** model trained on the **mujoco_standup** environment.
+ 
+ This model was trained using Sample-Factory 2.0: https://github.com/alex-petrenko/sample-factory.
+ Documentation for how to use Sample-Factory can be found at https://www.samplefactory.dev/
+@@ -30,7 +30,7 @@ Documentation for how to use Sample-Factory can be found at https://www.samplefa
+ 
+ After installing Sample-Factory, download the model with:
+ ```
+-python -m sample_factory.huggingface.load_from_hub -r MattStammers/appo-mujoco-Standup
++python -m sample_factory.huggingface.load_from_hub -r MattStammers/atd3-mujoco-standup
+ ```
+ 
+     
+@@ -38,7 +38,7 @@ python -m sample_factory.huggingface.load_from_hub -r MattStammers/appo-mujoco-S
+ 
+ To run the model after download, use the `enjoy` script corresponding to this environment:
+ ```
+-python -m sf_examples.mujoco.enjoy_mujoco --algo=APPO --env=mujoco_standup --train_dir=./train_dir --experiment=appo-mujoco-Standup
++python -m sf_examples.mujoco.enjoy_mujoco --algo=ATD3 --env=mujoco_standup --train_dir=./train_dir --experiment=atd3-mujoco-standup
+ ```
+ 
+ 
+@@ -49,7 +49,7 @@ See https://www.samplefactory.dev/10-huggingface/huggingface/ for more details
+ 
+ To continue training with this model, use the `train` script corresponding to this environment:
+ ```
+-python -m sf_examples.mujoco.train_mujoco --algo=APPO --env=mujoco_standup --train_dir=./train_dir --experiment=appo-mujoco-Standup --restart_behavior=resume --train_for_env_steps=10000000000
++python -m sf_examples.mujoco.train_mujoco --algo=ATD3 --env=mujoco_standup --train_dir=./train_dir --experiment=atd3-mujoco-standup --restart_behavior=resume --train_for_env_steps=10000000000
+ ```
+ 
+ Note, you may have to adjust `--train_for_env_steps` to a suitably high number as the experiment will resume at the number of steps it concluded at.
+diff --git a/train_dir/Standup/checkpoint_p0/best_000008160_4177920_reward_162764.036.pth b/train_dir/Standup/checkpoint_p0/best_000008160_4177920_reward_162764.036.pth
+deleted file mode 100644
+index 7b4f077..0000000
+Binary files a/train_dir/Standup/checkpoint_p0/best_000008160_4177920_reward_162764.036.pth and /dev/null differ
+diff --git a/train_dir/Standup/checkpoint_p0/checkpoint_000014336_7340032.pth b/train_dir/Standup/checkpoint_p0/checkpoint_000014336_7340032.pth
+deleted file mode 100644
+index d1f1336..0000000
+Binary files a/train_dir/Standup/checkpoint_p0/checkpoint_000014336_7340032.pth and /dev/null differ
+diff --git a/train_dir/Standup/checkpoint_p0/checkpoint_000014408_7376896.pth b/train_dir/Standup/checkpoint_p0/checkpoint_000014408_7376896.pth
+deleted file mode 100644
+index f4340e0..0000000
+Binary files a/train_dir/Standup/checkpoint_p0/checkpoint_000014408_7376896.pth and /dev/null differ
+diff --git a/train_dir/Standup/checkpoint_p1/best_000013232_6774784_reward_164168.870.pth b/train_dir/Standup/checkpoint_p1/best_000013232_6774784_reward_164168.870.pth
+deleted file mode 100644
+index af623df..0000000
+Binary files a/train_dir/Standup/checkpoint_p1/best_000013232_6774784_reward_164168.870.pth and /dev/null differ
+diff --git a/train_dir/Standup/checkpoint_p1/checkpoint_000014296_7319552.pth b/train_dir/Standup/checkpoint_p1/checkpoint_000014296_7319552.pth
+deleted file mode 100644
+index f875926..0000000
+Binary files a/train_dir/Standup/checkpoint_p1/checkpoint_000014296_7319552.pth and /dev/null differ
+diff --git a/train_dir/Standup/checkpoint_p1/checkpoint_000014368_7356416.pth b/train_dir/Standup/checkpoint_p1/checkpoint_000014368_7356416.pth
+deleted file mode 100644
+index 0916341..0000000
+Binary files a/train_dir/Standup/checkpoint_p1/checkpoint_000014368_7356416.pth and /dev/null differ
+diff --git a/train_dir/Standup/config.json b/train_dir/Standup/config.json
+index 638783d..22fa3bb 100644
+--- a/train_dir/Standup/config.json
++++ b/train_dir/Standup/config.json
+@@ -1,10 +1,10 @@
+ {
+   "help": false,
+-  "algo": "APPO",
++  "algo": "ATD3",
+   "env": "mujoco_standup",
+   "experiment": "Standup",
+   "train_dir": "./train_dir",
+-  "restart_behavior": "resume",
++  "restart_behavior": "restart",
+   "device": "gpu",
+   "seed": null,
+   "num_policies": 2,
+@@ -104,8 +104,8 @@
+   "use_record_episode_statistics": false,
+   "with_wandb": true,
+   "wandb_user": "matt-stammers",
+-  "wandb_project": "sample_factory",
+-  "wandb_group": "mujoco_standup",
++  "wandb_project": "mujoco",
++  "wandb_group": "mujoco_standup3",
+   "wandb_job_type": "SF",
+   "wandb_tags": [
+     "mujoco"
+diff --git a/train_dir/Standup/replay.mp4 b/train_dir/Standup/replay.mp4
+index 51d7026..f9ddacb 100644
+Binary files a/train_dir/Standup/replay.mp4 and b/train_dir/Standup/replay.mp4 differ
+diff --git a/train_dir/Standup/sf_log.txt b/train_dir/Standup/sf_log.txt
+index c3ddd83..0d60e70 100644
+--- a/train_dir/Standup/sf_log.txt
++++ b/train_dir/Standup/sf_log.txt
+@@ -1,46 +1,48 @@
+-[2023-09-19 11:12:17,416][35316] Saving configuration to ./train_dir/Standup/config.json...
+-[2023-09-19 11:12:17,417][35316] Rollout worker 0 uses device cpu
+-[2023-09-19 11:12:17,418][35316] Rollout worker 1 uses device cpu
+-[2023-09-19 11:12:17,418][35316] Rollout worker 2 uses device cpu
+-[2023-09-19 11:12:17,418][35316] Rollout worker 3 uses device cpu
+-[2023-09-19 11:12:17,418][35316] Rollout worker 4 uses device cpu
+-[2023-09-19 11:12:17,419][35316] Rollout worker 5 uses device cpu
+-[2023-09-19 11:12:17,419][35316] Rollout worker 6 uses device cpu
+-[2023-09-19 11:12:17,419][35316] Rollout worker 7 uses device cpu
+-[2023-09-19 11:12:17,419][35316] In synchronous mode, we only accumulate one batch. Setting num_batches_to_accumulate to 1
+-[2023-09-19 11:12:17,463][35316] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+-[2023-09-19 11:12:17,463][35316] InferenceWorker_p0-w0: min num requests: 2
+-[2023-09-19 11:12:17,487][35316] Starting all processes...
+-[2023-09-19 11:12:17,488][35316] Starting process learner_proc0
+-[2023-09-19 11:12:17,492][35316] Starting all processes...
+-[2023-09-19 11:12:17,504][35316] Starting process inference_proc0-0
+-[2023-09-19 11:12:17,504][35316] Starting process rollout_proc0
+-[2023-09-19 11:12:17,505][35316] Starting process rollout_proc1
+-[2023-09-19 11:12:17,505][35316] Starting process rollout_proc2
+-[2023-09-19 11:12:17,507][35316] Starting process rollout_proc3
+-[2023-09-19 11:12:17,507][35316] Starting process rollout_proc4
+-[2023-09-19 11:12:17,508][35316] Starting process rollout_proc5
+-[2023-09-19 11:12:17,508][35316] Starting process rollout_proc6
+-[2023-09-19 11:12:17,508][35316] Starting process rollout_proc7
+-[2023-09-19 11:12:19,355][36026] Worker 6 uses CPU cores [24, 25, 26, 27]
+-[2023-09-19 11:12:19,356][36006] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+-[2023-09-19 11:12:19,356][36006] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0
+-[2023-09-19 11:12:19,370][36022] Worker 0 uses CPU cores [0, 1, 2, 3]
+-[2023-09-19 11:12:19,373][36023] Worker 5 uses CPU cores [20, 21, 22, 23]
+-[2023-09-19 11:12:19,378][36006] Num visible devices: 1
+-[2023-09-19 11:12:19,396][36020] Worker 1 uses CPU cores [4, 5, 6, 7]
+-[2023-09-19 11:12:19,404][36021] Worker 2 uses CPU cores [8, 9, 10, 11]
+-[2023-09-19 11:12:19,410][36027] Worker 4 uses CPU cores [16, 17, 18, 19]
+-[2023-09-19 11:12:19,436][36025] Worker 7 uses CPU cores [28, 29, 30, 31]
+-[2023-09-19 11:12:19,436][36006] Starting seed is not provided
+-[2023-09-19 11:12:19,436][36006] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+-[2023-09-19 11:12:19,436][36006] Initializing actor-critic model on device cuda:0
+-[2023-09-19 11:12:19,437][36006] RunningMeanStd input shape: (376,)
+-[2023-09-19 11:12:19,437][36006] RunningMeanStd input shape: (1,)
+-[2023-09-19 11:12:19,528][36019] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+-[2023-09-19 11:12:19,529][36019] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0
+-[2023-09-19 11:12:19,530][36006] Created Actor Critic model with architecture:
+-[2023-09-19 11:12:19,530][36006] ActorCriticSharedWeights(
++[2023-09-21 15:10:43,177][99566] Saving configuration to ./train_dir/Standup/config.json...
++[2023-09-21 15:10:43,343][99566] Rollout worker 0 uses device cpu
++[2023-09-21 15:10:43,344][99566] Rollout worker 1 uses device cpu
++[2023-09-21 15:10:43,345][99566] Rollout worker 2 uses device cpu
++[2023-09-21 15:10:43,345][99566] Rollout worker 3 uses device cpu
++[2023-09-21 15:10:43,346][99566] Rollout worker 4 uses device cpu
++[2023-09-21 15:10:43,346][99566] Rollout worker 5 uses device cpu
++[2023-09-21 15:10:43,346][99566] Rollout worker 6 uses device cpu
++[2023-09-21 15:10:43,347][99566] Rollout worker 7 uses device cpu
++[2023-09-21 15:10:43,347][99566] In synchronous mode, we only accumulate one batch. Setting num_batches_to_accumulate to 1
++[2023-09-21 15:10:43,408][99566] Using GPUs [0] for process 0 (actually maps to GPUs [0])
++[2023-09-21 15:10:43,408][99566] InferenceWorker_p0-w0: min num requests: 1
++[2023-09-21 15:10:43,411][99566] Using GPUs [1] for process 1 (actually maps to GPUs [1])
++[2023-09-21 15:10:43,412][99566] InferenceWorker_p1-w0: min num requests: 1
++[2023-09-21 15:10:43,436][99566] Starting all processes...
++[2023-09-21 15:10:43,437][99566] Starting process learner_proc0
++[2023-09-21 15:10:43,439][99566] Starting process learner_proc1
++[2023-09-21 15:10:43,486][99566] Starting all processes...
++[2023-09-21 15:10:43,493][99566] Starting process inference_proc0-0
++[2023-09-21 15:10:43,493][99566] Starting process inference_proc1-0
++[2023-09-21 15:10:43,494][99566] Starting process rollout_proc0
++[2023-09-21 15:10:43,494][99566] Starting process rollout_proc1
++[2023-09-21 15:10:43,494][99566] Starting process rollout_proc2
++[2023-09-21 15:10:43,495][99566] Starting process rollout_proc3
++[2023-09-21 15:10:43,495][99566] Starting process rollout_proc4
++[2023-09-21 15:10:43,505][99566] Starting process rollout_proc5
++[2023-09-21 15:10:43,508][99566] Starting process rollout_proc6
++[2023-09-21 15:10:43,514][99566] Starting process rollout_proc7
++[2023-09-21 15:10:45,312][101035] Using GPUs [1] for process 1 (actually maps to GPUs [1])
++[2023-09-21 15:10:45,312][101035] Set environment var CUDA_VISIBLE_DEVICES to '1' (GPU indices [1]) for learning process 1
++[2023-09-21 15:10:45,328][101117] Using GPUs [1] for process 1 (actually maps to GPUs [1])
++[2023-09-21 15:10:45,328][101117] Set environment var CUDA_VISIBLE_DEVICES to '1' (GPU indices [1]) for inference process 1
++[2023-09-21 15:10:45,330][101035] Num visible devices: 1
++[2023-09-21 15:10:45,346][101117] Num visible devices: 1
++[2023-09-21 15:10:45,369][101035] Starting seed is not provided
++[2023-09-21 15:10:45,370][101035] Using GPUs [0] for process 1 (actually maps to GPUs [1])
++[2023-09-21 15:10:45,370][101035] Initializing actor-critic model on device cuda:0
++[2023-09-21 15:10:45,370][101035] RunningMeanStd input shape: (376,)
++[2023-09-21 15:10:45,371][101035] RunningMeanStd input shape: (1,)
++[2023-09-21 15:10:45,373][101122] Worker 4 uses CPU cores [16, 17, 18, 19]
++[2023-09-21 15:10:45,392][101119] Worker 2 uses CPU cores [8, 9, 10, 11]
++[2023-09-21 15:10:45,415][101120] Worker 3 uses CPU cores [12, 13, 14, 15]
++[2023-09-21 15:10:45,415][101121] Worker 5 uses CPU cores [20, 21, 22, 23]
++[2023-09-21 15:10:45,421][101035] Created Actor Critic model with architecture:
++[2023-09-21 15:10:45,421][101035] ActorCriticSharedWeights(
+   (obs_normalizer): ObservationNormalizer(
+     (running_mean_std): RunningMeanStdDictInPlace(
+       (running_mean_std): ModuleDict(
+@@ -71,167 +73,21 @@
+     (distribution_linear): Linear(in_features=64, out_features=17, bias=True)
+   )
+ )
+-[2023-09-19 11:12:19,571][36019] Num visible devices: 1
+-[2023-09-19 11:12:19,598][36024] Worker 3 uses CPU cores [12, 13, 14, 15]
+-[2023-09-19 11:12:20,100][36006] Using optimizer <class 'torch.optim.adam.Adam'>
+-[2023-09-19 11:12:20,101][36006] No checkpoints found
+-[2023-09-19 11:12:20,101][36006] Did not load from checkpoint, starting from scratch!
+-[2023-09-19 11:12:20,101][36006] Initialized policy 0 weights for model version 0
+-[2023-09-19 11:12:20,103][36006] LearnerWorker_p0 finished initialization!
+-[2023-09-19 11:12:20,103][36006] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+-[2023-09-19 11:12:20,715][36019] RunningMeanStd input shape: (376,)
+-[2023-09-19 11:12:20,716][36019] RunningMeanStd input shape: (1,)
+-[2023-09-19 11:12:20,748][35316] Inference worker 0-0 is ready!
+-[2023-09-19 11:12:20,749][35316] All inference workers are ready! Signal rollout workers to start!
+-[2023-09-19 11:12:20,854][36024] Decorrelating experience for 0 frames...
+-[2023-09-19 11:12:20,855][36024] Decorrelating experience for 64 frames...
+-[2023-09-19 11:12:20,857][36025] Decorrelating experience for 0 frames...
+-[2023-09-19 11:12:20,858][36025] Decorrelating experience for 64 frames...
+-[2023-09-19 11:12:20,858][36026] Decorrelating experience for 0 frames...
+-[2023-09-19 11:12:20,858][36021] Decorrelating experience for 0 frames...
+-[2023-09-19 11:12:20,859][36026] Decorrelating experience for 64 frames...
+-[2023-09-19 11:12:20,859][36021] Decorrelating experience for 64 frames...
+-[2023-09-19 11:12:20,872][36027] Decorrelating experience for 0 frames...
+-[2023-09-19 11:12:20,873][36027] Decorrelating experience for 64 frames...
+-[2023-09-19 11:12:20,881][36022] Decorrelating experience for 0 frames...
+-[2023-09-19 11:12:20,882][36022] Decorrelating experience for 64 frames...
+-[2023-09-19 11:12:20,899][36020] Decorrelating experience for 0 frames...
+-[2023-09-19 11:12:20,899][36023] Decorrelating experience for 0 frames...
+-[2023-09-19 11:12:20,900][36023] Decorrelating experience for 64 frames...
+-[2023-09-19 11:12:20,900][36020] Decorrelating experience for 64 frames...
+-[2023-09-19 11:12:20,908][36024] Decorrelating experience for 128 frames...
+-[2023-09-19 11:12:20,910][36026] Decorrelating experience for 128 frames...
+-[2023-09-19 11:12:20,913][36025] Decorrelating experience for 128 frames...
+-[2023-09-19 11:12:20,915][36021] Decorrelating experience for 128 frames...
+-[2023-09-19 11:12:20,926][36027] Decorrelating experience for 128 frames...
+-[2023-09-19 11:12:20,938][36022] Decorrelating experience for 128 frames...
+-[2023-09-19 11:12:20,984][36023] Decorrelating experience for 128 frames...
+-[2023-09-19 11:12:20,986][36020] Decorrelating experience for 128 frames...
+-[2023-09-19 11:12:21,016][36026] Decorrelating experience for 192 frames...
+-[2023-09-19 11:12:21,017][36024] Decorrelating experience for 192 frames...
+-[2023-09-19 11:12:21,018][36021] Decorrelating experience for 192 frames...
+-[2023-09-19 11:12:21,021][36025] Decorrelating experience for 192 frames...
+-[2023-09-19 11:12:21,033][36027] Decorrelating experience for 192 frames...
+-[2023-09-19 11:12:21,055][36022] Decorrelating experience for 192 frames...
+-[2023-09-19 11:12:21,144][36023] Decorrelating experience for 192 frames...
+-[2023-09-19 11:12:21,150][36020] Decorrelating experience for 192 frames...
+-[2023-09-19 11:12:21,191][36021] Decorrelating experience for 256 frames...
+-[2023-09-19 11:12:21,191][36024] Decorrelating experience for 256 frames...
+-[2023-09-19 11:12:21,198][36025] Decorrelating experience for 256 frames...
+-[2023-09-19 11:12:21,200][36026] Decorrelating experience for 256 frames...
+-[2023-09-19 11:12:21,204][36027] Decorrelating experience for 256 frames...
+-[2023-09-19 11:12:21,236][36022] Decorrelating experience for 256 frames...
+-[2023-09-19 11:12:21,312][36023] Decorrelating experience for 256 frames...
+-[2023-09-19 11:12:21,320][36020] Decorrelating experience for 256 frames...
+-[2023-09-19 11:12:21,387][36021] Decorrelating experience for 320 frames...
+-[2023-09-19 11:12:21,402][36024] Decorrelating experience for 320 frames...
+-[2023-09-19 11:12:21,408][36027] Decorrelating experience for 320 frames...
+-[2023-09-19 11:12:21,411][36025] Decorrelating experience for 320 frames...
+-[2023-09-19 11:12:21,449][36026] Decorrelating experience for 320 frames...
+-[2023-09-19 11:12:21,456][36022] Decorrelating experience for 320 frames...
+-[2023-09-19 11:12:21,516][36023] Decorrelating experience for 320 frames...
+-[2023-09-19 11:12:21,526][36020] Decorrelating experience for 320 frames...
+-[2023-09-19 11:12:21,639][36021] Decorrelating experience for 384 frames...
+-[2023-09-19 11:12:21,667][36024] Decorrelating experience for 384 frames...
+-[2023-09-19 11:12:21,672][36027] Decorrelating experience for 384 frames...
+-[2023-09-19 11:12:21,679][36025] Decorrelating experience for 384 frames...
+-[2023-09-19 11:12:21,690][36026] Decorrelating experience for 384 frames...
+-[2023-09-19 11:12:21,727][36022] Decorrelating experience for 384 frames...
+-[2023-09-19 11:12:21,766][36020] Decorrelating experience for 384 frames...
+-[2023-09-19 11:12:21,777][36023] Decorrelating experience for 384 frames...
+-[2023-09-19 11:12:21,966][36021] Decorrelating experience for 448 frames...
+-[2023-09-19 11:12:21,974][36027] Decorrelating experience for 448 frames...
+-[2023-09-19 11:12:21,978][36024] Decorrelating experience for 448 frames...
+-[2023-09-19 11:12:21,991][36025] Decorrelating experience for 448 frames...
+-[2023-09-19 11:12:22,000][36026] Decorrelating experience for 448 frames...
+-[2023-09-19 11:12:22,066][36022] Decorrelating experience for 448 frames...
+-[2023-09-19 11:12:22,100][36020] Decorrelating experience for 448 frames...
+-[2023-09-19 11:12:22,150][36023] Decorrelating experience for 448 frames...
+-[2023-09-19 11:12:23,541][35316] Fps is (10 sec: nan, 60 sec: nan, 300 sec: nan). Total num frames: 0. Throughput: 0: nan. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
+-[2023-09-19 11:12:28,541][35316] Fps is (10 sec: 3276.8, 60 sec: 3276.8, 300 sec: 3276.8). Total num frames: 16384. Throughput: 0: 2365.6. Samples: 11828. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:12:28,544][36006] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000000032_16384.pth...
+-[2023-09-19 11:12:29,287][35316] Keyboard interrupt detected in the event loop EvtLoop [Runner_EvtLoop, process=main process 35316], exiting...
+-[2023-09-19 11:12:29,288][35316] Runner profile tree view:
+-main_loop: 11.8008
+-[2023-09-19 11:12:29,288][35316] Collected {0: 20480}, FPS: 1735.5
+-[2023-09-19 11:12:29,288][36006] Stopping Batcher_0...
+-[2023-09-19 11:12:29,289][36026] Stopping RolloutWorker_w6...
+-[2023-09-19 11:12:29,290][36026] Loop rollout_proc6_evt_loop terminating...
+-[2023-09-19 11:12:29,289][36006] Loop batcher_evt_loop terminating...
+-[2023-09-19 11:12:29,290][36027] Stopping RolloutWorker_w4...
+-[2023-09-19 11:12:29,290][36027] Loop rollout_proc4_evt_loop terminating...
+-[2023-09-19 11:12:29,290][36020] Stopping RolloutWorker_w1...
+-[2023-09-19 11:12:29,290][36023] Stopping RolloutWorker_w5...
+-[2023-09-19 11:12:29,290][36020] Loop rollout_proc1_evt_loop terminating...
+-[2023-09-19 11:12:29,290][36023] Loop rollout_proc5_evt_loop terminating...
+-[2023-09-19 11:12:29,290][36006] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000000040_20480.pth...
+-[2023-09-19 11:12:29,291][36022] Stopping RolloutWorker_w0...
+-[2023-09-19 11:12:29,291][36022] Loop rollout_proc0_evt_loop terminating...
+-[2023-09-19 11:12:29,291][36024] Stopping RolloutWorker_w3...
+-[2023-09-19 11:12:29,292][36024] Loop rollout_proc3_evt_loop terminating...
+-[2023-09-19 11:12:29,292][36021] Stopping RolloutWorker_w2...
+-[2023-09-19 11:12:29,292][36021] Loop rollout_proc2_evt_loop terminating...
+-[2023-09-19 11:12:29,294][36025] Stopping RolloutWorker_w7...
+-[2023-09-19 11:12:29,295][36025] Loop rollout_proc7_evt_loop terminating...
+-[2023-09-19 11:12:29,299][36006] Stopping LearnerWorker_p0...
+-[2023-09-19 11:12:29,300][36006] Loop learner_proc0_evt_loop terminating...
+-[2023-09-19 11:12:29,303][36019] Weights refcount: 2 0
+-[2023-09-19 11:12:29,304][36019] Stopping InferenceWorker_p0-w0...
+-[2023-09-19 11:12:29,304][36019] Loop inference_proc0-0_evt_loop terminating...
+-[2023-09-19 11:13:18,923][40303] Saving configuration to ./train_dir/Standup/config.json...
+-[2023-09-19 11:13:18,925][40303] Rollout worker 0 uses device cpu
+-[2023-09-19 11:13:18,926][40303] Rollout worker 1 uses device cpu
+-[2023-09-19 11:13:18,926][40303] Rollout worker 2 uses device cpu
+-[2023-09-19 11:13:18,927][40303] Rollout worker 3 uses device cpu
+-[2023-09-19 11:13:18,928][40303] Rollout worker 4 uses device cpu
+-[2023-09-19 11:13:18,928][40303] Rollout worker 5 uses device cpu
+-[2023-09-19 11:13:18,929][40303] Rollout worker 6 uses device cpu
+-[2023-09-19 11:13:18,929][40303] Rollout worker 7 uses device cpu
+-[2023-09-19 11:13:18,930][40303] In synchronous mode, we only accumulate one batch. Setting num_batches_to_accumulate to 1
+-[2023-09-19 11:13:18,986][40303] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+-[2023-09-19 11:13:18,986][40303] InferenceWorker_p0-w0: min num requests: 1
+-[2023-09-19 11:13:18,990][40303] Using GPUs [1] for process 1 (actually maps to GPUs [1])
+-[2023-09-19 11:13:18,990][40303] InferenceWorker_p1-w0: min num requests: 1
+-[2023-09-19 11:13:19,015][40303] Starting all processes...
+-[2023-09-19 11:13:19,015][40303] Starting process learner_proc0
+-[2023-09-19 11:13:19,018][40303] Starting process learner_proc1
+-[2023-09-19 11:13:19,065][40303] Starting all processes...
+-[2023-09-19 11:13:19,071][40303] Starting process inference_proc0-0
+-[2023-09-19 11:13:19,071][40303] Starting process inference_proc1-0
+-[2023-09-19 11:13:19,071][40303] Starting process rollout_proc0
+-[2023-09-19 11:13:19,071][40303] Starting process rollout_proc1
+-[2023-09-19 11:13:19,072][40303] Starting process rollout_proc2
+-[2023-09-19 11:13:19,072][40303] Starting process rollout_proc3
+-[2023-09-19 11:13:19,073][40303] Starting process rollout_proc4
+-[2023-09-19 11:13:19,074][40303] Starting process rollout_proc5
+-[2023-09-19 11:13:19,080][40303] Starting process rollout_proc6
+-[2023-09-19 11:13:19,081][40303] Starting process rollout_proc7
+-[2023-09-19 11:13:21,055][41278] Worker 2 uses CPU cores [8, 9, 10, 11]
+-[2023-09-19 11:13:21,063][41246] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+-[2023-09-19 11:13:21,063][41246] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0
+-[2023-09-19 11:13:21,068][41284] Worker 3 uses CPU cores [12, 13, 14, 15]
+-[2023-09-19 11:13:21,080][41271] Using GPUs [1] for process 1 (actually maps to GPUs [1])
+-[2023-09-19 11:13:21,080][41271] Set environment var CUDA_VISIBLE_DEVICES to '1' (GPU indices [1]) for inference process 1
+-[2023-09-19 11:13:21,083][41246] Num visible devices: 1
+-[2023-09-19 11:13:21,088][41292] Worker 5 uses CPU cores [20, 21, 22, 23]
+-[2023-09-19 11:13:21,100][41271] Num visible devices: 1
+-[2023-09-19 11:13:21,157][41272] Worker 0 uses CPU cores [0, 1, 2, 3]
+-[2023-09-19 11:13:21,187][41276] Worker 1 uses CPU cores [4, 5, 6, 7]
+-[2023-09-19 11:13:21,291][41291] Worker 7 uses CPU cores [28, 29, 30, 31]
+-[2023-09-19 11:13:21,319][41290] Worker 6 uses CPU cores [24, 25, 26, 27]
+-[2023-09-19 11:13:21,326][41287] Worker 4 uses CPU cores [16, 17, 18, 19]
+-[2023-09-19 11:13:21,373][41187] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+-[2023-09-19 11:13:21,373][41187] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0
+-[2023-09-19 11:13:21,391][41187] Num visible devices: 1
+-[2023-09-19 11:13:21,412][41187] Starting seed is not provided
+-[2023-09-19 11:13:21,412][41187] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+-[2023-09-19 11:13:21,412][41187] Initializing actor-critic model on device cuda:0
+-[2023-09-19 11:13:21,413][41187] RunningMeanStd input shape: (376,)
+-[2023-09-19 11:13:21,413][41187] RunningMeanStd input shape: (1,)
+-[2023-09-19 11:13:21,450][41188] Using GPUs [1] for process 1 (actually maps to GPUs [1])
+-[2023-09-19 11:13:21,450][41188] Set environment var CUDA_VISIBLE_DEVICES to '1' (GPU indices [1]) for learning process 1
+-[2023-09-19 11:13:21,461][41187] Created Actor Critic model with architecture:
+-[2023-09-19 11:13:21,462][41187] ActorCriticSharedWeights(
++[2023-09-21 15:10:45,459][101034] Using GPUs [0] for process 0 (actually maps to GPUs [0])
++[2023-09-21 15:10:45,459][101034] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0
++[2023-09-21 15:10:45,470][101124] Worker 7 uses CPU cores [28, 29, 30, 31]
++[2023-09-21 15:10:45,484][101123] Worker 6 uses CPU cores [24, 25, 26, 27]
++[2023-09-21 15:10:45,490][101034] Num visible devices: 1
++[2023-09-21 15:10:45,528][101034] Starting seed is not provided
++[2023-09-21 15:10:45,528][101034] Using GPUs [0] for process 0 (actually maps to GPUs [0])
++[2023-09-21 15:10:45,528][101034] Initializing actor-critic model on device cuda:0
++[2023-09-21 15:10:45,529][101034] RunningMeanStd input shape: (376,)
++[2023-09-21 15:10:45,530][101034] RunningMeanStd input shape: (1,)
++[2023-09-21 15:10:45,552][101115] Using GPUs [0] for process 0 (actually maps to GPUs [0])
++[2023-09-21 15:10:45,552][101115] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0
++[2023-09-21 15:10:45,570][101115] Num visible devices: 1
++[2023-09-21 15:10:45,580][101034] Created Actor Critic model with architecture:
++[2023-09-21 15:10:45,581][101034] ActorCriticSharedWeights(
+   (obs_normalizer): ObservationNormalizer(
+     (running_mean_std): RunningMeanStdDictInPlace(
+       (running_mean_std): ModuleDict(
+@@ -262,2573 +118,537 @@ main_loop: 11.8008
+     (distribution_linear): Linear(in_features=64, out_features=17, bias=True)
+   )
+ )
+-[2023-09-19 11:13:21,478][41188] Num visible devices: 1
+-[2023-09-19 11:13:21,500][41188] Starting seed is not provided
+-[2023-09-19 11:13:21,500][41188] Using GPUs [0] for process 1 (actually maps to GPUs [1])
+-[2023-09-19 11:13:21,500][41188] Initializing actor-critic model on device cuda:0
+-[2023-09-19 11:13:21,501][41188] RunningMeanStd input shape: (376,)
+-[2023-09-19 11:13:21,501][41188] RunningMeanStd input shape: (1,)
+-[2023-09-19 11:13:21,548][41188] Created Actor Critic model with architecture:
+-[2023-09-19 11:13:21,548][41188] ActorCriticSharedWeights(
+-  (obs_normalizer): ObservationNormalizer(
+-    (running_mean_std): RunningMeanStdDictInPlace(
+-      (running_mean_std): ModuleDict(
+-        (obs): RunningMeanStdInPlace()
+-      )
+-    )
+-  )
+-  (returns_normalizer): RecursiveScriptModule(original_name=RunningMeanStdInPlace)
+-  (encoder): MultiInputEncoder(
+-    (encoders): ModuleDict(
+-      (obs): MlpEncoder(
+-        (mlp_head): RecursiveScriptModule(
+-          original_name=Sequential
+-          (0): RecursiveScriptModule(original_name=Linear)
+-          (1): RecursiveScriptModule(original_name=Tanh)
+-          (2): RecursiveScriptModule(original_name=Linear)
+-          (3): RecursiveScriptModule(original_name=Tanh)
+-        )
+-      )
+-    )
+-  )
+-  (core): ModelCoreIdentity()
+-  (decoder): MlpDecoder(
+-    (mlp): Identity()
+-  )
+-  (critic_linear): Linear(in_features=64, out_features=1, bias=True)
+-  (action_parameterization): ActionParameterizationContinuousNonAdaptiveStddev(
+-    (distribution_linear): Linear(in_features=64, out_features=17, bias=True)
+-  )
+-)
+-[2023-09-19 11:13:22,080][41187] Using optimizer <class 'torch.optim.adam.Adam'>
+-[2023-09-19 11:13:22,081][41187] Loading state from checkpoint ./train_dir/Standup/checkpoint_p0/checkpoint_000000040_20480.pth...
+-[2023-09-19 11:13:22,087][41187] Loading model from checkpoint
+-[2023-09-19 11:13:22,089][41187] Loaded experiment state at self.train_step=40, self.env_steps=20480
+-[2023-09-19 11:13:22,090][41187] Initialized policy 0 weights for model version 40
+-[2023-09-19 11:13:22,091][41187] LearnerWorker_p0 finished initialization!
+-[2023-09-19 11:13:22,092][41187] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+-[2023-09-19 11:13:22,122][41188] Using optimizer <class 'torch.optim.adam.Adam'>
+-[2023-09-19 11:13:22,123][41188] No checkpoints found
+-[2023-09-19 11:13:22,123][41188] Did not load from checkpoint, starting from scratch!
+-[2023-09-19 11:13:22,124][41188] Initialized policy 1 weights for model version 0
+-[2023-09-19 11:13:22,142][41188] LearnerWorker_p1 finished initialization!
+-[2023-09-19 11:13:22,142][41188] Using GPUs [0] for process 1 (actually maps to GPUs [1])
+-[2023-09-19 11:13:22,704][41246] RunningMeanStd input shape: (376,)
+-[2023-09-19 11:13:22,705][41246] RunningMeanStd input shape: (1,)
+-[2023-09-19 11:13:22,718][41271] RunningMeanStd input shape: (376,)
+-[2023-09-19 11:13:22,718][41271] RunningMeanStd input shape: (1,)
+-[2023-09-19 11:13:22,737][40303] Inference worker 0-0 is ready!
+-[2023-09-19 11:13:22,750][40303] Inference worker 1-0 is ready!
+-[2023-09-19 11:13:22,751][40303] All inference workers are ready! Signal rollout workers to start!
+-[2023-09-19 11:13:22,845][41278] Decorrelating experience for 0 frames...
+-[2023-09-19 11:13:22,846][41278] Decorrelating experience for 64 frames...
+-[2023-09-19 11:13:22,852][41290] Decorrelating experience for 0 frames...
+-[2023-09-19 11:13:22,853][41290] Decorrelating experience for 64 frames...
+-[2023-09-19 11:13:22,872][41287] Decorrelating experience for 0 frames...
+-[2023-09-19 11:13:22,873][41287] Decorrelating experience for 64 frames...
+-[2023-09-19 11:13:22,886][41276] Decorrelating experience for 0 frames...
+-[2023-09-19 11:13:22,885][41272] Decorrelating experience for 0 frames...
+-[2023-09-19 11:13:22,886][41276] Decorrelating experience for 64 frames...
+-[2023-09-19 11:13:22,886][41272] Decorrelating experience for 64 frames...
+-[2023-09-19 11:13:22,893][41292] Decorrelating experience for 0 frames...
+-[2023-09-19 11:13:22,894][41292] Decorrelating experience for 64 frames...
+-[2023-09-19 11:13:22,899][41278] Decorrelating experience for 128 frames...
+-[2023-09-19 11:13:22,905][41291] Decorrelating experience for 0 frames...
+-[2023-09-19 11:13:22,905][41284] Decorrelating experience for 0 frames...
+-[2023-09-19 11:13:22,907][41284] Decorrelating experience for 64 frames...
+-[2023-09-19 11:13:22,907][41291] Decorrelating experience for 64 frames...
+-[2023-09-19 11:13:22,907][41290] Decorrelating experience for 128 frames...
+-[2023-09-19 11:13:22,939][41276] Decorrelating experience for 128 frames...
+-[2023-09-19 11:13:22,944][41287] Decorrelating experience for 128 frames...
+-[2023-09-19 11:13:22,957][41292] Decorrelating experience for 128 frames...
+-[2023-09-19 11:13:22,974][41272] Decorrelating experience for 128 frames...
+-[2023-09-19 11:13:22,990][41291] Decorrelating experience for 128 frames...
+-[2023-09-19 11:13:23,000][41284] Decorrelating experience for 128 frames...
+-[2023-09-19 11:13:23,003][41278] Decorrelating experience for 192 frames...
+-[2023-09-19 11:13:23,051][41290] Decorrelating experience for 192 frames...
+-[2023-09-19 11:13:23,056][41287] Decorrelating experience for 192 frames...
+-[2023-09-19 11:13:23,057][41292] Decorrelating experience for 192 frames...
+-[2023-09-19 11:13:23,102][41276] Decorrelating experience for 192 frames...
+-[2023-09-19 11:13:23,147][41272] Decorrelating experience for 192 frames...
+-[2023-09-19 11:13:23,170][41291] Decorrelating experience for 192 frames...
+-[2023-09-19 11:13:23,177][41278] Decorrelating experience for 256 frames...
+-[2023-09-19 11:13:23,180][41284] Decorrelating experience for 192 frames...
+-[2023-09-19 11:13:23,229][41292] Decorrelating experience for 256 frames...
+-[2023-09-19 11:13:23,230][41287] Decorrelating experience for 256 frames...
+-[2023-09-19 11:13:23,248][41290] Decorrelating experience for 256 frames...
+-[2023-09-19 11:13:23,374][41276] Decorrelating experience for 256 frames...
+-[2023-09-19 11:13:23,378][41278] Decorrelating experience for 320 frames...
+-[2023-09-19 11:13:23,426][41287] Decorrelating experience for 320 frames...
+-[2023-09-19 11:13:23,428][41272] Decorrelating experience for 256 frames...
+-[2023-09-19 11:13:23,429][41292] Decorrelating experience for 320 frames...
+-[2023-09-19 11:13:23,433][41291] Decorrelating experience for 256 frames...
+-[2023-09-19 11:13:23,434][41284] Decorrelating experience for 256 frames...
+-[2023-09-19 11:13:23,481][41290] Decorrelating experience for 320 frames...
+-[2023-09-19 11:13:23,626][41291] Decorrelating experience for 320 frames...
+-[2023-09-19 11:13:23,675][41278] Decorrelating experience for 384 frames...
+-[2023-09-19 11:13:23,680][41284] Decorrelating experience for 320 frames...
+-[2023-09-19 11:13:23,685][41292] Decorrelating experience for 384 frames...
+-[2023-09-19 11:13:23,686][41287] Decorrelating experience for 384 frames...
+-[2023-09-19 11:13:23,711][41276] Decorrelating experience for 320 frames...
+-[2023-09-19 11:13:23,748][41272] Decorrelating experience for 320 frames...
+-[2023-09-19 11:13:23,770][41290] Decorrelating experience for 384 frames...
+-[2023-09-19 11:13:23,868][41291] Decorrelating experience for 384 frames...
+-[2023-09-19 11:13:23,948][41284] Decorrelating experience for 384 frames...
+-[2023-09-19 11:13:23,986][41278] Decorrelating experience for 448 frames...
+-[2023-09-19 11:13:23,993][41292] Decorrelating experience for 448 frames...
+-[2023-09-19 11:13:23,995][41287] Decorrelating experience for 448 frames...
+-[2023-09-19 11:13:24,071][41290] Decorrelating experience for 448 frames...
+-[2023-09-19 11:13:24,113][41276] Decorrelating experience for 384 frames...
+-[2023-09-19 11:13:24,140][41272] Decorrelating experience for 384 frames...
+-[2023-09-19 11:13:24,170][41291] Decorrelating experience for 448 frames...
+-[2023-09-19 11:13:24,250][41284] Decorrelating experience for 448 frames...
+-[2023-09-19 11:13:24,433][41276] Decorrelating experience for 448 frames...
+-[2023-09-19 11:13:24,471][41272] Decorrelating experience for 448 frames...
+-[2023-09-19 11:13:25,197][40303] Fps is (10 sec: nan, 60 sec: nan, 300 sec: nan). Total num frames: 20480. Throughput: 0: nan, 1: nan. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
+-[2023-09-19 11:13:30,198][40303] Fps is (10 sec: 3276.7, 60 sec: 3276.7, 300 sec: 3276.7). Total num frames: 36864. Throughput: 0: 1638.4, 1: 1638.4. Samples: 16384. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:13:30,200][41187] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000000056_28672.pth...
+-[2023-09-19 11:13:30,201][41188] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000000016_8192.pth...
+-[2023-09-19 11:13:30,211][41187] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000000032_16384.pth
+-[2023-09-19 11:13:35,197][40303] Fps is (10 sec: 4915.2, 60 sec: 4915.2, 300 sec: 4915.2). Total num frames: 69632. Throughput: 0: 2621.6, 1: 2627.4. Samples: 52490. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0)
+-[2023-09-19 11:13:35,198][40303] Avg episode reward: [(0, '31454.083'), (1, '27038.960')]
+-[2023-09-19 11:13:38,652][41271] Updated weights for policy 1, policy_version 80 (0.0016)
+-[2023-09-19 11:13:38,652][41246] Updated weights for policy 0, policy_version 120 (0.0015)
+-[2023-09-19 11:13:38,973][40303] Heartbeat connected on Batcher_0
+-[2023-09-19 11:13:38,976][40303] Heartbeat connected on LearnerWorker_p0
+-[2023-09-19 11:13:38,979][40303] Heartbeat connected on Batcher_1
+-[2023-09-19 11:13:38,982][40303] Heartbeat connected on LearnerWorker_p1
+-[2023-09-19 11:13:38,989][40303] Heartbeat connected on InferenceWorker_p0-w0
+-[2023-09-19 11:13:38,992][40303] Heartbeat connected on InferenceWorker_p1-w0
+-[2023-09-19 11:13:38,998][40303] Heartbeat connected on RolloutWorker_w0
+-[2023-09-19 11:13:39,001][40303] Heartbeat connected on RolloutWorker_w1
+-[2023-09-19 11:13:39,004][40303] Heartbeat connected on RolloutWorker_w2
+-[2023-09-19 11:13:39,006][40303] Heartbeat connected on RolloutWorker_w3
+-[2023-09-19 11:13:39,008][40303] Heartbeat connected on RolloutWorker_w4
+-[2023-09-19 11:13:39,014][40303] Heartbeat connected on RolloutWorker_w5
+-[2023-09-19 11:13:39,018][40303] Heartbeat connected on RolloutWorker_w7
+-[2023-09-19 11:13:39,018][40303] Heartbeat connected on RolloutWorker_w6
+-[2023-09-19 11:13:40,198][40303] Fps is (10 sec: 7372.8, 60 sec: 6007.4, 300 sec: 6007.4). Total num frames: 110592. Throughput: 0: 2508.5, 1: 2511.7. Samples: 75304. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:13:40,199][40303] Avg episode reward: [(0, '34634.079'), (1, '30037.595')]
+-[2023-09-19 11:13:45,197][40303] Fps is (10 sec: 7372.8, 60 sec: 6144.0, 300 sec: 6144.0). Total num frames: 143360. Throughput: 0: 2989.8, 1: 2992.6. Samples: 119648. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0)
+-[2023-09-19 11:13:45,198][40303] Avg episode reward: [(0, '43292.280'), (1, '42584.158')]
+-[2023-09-19 11:13:45,201][41187] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000000160_81920.pth...
+-[2023-09-19 11:13:45,201][41188] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000000120_61440.pth...
+-[2023-09-19 11:13:45,207][41187] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000000040_20480.pth
+-[2023-09-19 11:13:49,800][41271] Updated weights for policy 1, policy_version 160 (0.0015)
+-[2023-09-19 11:13:49,801][41246] Updated weights for policy 0, policy_version 200 (0.0014)
+-[2023-09-19 11:13:50,198][40303] Fps is (10 sec: 7372.8, 60 sec: 6553.6, 300 sec: 6553.6). Total num frames: 184320. Throughput: 0: 3276.9, 1: 3276.9. Samples: 163844. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0)
+-[2023-09-19 11:13:50,199][40303] Avg episode reward: [(0, '43292.280'), (1, '44801.351')]
+-[2023-09-19 11:13:50,200][41187] Saving new best policy, reward=43292.280!
+-[2023-09-19 11:13:55,197][40303] Fps is (10 sec: 7372.8, 60 sec: 6553.6, 300 sec: 6553.6). Total num frames: 217088. Throughput: 0: 3089.5, 1: 3091.3. Samples: 185422. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:13:55,198][40303] Avg episode reward: [(0, '50284.168'), (1, '51051.259')]
+-[2023-09-19 11:13:55,199][41187] Saving new best policy, reward=50284.168!
+-[2023-09-19 11:14:00,198][40303] Fps is (10 sec: 6553.5, 60 sec: 6553.6, 300 sec: 6553.6). Total num frames: 249856. Throughput: 0: 3196.1, 1: 3197.6. Samples: 223782. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0)
+-[2023-09-19 11:14:00,199][40303] Avg episode reward: [(0, '53046.991'), (1, '53883.351')]
+-[2023-09-19 11:14:00,208][41187] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000000264_135168.pth...
+-[2023-09-19 11:14:00,208][41188] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000000224_114688.pth...
+-[2023-09-19 11:14:00,217][41188] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000000016_8192.pth
+-[2023-09-19 11:14:00,217][41187] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000000056_28672.pth
+-[2023-09-19 11:14:00,218][41188] Saving new best policy, reward=53883.351!
+-[2023-09-19 11:14:00,218][41187] Saving new best policy, reward=53046.991!
+-[2023-09-19 11:14:01,592][41271] Updated weights for policy 1, policy_version 240 (0.0012)
+-[2023-09-19 11:14:01,592][41246] Updated weights for policy 0, policy_version 280 (0.0013)
+-[2023-09-19 11:14:05,198][40303] Fps is (10 sec: 7372.7, 60 sec: 6758.4, 300 sec: 6758.4). Total num frames: 290816. Throughput: 0: 3357.1, 1: 3358.6. Samples: 268630. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0)
+-[2023-09-19 11:14:05,199][40303] Avg episode reward: [(0, '62279.408'), (1, '63904.672')]
+-[2023-09-19 11:14:05,200][41187] Saving new best policy, reward=62279.408!
+-[2023-09-19 11:14:05,200][41188] Saving new best policy, reward=63904.672!
+-[2023-09-19 11:14:10,197][40303] Fps is (10 sec: 7372.9, 60 sec: 6735.6, 300 sec: 6735.6). Total num frames: 323584. Throughput: 0: 3232.0, 1: 3233.1. Samples: 290930. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:14:10,198][40303] Avg episode reward: [(0, '66478.184'), (1, '70755.397')]
+-[2023-09-19 11:14:10,199][41188] Saving new best policy, reward=70755.397!
+-[2023-09-19 11:14:10,199][41187] Saving new best policy, reward=66478.184!
+-[2023-09-19 11:14:12,751][41271] Updated weights for policy 1, policy_version 320 (0.0010)
+-[2023-09-19 11:14:12,752][41246] Updated weights for policy 0, policy_version 360 (0.0015)
+-[2023-09-19 11:14:15,197][40303] Fps is (10 sec: 7372.9, 60 sec: 6881.3, 300 sec: 6881.3). Total num frames: 364544. Throughput: 0: 3545.5, 1: 3546.1. Samples: 335508. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:14:15,198][40303] Avg episode reward: [(0, '69427.017'), (1, '72462.244')]
+-[2023-09-19 11:14:15,204][41187] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000000376_192512.pth...
+-[2023-09-19 11:14:15,204][41188] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000000336_172032.pth...
+-[2023-09-19 11:14:15,208][41187] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000000160_81920.pth
+-[2023-09-19 11:14:15,209][41187] Saving new best policy, reward=69427.017!
+-[2023-09-19 11:14:15,211][41188] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000000120_61440.pth
+-[2023-09-19 11:14:15,211][41188] Saving new best policy, reward=72462.244!
+-[2023-09-19 11:14:20,197][40303] Fps is (10 sec: 7372.9, 60 sec: 6851.5, 300 sec: 6851.5). Total num frames: 397312. Throughput: 0: 3635.0, 1: 3635.0. Samples: 379638. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:14:20,198][40303] Avg episode reward: [(0, '73711.169'), (1, '77171.232')]
+-[2023-09-19 11:14:20,199][41187] Saving new best policy, reward=73711.169!
+-[2023-09-19 11:14:20,199][41188] Saving new best policy, reward=77171.232!
+-[2023-09-19 11:14:23,933][41246] Updated weights for policy 0, policy_version 440 (0.0013)
+-[2023-09-19 11:14:23,934][41271] Updated weights for policy 1, policy_version 400 (0.0011)
+-[2023-09-19 11:14:25,197][40303] Fps is (10 sec: 6553.6, 60 sec: 6826.7, 300 sec: 6826.7). Total num frames: 430080. Throughput: 0: 3632.2, 1: 3632.4. Samples: 402210. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:14:25,198][40303] Avg episode reward: [(0, '73688.883'), (1, '77171.232')]
+-[2023-09-19 11:14:30,198][40303] Fps is (10 sec: 7372.7, 60 sec: 7236.3, 300 sec: 6931.7). Total num frames: 471040. Throughput: 0: 3606.1, 1: 3606.2. Samples: 444202. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:14:30,198][40303] Avg episode reward: [(0, '76128.666'), (1, '83391.647')]
+-[2023-09-19 11:14:30,204][41187] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000000480_245760.pth...
+-[2023-09-19 11:14:30,205][41188] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000000440_225280.pth...
+-[2023-09-19 11:14:30,211][41187] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000000264_135168.pth
+-[2023-09-19 11:14:30,212][41187] Saving new best policy, reward=76128.666!
+-[2023-09-19 11:14:30,213][41188] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000000224_114688.pth
+-[2023-09-19 11:14:30,214][41188] Saving new best policy, reward=83391.647!
+-[2023-09-19 11:14:35,005][41271] Updated weights for policy 1, policy_version 480 (0.0015)
+-[2023-09-19 11:14:35,006][41246] Updated weights for policy 0, policy_version 520 (0.0013)
+-[2023-09-19 11:14:35,198][40303] Fps is (10 sec: 8191.9, 60 sec: 7372.8, 300 sec: 7021.7). Total num frames: 512000. Throughput: 0: 3626.8, 1: 3628.0. Samples: 490312. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0)
+-[2023-09-19 11:14:35,199][40303] Avg episode reward: [(0, '76490.813'), (1, '86333.937')]
+-[2023-09-19 11:14:35,200][41187] Saving new best policy, reward=76490.813!
+-[2023-09-19 11:14:35,200][41188] Saving new best policy, reward=86333.937!
+-[2023-09-19 11:14:40,198][40303] Fps is (10 sec: 7372.6, 60 sec: 7236.2, 300 sec: 6990.5). Total num frames: 544768. Throughput: 0: 3630.3, 1: 3630.3. Samples: 512152. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:14:40,199][40303] Avg episode reward: [(0, '78215.963'), (1, '88825.825')]
+-[2023-09-19 11:14:40,201][41187] Saving new best policy, reward=78215.963!
+-[2023-09-19 11:14:40,201][41188] Saving new best policy, reward=88825.825!
+-[2023-09-19 11:14:45,197][40303] Fps is (10 sec: 7372.9, 60 sec: 7372.8, 300 sec: 7065.6). Total num frames: 585728. Throughput: 0: 3707.3, 1: 3707.2. Samples: 557434. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0)
+-[2023-09-19 11:14:45,198][40303] Avg episode reward: [(0, '80179.767'), (1, '93784.048')]
+-[2023-09-19 11:14:45,208][41188] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000000552_282624.pth...
+-[2023-09-19 11:14:45,207][41187] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000000592_303104.pth...
+-[2023-09-19 11:14:45,216][41188] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000000336_172032.pth
+-[2023-09-19 11:14:45,216][41188] Saving new best policy, reward=93784.048!
+-[2023-09-19 11:14:45,219][41187] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000000376_192512.pth
+-[2023-09-19 11:14:45,220][41187] Saving new best policy, reward=80179.767!
+-[2023-09-19 11:14:46,154][41271] Updated weights for policy 1, policy_version 560 (0.0013)
+-[2023-09-19 11:14:46,154][41246] Updated weights for policy 0, policy_version 600 (0.0015)
+-[2023-09-19 11:14:50,198][40303] Fps is (10 sec: 7372.9, 60 sec: 7236.3, 300 sec: 7035.5). Total num frames: 618496. Throughput: 0: 3695.9, 1: 3695.8. Samples: 601256. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:14:50,199][40303] Avg episode reward: [(0, '81224.789'), (1, '95410.430')]
+-[2023-09-19 11:14:50,200][41187] Saving new best policy, reward=81224.789!
+-[2023-09-19 11:14:50,200][41188] Saving new best policy, reward=95410.430!
+-[2023-09-19 11:14:55,215][40303] Fps is (10 sec: 7359.6, 60 sec: 7370.6, 300 sec: 7098.3). Total num frames: 659456. Throughput: 0: 3656.8, 1: 3656.9. Samples: 620178. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0)
+-[2023-09-19 11:14:55,218][40303] Avg episode reward: [(0, '81804.261'), (1, '100729.706')]
+-[2023-09-19 11:14:55,219][41187] Saving new best policy, reward=81804.261!
+-[2023-09-19 11:14:55,219][41188] Saving new best policy, reward=100729.706!
+-[2023-09-19 11:14:57,288][41246] Updated weights for policy 0, policy_version 680 (0.0016)
+-[2023-09-19 11:14:57,288][41271] Updated weights for policy 1, policy_version 640 (0.0013)
+-[2023-09-19 11:15:00,198][40303] Fps is (10 sec: 7372.8, 60 sec: 7372.8, 300 sec: 7071.0). Total num frames: 692224. Throughput: 0: 3672.5, 1: 3673.2. Samples: 666064. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0)
+-[2023-09-19 11:15:00,198][40303] Avg episode reward: [(0, '81842.550'), (1, '102461.265')]
+-[2023-09-19 11:15:00,204][41188] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000000656_335872.pth...
+-[2023-09-19 11:15:00,204][41187] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000000696_356352.pth...
+-[2023-09-19 11:15:00,208][41188] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000000440_225280.pth
+-[2023-09-19 11:15:00,208][41188] Saving new best policy, reward=102461.265!
+-[2023-09-19 11:15:00,211][41187] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000000480_245760.pth
+-[2023-09-19 11:15:00,211][41187] Saving new best policy, reward=81842.550!
+-[2023-09-19 11:15:05,198][40303] Fps is (10 sec: 5744.7, 60 sec: 7099.7, 300 sec: 6963.2). Total num frames: 716800. Throughput: 0: 3578.5, 1: 3578.2. Samples: 701690. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:15:05,199][40303] Avg episode reward: [(0, '82742.948'), (1, '108945.356')]
+-[2023-09-19 11:15:05,200][41187] Saving new best policy, reward=82742.948!
+-[2023-09-19 11:15:05,200][41188] Saving new best policy, reward=108945.356!
+-[2023-09-19 11:15:09,873][41271] Updated weights for policy 1, policy_version 720 (0.0015)
+-[2023-09-19 11:15:09,873][41246] Updated weights for policy 0, policy_version 760 (0.0015)
+-[2023-09-19 11:15:10,198][40303] Fps is (10 sec: 6553.6, 60 sec: 7236.3, 300 sec: 7021.7). Total num frames: 757760. Throughput: 0: 3542.3, 1: 3541.1. Samples: 720964. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0)
+-[2023-09-19 11:15:10,199][40303] Avg episode reward: [(0, '83013.951'), (1, '110482.262')]
+-[2023-09-19 11:15:10,200][41187] Saving new best policy, reward=83013.951!
+-[2023-09-19 11:15:10,200][41188] Saving new best policy, reward=110482.262!
+-[2023-09-19 11:15:15,198][40303] Fps is (10 sec: 7372.7, 60 sec: 7099.7, 300 sec: 7000.4). Total num frames: 790528. Throughput: 0: 3537.8, 1: 3537.8. Samples: 762602. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
+-[2023-09-19 11:15:15,199][40303] Avg episode reward: [(0, '84790.627'), (1, '117040.476')]
+-[2023-09-19 11:15:15,208][41187] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000000792_405504.pth...
+-[2023-09-19 11:15:15,209][41188] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000000752_385024.pth...
+-[2023-09-19 11:15:15,215][41188] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000000552_282624.pth
+-[2023-09-19 11:15:15,216][41188] Saving new best policy, reward=117040.476!
+-[2023-09-19 11:15:15,218][41187] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000000592_303104.pth
+-[2023-09-19 11:15:15,219][41187] Saving new best policy, reward=84790.627!
+-[2023-09-19 11:15:20,197][40303] Fps is (10 sec: 6553.7, 60 sec: 7099.7, 300 sec: 6981.0). Total num frames: 823296. Throughput: 0: 3525.8, 1: 3526.0. Samples: 807640. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:15:20,198][40303] Avg episode reward: [(0, '86690.838'), (1, '119342.411')]
+-[2023-09-19 11:15:20,199][41188] Saving new best policy, reward=119342.411!
+-[2023-09-19 11:15:20,199][41187] Saving new best policy, reward=86690.838!
+-[2023-09-19 11:15:21,652][41271] Updated weights for policy 1, policy_version 800 (0.0011)
+-[2023-09-19 11:15:21,653][41246] Updated weights for policy 0, policy_version 840 (0.0015)
+-[2023-09-19 11:15:25,198][40303] Fps is (10 sec: 7372.9, 60 sec: 7236.2, 300 sec: 7031.5). Total num frames: 864256. Throughput: 0: 3502.0, 1: 3501.0. Samples: 827284. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:15:25,199][40303] Avg episode reward: [(0, '90539.601'), (1, '125734.908')]
+-[2023-09-19 11:15:25,200][41187] Saving new best policy, reward=90539.601!
+-[2023-09-19 11:15:25,200][41188] Saving new best policy, reward=125734.908!
+-[2023-09-19 11:15:30,198][40303] Fps is (10 sec: 8191.9, 60 sec: 7236.3, 300 sec: 7077.9). Total num frames: 905216. Throughput: 0: 3517.5, 1: 3518.0. Samples: 874032. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:15:30,198][40303] Avg episode reward: [(0, '92852.762'), (1, '132358.210')]
+-[2023-09-19 11:15:30,207][41187] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000000904_462848.pth...
+-[2023-09-19 11:15:30,207][41188] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000000864_442368.pth...
+-[2023-09-19 11:15:30,213][41188] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000000656_335872.pth
+-[2023-09-19 11:15:30,214][41188] Saving new best policy, reward=132358.210!
+-[2023-09-19 11:15:30,216][41187] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000000696_356352.pth
+-[2023-09-19 11:15:30,217][41187] Saving new best policy, reward=92852.762!
+-[2023-09-19 11:15:32,850][41271] Updated weights for policy 1, policy_version 880 (0.0013)
+-[2023-09-19 11:15:32,851][41246] Updated weights for policy 0, policy_version 920 (0.0013)
+-[2023-09-19 11:15:35,197][40303] Fps is (10 sec: 7372.9, 60 sec: 7099.7, 300 sec: 7057.7). Total num frames: 937984. Throughput: 0: 3497.4, 1: 3497.6. Samples: 916030. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:15:35,198][40303] Avg episode reward: [(0, '96297.528'), (1, '134666.372')]
+-[2023-09-19 11:15:35,199][41187] Saving new best policy, reward=96297.528!
+-[2023-09-19 11:15:35,200][41188] Saving new best policy, reward=134666.372!
+-[2023-09-19 11:15:40,198][40303] Fps is (10 sec: 6553.5, 60 sec: 7099.7, 300 sec: 7039.0). Total num frames: 970752. Throughput: 0: 3537.6, 1: 3537.8. Samples: 938444. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:15:40,199][40303] Avg episode reward: [(0, '101172.898'), (1, '137965.048')]
+-[2023-09-19 11:15:40,200][41187] Saving new best policy, reward=101172.898!
+-[2023-09-19 11:15:40,200][41188] Saving new best policy, reward=137965.048!
+-[2023-09-19 11:15:44,038][41246] Updated weights for policy 0, policy_version 1000 (0.0014)
+-[2023-09-19 11:15:44,038][41271] Updated weights for policy 1, policy_version 960 (0.0014)
+-[2023-09-19 11:15:45,197][40303] Fps is (10 sec: 6553.7, 60 sec: 6963.2, 300 sec: 7021.7). Total num frames: 1003520. Throughput: 0: 3519.5, 1: 3518.3. Samples: 982764. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:15:45,198][40303] Avg episode reward: [(0, '103392.205'), (1, '137965.048')]
+-[2023-09-19 11:15:45,205][41188] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000000968_495616.pth...
+-[2023-09-19 11:15:45,208][41188] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000000752_385024.pth
+-[2023-09-19 11:15:45,213][41187] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000001008_516096.pth...
+-[2023-09-19 11:15:45,217][41187] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000000792_405504.pth
+-[2023-09-19 11:15:45,218][41187] Saving new best policy, reward=103392.205!
+-[2023-09-19 11:15:50,198][40303] Fps is (10 sec: 7372.8, 60 sec: 7099.7, 300 sec: 7062.1). Total num frames: 1044480. Throughput: 0: 3604.8, 1: 3604.9. Samples: 1026124. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0)
+-[2023-09-19 11:15:50,199][40303] Avg episode reward: [(0, '112090.239'), (1, '141479.122')]
+-[2023-09-19 11:15:50,200][41187] Saving new best policy, reward=112090.239!
+-[2023-09-19 11:15:50,200][41188] Saving new best policy, reward=141479.122!
+-[2023-09-19 11:15:55,198][40303] Fps is (10 sec: 7372.6, 60 sec: 6965.3, 300 sec: 7045.1). Total num frames: 1077248. Throughput: 0: 3640.0, 1: 3640.1. Samples: 1048568. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
+-[2023-09-19 11:15:55,199][40303] Avg episode reward: [(0, '115037.292'), (1, '141360.147')]
+-[2023-09-19 11:15:55,200][41187] Saving new best policy, reward=115037.292!
+-[2023-09-19 11:15:55,356][41271] Updated weights for policy 1, policy_version 1040 (0.0016)
+-[2023-09-19 11:15:55,356][41246] Updated weights for policy 0, policy_version 1080 (0.0011)
+-[2023-09-19 11:16:00,198][40303] Fps is (10 sec: 7372.8, 60 sec: 7099.7, 300 sec: 7082.1). Total num frames: 1118208. Throughput: 0: 3634.6, 1: 3634.6. Samples: 1089716. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:16:00,199][40303] Avg episode reward: [(0, '121696.345'), (1, '143516.477')]
+-[2023-09-19 11:16:00,207][41187] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000001112_569344.pth...
+-[2023-09-19 11:16:00,207][41188] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000001072_548864.pth...
+-[2023-09-19 11:16:00,213][41187] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000000904_462848.pth
+-[2023-09-19 11:16:00,214][41187] Saving new best policy, reward=121696.345!
+-[2023-09-19 11:16:00,218][41188] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000000864_442368.pth
+-[2023-09-19 11:16:00,218][41188] Saving new best policy, reward=143516.477!
+-[2023-09-19 11:16:05,198][40303] Fps is (10 sec: 8192.0, 60 sec: 7372.8, 300 sec: 7116.8). Total num frames: 1159168. Throughput: 0: 3656.8, 1: 3657.0. Samples: 1136764. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
+-[2023-09-19 11:16:05,199][40303] Avg episode reward: [(0, '126501.030'), (1, '144413.674')]
+-[2023-09-19 11:16:05,200][41187] Saving new best policy, reward=126501.030!
+-[2023-09-19 11:16:05,200][41188] Saving new best policy, reward=144413.674!
+-[2023-09-19 11:16:06,100][41271] Updated weights for policy 1, policy_version 1120 (0.0013)
+-[2023-09-19 11:16:06,100][41246] Updated weights for policy 0, policy_version 1160 (0.0016)
+-[2023-09-19 11:16:10,197][40303] Fps is (10 sec: 7372.9, 60 sec: 7236.3, 300 sec: 7099.7). Total num frames: 1191936. Throughput: 0: 3691.9, 1: 3692.5. Samples: 1159578. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0)
+-[2023-09-19 11:16:10,198][40303] Avg episode reward: [(0, '132111.068'), (1, '146024.408')]
+-[2023-09-19 11:16:10,199][41187] Saving new best policy, reward=132111.068!
+-[2023-09-19 11:16:10,200][41188] Saving new best policy, reward=146024.408!
+-[2023-09-19 11:16:15,198][40303] Fps is (10 sec: 5734.4, 60 sec: 7099.7, 300 sec: 7035.5). Total num frames: 1216512. Throughput: 0: 3566.4, 1: 3565.5. Samples: 1194970. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0)
+-[2023-09-19 11:16:15,198][40303] Avg episode reward: [(0, '135452.407'), (1, '145133.020')]
+-[2023-09-19 11:16:15,205][41187] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000001208_618496.pth...
+-[2023-09-19 11:16:15,207][41188] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000001168_598016.pth...
+-[2023-09-19 11:16:15,217][41188] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000000968_495616.pth
+-[2023-09-19 11:16:15,218][41187] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000001008_516096.pth
+-[2023-09-19 11:16:15,218][41187] Saving new best policy, reward=135452.407!
+-[2023-09-19 11:16:19,680][41271] Updated weights for policy 1, policy_version 1200 (0.0013)
+-[2023-09-19 11:16:19,680][41246] Updated weights for policy 0, policy_version 1240 (0.0011)
+-[2023-09-19 11:16:20,198][40303] Fps is (10 sec: 5734.3, 60 sec: 7099.7, 300 sec: 7021.7). Total num frames: 1249280. Throughput: 0: 3480.7, 1: 3480.4. Samples: 1229280. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:16:20,199][40303] Avg episode reward: [(0, '138970.413'), (1, '144367.334')]
+-[2023-09-19 11:16:20,200][41187] Saving new best policy, reward=138970.413!
+-[2023-09-19 11:16:25,198][40303] Fps is (10 sec: 7372.8, 60 sec: 7099.7, 300 sec: 7054.2). Total num frames: 1290240. Throughput: 0: 3490.3, 1: 3490.3. Samples: 1252572. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0)
+-[2023-09-19 11:16:25,199][40303] Avg episode reward: [(0, '138954.797'), (1, '143024.613')]
+-[2023-09-19 11:16:30,198][40303] Fps is (10 sec: 7372.7, 60 sec: 6963.2, 300 sec: 7040.7). Total num frames: 1323008. Throughput: 0: 3514.6, 1: 3515.8. Samples: 1299130. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0)
+-[2023-09-19 11:16:30,199][40303] Avg episode reward: [(0, '138602.655'), (1, '141826.181')]
+-[2023-09-19 11:16:30,206][41187] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000001312_671744.pth...
+-[2023-09-19 11:16:30,207][41188] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000001272_651264.pth...
+-[2023-09-19 11:16:30,216][41187] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000001112_569344.pth
+-[2023-09-19 11:16:30,216][41188] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000001072_548864.pth
+-[2023-09-19 11:16:30,719][41246] Updated weights for policy 0, policy_version 1320 (0.0010)
+-[2023-09-19 11:16:30,720][41271] Updated weights for policy 1, policy_version 1280 (0.0015)
+-[2023-09-19 11:16:35,198][40303] Fps is (10 sec: 6553.6, 60 sec: 6963.2, 300 sec: 7027.9). Total num frames: 1355776. Throughput: 0: 3463.6, 1: 3463.8. Samples: 1337854. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
+-[2023-09-19 11:16:35,199][40303] Avg episode reward: [(0, '139704.889'), (1, '143172.712')]
+-[2023-09-19 11:16:35,200][41187] Saving new best policy, reward=139704.889!
+-[2023-09-19 11:16:40,197][40303] Fps is (10 sec: 6553.8, 60 sec: 6963.2, 300 sec: 7015.7). Total num frames: 1388544. Throughput: 0: 3470.0, 1: 3470.8. Samples: 1360900. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:16:40,198][40303] Avg episode reward: [(0, '140044.752'), (1, '143172.712')]
+-[2023-09-19 11:16:40,199][41187] Saving new best policy, reward=140044.752!
+-[2023-09-19 11:16:42,534][41246] Updated weights for policy 0, policy_version 1400 (0.0015)
+-[2023-09-19 11:16:42,534][41271] Updated weights for policy 1, policy_version 1360 (0.0013)
+-[2023-09-19 11:16:45,198][40303] Fps is (10 sec: 7372.7, 60 sec: 7099.7, 300 sec: 7045.1). Total num frames: 1429504. Throughput: 0: 3467.3, 1: 3466.8. Samples: 1401752. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0)
+-[2023-09-19 11:16:45,199][40303] Avg episode reward: [(0, '142593.411'), (1, '143339.303')]
+-[2023-09-19 11:16:45,209][41187] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000001416_724992.pth...
+-[2023-09-19 11:16:45,211][41188] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000001376_704512.pth...
+-[2023-09-19 11:16:45,219][41187] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000001208_618496.pth
+-[2023-09-19 11:16:45,220][41187] Saving new best policy, reward=142593.411!
+-[2023-09-19 11:16:45,221][41188] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000001168_598016.pth
+-[2023-09-19 11:16:50,198][40303] Fps is (10 sec: 7372.6, 60 sec: 6963.2, 300 sec: 7033.1). Total num frames: 1462272. Throughput: 0: 3406.2, 1: 3406.0. Samples: 1443310. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:16:50,199][40303] Avg episode reward: [(0, '142593.411'), (1, '143931.524')]
+-[2023-09-19 11:16:53,925][41271] Updated weights for policy 1, policy_version 1440 (0.0013)
+-[2023-09-19 11:16:53,925][41246] Updated weights for policy 0, policy_version 1480 (0.0014)
+-[2023-09-19 11:16:55,197][40303] Fps is (10 sec: 6553.8, 60 sec: 6963.2, 300 sec: 7021.7). Total num frames: 1495040. Throughput: 0: 3409.2, 1: 3408.4. Samples: 1466370. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0)
+-[2023-09-19 11:16:55,198][40303] Avg episode reward: [(0, '149470.139'), (1, '145636.804')]
+-[2023-09-19 11:16:55,217][41187] Saving new best policy, reward=149470.139!
+-[2023-09-19 11:17:00,198][40303] Fps is (10 sec: 7372.9, 60 sec: 6963.2, 300 sec: 7048.9). Total num frames: 1536000. Throughput: 0: 3492.7, 1: 3493.2. Samples: 1509334. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:17:00,198][40303] Avg episode reward: [(0, '153538.121'), (1, '146540.869')]
+-[2023-09-19 11:17:00,207][41187] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000001520_778240.pth...
+-[2023-09-19 11:17:00,207][41188] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000001480_757760.pth...
+-[2023-09-19 11:17:00,214][41188] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000001272_651264.pth
+-[2023-09-19 11:17:00,215][41188] Saving new best policy, reward=146540.869!
+-[2023-09-19 11:17:00,215][41187] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000001312_671744.pth
+-[2023-09-19 11:17:00,216][41187] Saving new best policy, reward=153538.121!
+-[2023-09-19 11:17:05,198][40303] Fps is (10 sec: 7372.6, 60 sec: 6826.7, 300 sec: 7037.7). Total num frames: 1568768. Throughput: 0: 3593.8, 1: 3594.0. Samples: 1552730. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:17:05,199][40303] Avg episode reward: [(0, '153219.886'), (1, '146009.885')]
+-[2023-09-19 11:17:05,296][41271] Updated weights for policy 1, policy_version 1520 (0.0013)
+-[2023-09-19 11:17:05,298][41246] Updated weights for policy 0, policy_version 1560 (0.0011)
+-[2023-09-19 11:17:10,197][40303] Fps is (10 sec: 7372.9, 60 sec: 6963.2, 300 sec: 7063.3). Total num frames: 1609728. Throughput: 0: 3560.3, 1: 3559.7. Samples: 1572972. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0)
+-[2023-09-19 11:17:10,198][40303] Avg episode reward: [(0, '152679.736'), (1, '148353.321')]
+-[2023-09-19 11:17:10,199][41188] Saving new best policy, reward=148353.321!
+-[2023-09-19 11:17:15,197][40303] Fps is (10 sec: 7372.9, 60 sec: 7099.7, 300 sec: 7052.2). Total num frames: 1642496. Throughput: 0: 3533.3, 1: 3532.9. Samples: 1617104. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
+-[2023-09-19 11:17:15,198][40303] Avg episode reward: [(0, '152608.632'), (1, '147785.111')]
+-[2023-09-19 11:17:15,204][41187] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000001624_831488.pth...
+-[2023-09-19 11:17:15,204][41188] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000001584_811008.pth...
+-[2023-09-19 11:17:15,211][41188] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000001376_704512.pth
+-[2023-09-19 11:17:15,212][41187] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000001416_724992.pth
+-[2023-09-19 11:17:17,037][41271] Updated weights for policy 1, policy_version 1600 (0.0014)
+-[2023-09-19 11:17:17,037][41246] Updated weights for policy 0, policy_version 1640 (0.0013)
+-[2023-09-19 11:17:20,198][40303] Fps is (10 sec: 6553.5, 60 sec: 7099.7, 300 sec: 7041.6). Total num frames: 1675264. Throughput: 0: 3521.5, 1: 3520.4. Samples: 1654740. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:17:20,199][40303] Avg episode reward: [(0, '153339.116'), (1, '146902.121')]
+-[2023-09-19 11:17:25,198][40303] Fps is (10 sec: 5734.3, 60 sec: 6826.7, 300 sec: 6997.3). Total num frames: 1699840. Throughput: 0: 3454.4, 1: 3454.3. Samples: 1671790. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:17:25,199][40303] Avg episode reward: [(0, '153197.923'), (1, '148121.368')]
+-[2023-09-19 11:17:29,838][41246] Updated weights for policy 0, policy_version 1720 (0.0013)
+-[2023-09-19 11:17:29,839][41271] Updated weights for policy 1, policy_version 1680 (0.0014)
+-[2023-09-19 11:17:30,198][40303] Fps is (10 sec: 6553.5, 60 sec: 6963.2, 300 sec: 7021.7). Total num frames: 1740800. Throughput: 0: 3465.9, 1: 3466.4. Samples: 1713704. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:17:30,199][40303] Avg episode reward: [(0, '149499.415'), (1, '148156.690')]
+-[2023-09-19 11:17:30,206][41187] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000001720_880640.pth...
+-[2023-09-19 11:17:30,207][41188] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000001680_860160.pth...
+-[2023-09-19 11:17:30,213][41187] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000001520_778240.pth
+-[2023-09-19 11:17:30,215][41188] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000001480_757760.pth
+-[2023-09-19 11:17:35,198][40303] Fps is (10 sec: 7372.8, 60 sec: 6963.2, 300 sec: 7012.3). Total num frames: 1773568. Throughput: 0: 3480.4, 1: 3480.4. Samples: 1756542. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0)
+-[2023-09-19 11:17:35,199][40303] Avg episode reward: [(0, '148300.205'), (1, '148607.536')]
+-[2023-09-19 11:17:35,200][41188] Saving new best policy, reward=148607.536!
+-[2023-09-19 11:17:40,198][40303] Fps is (10 sec: 7372.8, 60 sec: 7099.7, 300 sec: 7035.5). Total num frames: 1814528. Throughput: 0: 3459.8, 1: 3460.8. Samples: 1777800. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:17:40,199][40303] Avg episode reward: [(0, '148265.013'), (1, '149557.427')]
+-[2023-09-19 11:17:40,201][41188] Saving new best policy, reward=149557.427!
+-[2023-09-19 11:17:41,639][41271] Updated weights for policy 1, policy_version 1760 (0.0011)
+-[2023-09-19 11:17:41,639][41246] Updated weights for policy 0, policy_version 1800 (0.0015)
+-[2023-09-19 11:17:45,198][40303] Fps is (10 sec: 6553.5, 60 sec: 6826.7, 300 sec: 6994.7). Total num frames: 1839104. Throughput: 0: 3421.1, 1: 3421.1. Samples: 1817234. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
+-[2023-09-19 11:17:45,199][40303] Avg episode reward: [(0, '148265.013'), (1, '149557.427')]
+-[2023-09-19 11:17:45,233][41188] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000001784_913408.pth...
+-[2023-09-19 11:17:45,236][41188] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000001584_811008.pth
+-[2023-09-19 11:17:45,238][41187] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000001824_933888.pth...
+-[2023-09-19 11:17:45,242][41187] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000001624_831488.pth
+-[2023-09-19 11:17:50,198][40303] Fps is (10 sec: 6553.6, 60 sec: 6963.2, 300 sec: 7017.3). Total num frames: 1880064. Throughput: 0: 3389.4, 1: 3389.2. Samples: 1857766. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0)
+-[2023-09-19 11:17:50,199][40303] Avg episode reward: [(0, '148074.607'), (1, '152409.695')]
+-[2023-09-19 11:17:50,201][41188] Saving new best policy, reward=152409.695!
+-[2023-09-19 11:17:53,620][41246] Updated weights for policy 0, policy_version 1880 (0.0014)
+-[2023-09-19 11:17:53,621][41271] Updated weights for policy 1, policy_version 1840 (0.0015)
+-[2023-09-19 11:17:55,198][40303] Fps is (10 sec: 7372.9, 60 sec: 6963.2, 300 sec: 7008.7). Total num frames: 1912832. Throughput: 0: 3389.5, 1: 3390.0. Samples: 1878050. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0)
+-[2023-09-19 11:17:55,199][40303] Avg episode reward: [(0, '148074.607'), (1, '152273.875')]
+-[2023-09-19 11:18:00,198][40303] Fps is (10 sec: 6553.6, 60 sec: 6826.7, 300 sec: 7000.4). Total num frames: 1945600. Throughput: 0: 3345.4, 1: 3345.7. Samples: 1918202. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:18:00,198][40303] Avg episode reward: [(0, '153050.644'), (1, '152274.335')]
+-[2023-09-19 11:18:00,206][41188] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000001880_962560.pth...
+-[2023-09-19 11:18:00,206][41187] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000001920_983040.pth...
+-[2023-09-19 11:18:00,212][41188] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000001680_860160.pth
+-[2023-09-19 11:18:00,216][41187] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000001720_880640.pth
+-[2023-09-19 11:18:05,198][40303] Fps is (10 sec: 6553.7, 60 sec: 6826.7, 300 sec: 6992.5). Total num frames: 1978368. Throughput: 0: 3388.8, 1: 3389.7. Samples: 1959770. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:18:05,199][40303] Avg episode reward: [(0, '154101.029'), (1, '152166.485')]
+-[2023-09-19 11:18:05,200][41187] Saving new best policy, reward=154101.029!
+-[2023-09-19 11:18:05,611][41246] Updated weights for policy 0, policy_version 1960 (0.0016)
+-[2023-09-19 11:18:05,611][41271] Updated weights for policy 1, policy_version 1920 (0.0015)
+-[2023-09-19 11:18:10,198][40303] Fps is (10 sec: 6553.5, 60 sec: 6690.1, 300 sec: 6984.8). Total num frames: 2011136. Throughput: 0: 3449.6, 1: 3449.8. Samples: 1982264. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
+-[2023-09-19 11:18:10,199][40303] Avg episode reward: [(0, '156034.676'), (1, '151366.137')]
+-[2023-09-19 11:18:10,200][41187] Saving new best policy, reward=156034.676!
+-[2023-09-19 11:18:15,198][40303] Fps is (10 sec: 6553.4, 60 sec: 6690.1, 300 sec: 6977.3). Total num frames: 2043904. Throughput: 0: 3381.2, 1: 3381.2. Samples: 2018014. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:18:15,199][40303] Avg episode reward: [(0, '155164.894'), (1, '150838.954')]
+-[2023-09-19 11:18:15,207][41187] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000002016_1032192.pth...
+-[2023-09-19 11:18:15,207][41188] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000001976_1011712.pth...
+-[2023-09-19 11:18:15,217][41187] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000001824_933888.pth
+-[2023-09-19 11:18:15,217][41188] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000001784_913408.pth
+-[2023-09-19 11:18:18,102][41246] Updated weights for policy 0, policy_version 2040 (0.0012)
+-[2023-09-19 11:18:18,102][41271] Updated weights for policy 1, policy_version 2000 (0.0012)
+-[2023-09-19 11:18:20,198][40303] Fps is (10 sec: 6553.6, 60 sec: 6690.1, 300 sec: 6970.1). Total num frames: 2076672. Throughput: 0: 3371.1, 1: 3370.6. Samples: 2059918. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
+-[2023-09-19 11:18:20,199][40303] Avg episode reward: [(0, '155231.770'), (1, '150958.366')]
+-[2023-09-19 11:18:25,198][40303] Fps is (10 sec: 5734.5, 60 sec: 6690.1, 300 sec: 6997.9). Total num frames: 2101248. Throughput: 0: 3299.0, 1: 3299.1. Samples: 2074716. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
+-[2023-09-19 11:18:25,199][40303] Avg episode reward: [(0, '154273.430'), (1, '151002.496')]
+-[2023-09-19 11:18:30,198][40303] Fps is (10 sec: 5734.4, 60 sec: 6553.6, 300 sec: 6997.9). Total num frames: 2134016. Throughput: 0: 3270.6, 1: 3270.6. Samples: 2111590. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:18:30,198][40303] Avg episode reward: [(0, '155007.997'), (1, '150084.194')]
+-[2023-09-19 11:18:30,205][41188] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000002064_1056768.pth...
+-[2023-09-19 11:18:30,205][41187] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000002104_1077248.pth...
+-[2023-09-19 11:18:30,211][41188] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000001880_962560.pth
+-[2023-09-19 11:18:30,214][41187] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000001920_983040.pth
+-[2023-09-19 11:18:32,089][41271] Updated weights for policy 1, policy_version 2080 (0.0011)
+-[2023-09-19 11:18:32,090][41246] Updated weights for policy 0, policy_version 2120 (0.0012)
+-[2023-09-19 11:18:35,197][40303] Fps is (10 sec: 6553.7, 60 sec: 6553.6, 300 sec: 6970.1). Total num frames: 2166784. Throughput: 0: 3205.9, 1: 3205.1. Samples: 2146258. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:18:35,198][40303] Avg episode reward: [(0, '155007.997'), (1, '150624.279')]
+-[2023-09-19 11:18:40,198][40303] Fps is (10 sec: 6553.6, 60 sec: 6417.1, 300 sec: 6970.1). Total num frames: 2199552. Throughput: 0: 3184.1, 1: 3184.0. Samples: 2164612. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:18:40,199][40303] Avg episode reward: [(0, '145580.524'), (1, '151090.148')]
+-[2023-09-19 11:18:44,767][41271] Updated weights for policy 1, policy_version 2160 (0.0013)
+-[2023-09-19 11:18:44,768][41246] Updated weights for policy 0, policy_version 2200 (0.0014)
+-[2023-09-19 11:18:45,198][40303] Fps is (10 sec: 6553.5, 60 sec: 6553.6, 300 sec: 6942.4). Total num frames: 2232320. Throughput: 0: 3191.7, 1: 3191.8. Samples: 2205460. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
+-[2023-09-19 11:18:45,199][40303] Avg episode reward: [(0, '145607.879'), (1, '152391.555')]
+-[2023-09-19 11:18:45,208][41187] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000002200_1126400.pth...
+-[2023-09-19 11:18:45,208][41188] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000002160_1105920.pth...
+-[2023-09-19 11:18:45,214][41188] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000001976_1011712.pth
+-[2023-09-19 11:18:45,217][41187] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000002016_1032192.pth
+-[2023-09-19 11:18:50,197][40303] Fps is (10 sec: 6553.7, 60 sec: 6417.1, 300 sec: 6942.4). Total num frames: 2265088. Throughput: 0: 3173.6, 1: 3173.4. Samples: 2245384. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0)
+-[2023-09-19 11:18:50,198][40303] Avg episode reward: [(0, '141531.277'), (1, '153070.074')]
+-[2023-09-19 11:18:50,199][41188] Saving new best policy, reward=153070.074!
+-[2023-09-19 11:18:55,198][40303] Fps is (10 sec: 6553.6, 60 sec: 6417.1, 300 sec: 6942.4). Total num frames: 2297856. Throughput: 0: 3144.3, 1: 3144.4. Samples: 2265256. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0)
+-[2023-09-19 11:18:55,199][40303] Avg episode reward: [(0, '141531.277'), (1, '153134.366')]
+-[2023-09-19 11:18:55,200][41188] Saving new best policy, reward=153134.366!
+-[2023-09-19 11:18:57,266][41271] Updated weights for policy 1, policy_version 2240 (0.0014)
+-[2023-09-19 11:18:57,267][41246] Updated weights for policy 0, policy_version 2280 (0.0013)
+-[2023-09-19 11:19:00,198][40303] Fps is (10 sec: 6553.6, 60 sec: 6417.1, 300 sec: 6914.6). Total num frames: 2330624. Throughput: 0: 3181.9, 1: 3181.2. Samples: 2304352. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:19:00,198][40303] Avg episode reward: [(0, '140084.973'), (1, '153499.154')]
+-[2023-09-19 11:19:00,205][41187] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000002296_1175552.pth...
+-[2023-09-19 11:19:00,206][41188] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000002256_1155072.pth...
+-[2023-09-19 11:19:00,213][41188] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000002064_1056768.pth
+-[2023-09-19 11:19:00,213][41188] Saving new best policy, reward=153499.154!
+-[2023-09-19 11:19:00,214][41187] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000002104_1077248.pth
+-[2023-09-19 11:19:05,197][40303] Fps is (10 sec: 6553.7, 60 sec: 6417.1, 300 sec: 6914.6). Total num frames: 2363392. Throughput: 0: 3174.0, 1: 3174.3. Samples: 2345590. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:19:05,198][40303] Avg episode reward: [(0, '140163.997'), (1, '154850.945')]
+-[2023-09-19 11:19:05,199][41188] Saving new best policy, reward=154850.945!
+-[2023-09-19 11:19:09,431][41271] Updated weights for policy 1, policy_version 2320 (0.0012)
+-[2023-09-19 11:19:09,432][41246] Updated weights for policy 0, policy_version 2360 (0.0015)
+-[2023-09-19 11:19:10,198][40303] Fps is (10 sec: 6553.5, 60 sec: 6417.1, 300 sec: 6886.8). Total num frames: 2396160. Throughput: 0: 3226.4, 1: 3226.4. Samples: 2365092. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:19:10,199][40303] Avg episode reward: [(0, '146252.432'), (1, '155854.149')]
+-[2023-09-19 11:19:10,200][41188] Saving new best policy, reward=155854.149!
+-[2023-09-19 11:19:15,198][40303] Fps is (10 sec: 6553.5, 60 sec: 6417.1, 300 sec: 6886.8). Total num frames: 2428928. Throughput: 0: 3251.3, 1: 3251.4. Samples: 2404212. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
+-[2023-09-19 11:19:15,198][40303] Avg episode reward: [(0, '146450.850'), (1, '155450.882')]
+-[2023-09-19 11:19:15,205][41187] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000002392_1224704.pth...
+-[2023-09-19 11:19:15,206][41188] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000002352_1204224.pth...
+-[2023-09-19 11:19:15,216][41187] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000002200_1126400.pth
+-[2023-09-19 11:19:15,217][41188] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000002160_1105920.pth
+-[2023-09-19 11:19:16,564][40303] Keyboard interrupt detected in the event loop EvtLoop [Runner_EvtLoop, process=main process 40303], exiting...
+-[2023-09-19 11:19:16,565][40303] Runner profile tree view:
+-main_loop: 357.5508
+-[2023-09-19 11:19:16,566][41187] Stopping Batcher_0...
+-[2023-09-19 11:19:16,566][41187] Loop batcher_evt_loop terminating...
+-[2023-09-19 11:19:16,566][40303] Collected {0: 1228800, 1: 1208320}, FPS: 6758.9
+-[2023-09-19 11:19:16,566][41188] Stopping Batcher_1...
+-[2023-09-19 11:19:16,566][41188] Loop batcher_evt_loop terminating...
+-[2023-09-19 11:19:16,567][41188] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000002360_1208320.pth...
+-[2023-09-19 11:19:16,567][41287] Stopping RolloutWorker_w4...
+-[2023-09-19 11:19:16,567][41187] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000002400_1228800.pth...
+-[2023-09-19 11:19:16,567][41287] Loop rollout_proc4_evt_loop terminating...
+-[2023-09-19 11:19:16,569][41278] Stopping RolloutWorker_w2...
+-[2023-09-19 11:19:16,569][41276] Stopping RolloutWorker_w1...
+-[2023-09-19 11:19:16,569][41278] Loop rollout_proc2_evt_loop terminating...
+-[2023-09-19 11:19:16,569][41276] Loop rollout_proc1_evt_loop terminating...
+-[2023-09-19 11:19:16,570][41291] Stopping RolloutWorker_w7...
+-[2023-09-19 11:19:16,570][41291] Loop rollout_proc7_evt_loop terminating...
+-[2023-09-19 11:19:16,570][41272] Stopping RolloutWorker_w0...
+-[2023-09-19 11:19:16,570][41272] Loop rollout_proc0_evt_loop terminating...
+-[2023-09-19 11:19:16,571][41290] Stopping RolloutWorker_w6...
+-[2023-09-19 11:19:16,571][41290] Loop rollout_proc6_evt_loop terminating...
+-[2023-09-19 11:19:16,571][41284] Stopping RolloutWorker_w3...
+-[2023-09-19 11:19:16,571][41188] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000002256_1155072.pth
+-[2023-09-19 11:19:16,571][41284] Loop rollout_proc3_evt_loop terminating...
+-[2023-09-19 11:19:16,571][41292] Stopping RolloutWorker_w5...
+-[2023-09-19 11:19:16,572][41188] Stopping LearnerWorker_p1...
+-[2023-09-19 11:19:16,572][41292] Loop rollout_proc5_evt_loop terminating...
+-[2023-09-19 11:19:16,572][41188] Loop learner_proc1_evt_loop terminating...
+-[2023-09-19 11:19:16,575][41187] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000002296_1175552.pth
+-[2023-09-19 11:19:16,576][41187] Stopping LearnerWorker_p0...
+-[2023-09-19 11:19:16,576][41187] Loop learner_proc0_evt_loop terminating...
+-[2023-09-19 11:19:16,580][41246] Weights refcount: 2 0
+-[2023-09-19 11:19:16,581][41246] Stopping InferenceWorker_p0-w0...
+-[2023-09-19 11:19:16,581][41246] Loop inference_proc0-0_evt_loop terminating...
+-[2023-09-19 11:19:16,583][41271] Weights refcount: 2 0
+-[2023-09-19 11:19:16,584][41271] Stopping InferenceWorker_p1-w0...
+-[2023-09-19 11:19:16,584][41271] Loop inference_proc1-0_evt_loop terminating...
+-[2023-09-19 11:19:40,691][72530] Saving configuration to ./train_dir/Standup/config.json...
+-[2023-09-19 11:19:40,693][72530] Rollout worker 0 uses device cpu
+-[2023-09-19 11:19:40,694][72530] Rollout worker 1 uses device cpu
+-[2023-09-19 11:19:40,694][72530] Rollout worker 2 uses device cpu
+-[2023-09-19 11:19:40,695][72530] Rollout worker 3 uses device cpu
+-[2023-09-19 11:19:40,695][72530] Rollout worker 4 uses device cpu
+-[2023-09-19 11:19:40,695][72530] Rollout worker 5 uses device cpu
+-[2023-09-19 11:19:40,696][72530] Rollout worker 6 uses device cpu
+-[2023-09-19 11:19:40,696][72530] Rollout worker 7 uses device cpu
+-[2023-09-19 11:19:40,696][72530] In synchronous mode, we only accumulate one batch. Setting num_batches_to_accumulate to 1
+-[2023-09-19 11:19:40,753][72530] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+-[2023-09-19 11:19:40,753][72530] InferenceWorker_p0-w0: min num requests: 1
+-[2023-09-19 11:19:40,757][72530] Using GPUs [1] for process 1 (actually maps to GPUs [1])
+-[2023-09-19 11:19:40,757][72530] InferenceWorker_p1-w0: min num requests: 1
+-[2023-09-19 11:19:40,783][72530] Starting all processes...
+-[2023-09-19 11:19:40,783][72530] Starting process learner_proc0
+-[2023-09-19 11:19:40,786][72530] Starting process learner_proc1
+-[2023-09-19 11:19:40,832][72530] Starting all processes...
+-[2023-09-19 11:19:40,838][72530] Starting process inference_proc0-0
+-[2023-09-19 11:19:40,838][72530] Starting process inference_proc1-0
+-[2023-09-19 11:19:40,838][72530] Starting process rollout_proc0
+-[2023-09-19 11:19:40,839][72530] Starting process rollout_proc1
+-[2023-09-19 11:19:40,839][72530] Starting process rollout_proc2
+-[2023-09-19 11:19:40,839][72530] Starting process rollout_proc3
+-[2023-09-19 11:19:40,840][72530] Starting process rollout_proc4
+-[2023-09-19 11:19:40,843][72530] Starting process rollout_proc5
+-[2023-09-19 11:19:40,843][72530] Starting process rollout_proc6
+-[2023-09-19 11:19:40,844][72530] Starting process rollout_proc7
+-[2023-09-19 11:19:42,632][73131] Using GPUs [1] for process 1 (actually maps to GPUs [1])
+-[2023-09-19 11:19:42,632][73131] Set environment var CUDA_VISIBLE_DEVICES to '1' (GPU indices [1]) for learning process 1
+-[2023-09-19 11:19:42,651][73131] Num visible devices: 1
+-[2023-09-19 11:19:42,668][73131] Starting seed is not provided
+-[2023-09-19 11:19:42,669][73131] Using GPUs [0] for process 1 (actually maps to GPUs [1])
+-[2023-09-19 11:19:42,669][73131] Initializing actor-critic model on device cuda:0
+-[2023-09-19 11:19:42,670][73131] RunningMeanStd input shape: (376,)
+-[2023-09-19 11:19:42,670][73131] RunningMeanStd input shape: (1,)
+-[2023-09-19 11:19:42,680][73130] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+-[2023-09-19 11:19:42,681][73130] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0
+-[2023-09-19 11:19:42,683][73226] Worker 7 uses CPU cores [28, 29, 30, 31]
+-[2023-09-19 11:19:42,694][73220] Worker 2 uses CPU cores [8, 9, 10, 11]
+-[2023-09-19 11:19:42,701][73130] Num visible devices: 1
+-[2023-09-19 11:19:42,723][73222] Worker 6 uses CPU cores [24, 25, 26, 27]
+-[2023-09-19 11:19:42,725][73130] Starting seed is not provided
+-[2023-09-19 11:19:42,725][73130] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+-[2023-09-19 11:19:42,725][73130] Initializing actor-critic model on device cuda:0
+-[2023-09-19 11:19:42,725][73130] RunningMeanStd input shape: (376,)
+-[2023-09-19 11:19:42,726][73130] RunningMeanStd input shape: (1,)
+-[2023-09-19 11:19:42,731][73224] Worker 4 uses CPU cores [16, 17, 18, 19]
+-[2023-09-19 11:19:42,733][73131] Created Actor Critic model with architecture:
+-[2023-09-19 11:19:42,734][73131] ActorCriticSharedWeights(
+-  (obs_normalizer): ObservationNormalizer(
+-    (running_mean_std): RunningMeanStdDictInPlace(
+-      (running_mean_std): ModuleDict(
+-        (obs): RunningMeanStdInPlace()
+-      )
+-    )
+-  )
+-  (returns_normalizer): RecursiveScriptModule(original_name=RunningMeanStdInPlace)
+-  (encoder): MultiInputEncoder(
+-    (encoders): ModuleDict(
+-      (obs): MlpEncoder(
+-        (mlp_head): RecursiveScriptModule(
+-          original_name=Sequential
+-          (0): RecursiveScriptModule(original_name=Linear)
+-          (1): RecursiveScriptModule(original_name=Tanh)
+-          (2): RecursiveScriptModule(original_name=Linear)
+-          (3): RecursiveScriptModule(original_name=Tanh)
+-        )
+-      )
+-    )
+-  )
+-  (core): ModelCoreIdentity()
+-  (decoder): MlpDecoder(
+-    (mlp): Identity()
+-  )
+-  (critic_linear): Linear(in_features=64, out_features=1, bias=True)
+-  (action_parameterization): ActionParameterizationContinuousNonAdaptiveStddev(
+-    (distribution_linear): Linear(in_features=64, out_features=17, bias=True)
+-  )
+-)
+-[2023-09-19 11:19:42,740][73219] Using GPUs [1] for process 1 (actually maps to GPUs [1])
+-[2023-09-19 11:19:42,740][73219] Set environment var CUDA_VISIBLE_DEVICES to '1' (GPU indices [1]) for inference process 1
+-[2023-09-19 11:19:42,756][73145] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+-[2023-09-19 11:19:42,756][73145] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0
+-[2023-09-19 11:19:42,787][73145] Num visible devices: 1
+-[2023-09-19 11:19:42,787][73219] Num visible devices: 1
+-[2023-09-19 11:19:42,797][73130] Created Actor Critic model with architecture:
+-[2023-09-19 11:19:42,797][73130] ActorCriticSharedWeights(
+-  (obs_normalizer): ObservationNormalizer(
+-    (running_mean_std): RunningMeanStdDictInPlace(
+-      (running_mean_std): ModuleDict(
+-        (obs): RunningMeanStdInPlace()
+-      )
+-    )
+-  )
+-  (returns_normalizer): RecursiveScriptModule(original_name=RunningMeanStdInPlace)
+-  (encoder): MultiInputEncoder(
+-    (encoders): ModuleDict(
+-      (obs): MlpEncoder(
+-        (mlp_head): RecursiveScriptModule(
+-          original_name=Sequential
+-          (0): RecursiveScriptModule(original_name=Linear)
+-          (1): RecursiveScriptModule(original_name=Tanh)
+-          (2): RecursiveScriptModule(original_name=Linear)
+-          (3): RecursiveScriptModule(original_name=Tanh)
+-        )
+-      )
+-    )
+-  )
+-  (core): ModelCoreIdentity()
+-  (decoder): MlpDecoder(
+-    (mlp): Identity()
+-  )
+-  (critic_linear): Linear(in_features=64, out_features=1, bias=True)
+-  (action_parameterization): ActionParameterizationContinuousNonAdaptiveStddev(
+-    (distribution_linear): Linear(in_features=64, out_features=17, bias=True)
+-  )
+-)
+-[2023-09-19 11:19:42,798][73221] Worker 1 uses CPU cores [4, 5, 6, 7]
+-[2023-09-19 11:19:42,939][73223] Worker 3 uses CPU cores [12, 13, 14, 15]
+-[2023-09-19 11:19:43,116][73229] Worker 5 uses CPU cores [20, 21, 22, 23]
+-[2023-09-19 11:19:43,205][73218] Worker 0 uses CPU cores [0, 1, 2, 3]
+-[2023-09-19 11:19:43,373][73131] Using optimizer <class 'torch.optim.adam.Adam'>
+-[2023-09-19 11:19:43,373][73131] Loading state from checkpoint ./train_dir/Standup/checkpoint_p1/checkpoint_000002360_1208320.pth...
+-[2023-09-19 11:19:43,379][73131] Loading model from checkpoint
+-[2023-09-19 11:19:43,381][73131] Loaded experiment state at self.train_step=2360, self.env_steps=1208320
+-[2023-09-19 11:19:43,382][73131] Initialized policy 1 weights for model version 2360
+-[2023-09-19 11:19:43,383][73131] LearnerWorker_p1 finished initialization!
+-[2023-09-19 11:19:43,383][73131] Using GPUs [0] for process 1 (actually maps to GPUs [1])
+-[2023-09-19 11:19:43,409][73130] Using optimizer <class 'torch.optim.adam.Adam'>
+-[2023-09-19 11:19:43,410][73130] Loading state from checkpoint ./train_dir/Standup/checkpoint_p0/checkpoint_000002400_1228800.pth...
+-[2023-09-19 11:19:43,416][73130] Loading model from checkpoint
+-[2023-09-19 11:19:43,419][73130] Loaded experiment state at self.train_step=2400, self.env_steps=1228800
+-[2023-09-19 11:19:43,419][73130] Initialized policy 0 weights for model version 2400
+-[2023-09-19 11:19:43,427][73130] LearnerWorker_p0 finished initialization!
+-[2023-09-19 11:19:43,427][73130] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+-[2023-09-19 11:19:43,971][73219] RunningMeanStd input shape: (376,)
+-[2023-09-19 11:19:43,971][73219] RunningMeanStd input shape: (1,)
+-[2023-09-19 11:19:43,987][73145] RunningMeanStd input shape: (376,)
+-[2023-09-19 11:19:43,987][73145] RunningMeanStd input shape: (1,)
+-[2023-09-19 11:19:44,004][72530] Inference worker 1-0 is ready!
+-[2023-09-19 11:19:44,021][72530] Inference worker 0-0 is ready!
+-[2023-09-19 11:19:44,022][72530] All inference workers are ready! Signal rollout workers to start!
+-[2023-09-19 11:19:44,118][73223] Decorrelating experience for 0 frames...
+-[2023-09-19 11:19:44,119][73223] Decorrelating experience for 64 frames...
+-[2023-09-19 11:19:44,120][73229] Decorrelating experience for 0 frames...
+-[2023-09-19 11:19:44,121][73229] Decorrelating experience for 64 frames...
+-[2023-09-19 11:19:44,122][73221] Decorrelating experience for 0 frames...
+-[2023-09-19 11:19:44,123][73221] Decorrelating experience for 64 frames...
+-[2023-09-19 11:19:44,128][73226] Decorrelating experience for 0 frames...
+-[2023-09-19 11:19:44,128][73226] Decorrelating experience for 64 frames...
+-[2023-09-19 11:19:44,132][73220] Decorrelating experience for 0 frames...
+-[2023-09-19 11:19:44,133][73220] Decorrelating experience for 64 frames...
+-[2023-09-19 11:19:44,141][73222] Decorrelating experience for 0 frames...
+-[2023-09-19 11:19:44,142][73222] Decorrelating experience for 64 frames...
+-[2023-09-19 11:19:44,157][73224] Decorrelating experience for 0 frames...
+-[2023-09-19 11:19:44,158][73224] Decorrelating experience for 64 frames...
+-[2023-09-19 11:19:44,161][73218] Decorrelating experience for 0 frames...
+-[2023-09-19 11:19:44,162][73218] Decorrelating experience for 64 frames...
+-[2023-09-19 11:19:44,168][73223] Decorrelating experience for 128 frames...
+-[2023-09-19 11:19:44,171][73229] Decorrelating experience for 128 frames...
+-[2023-09-19 11:19:44,175][73221] Decorrelating experience for 128 frames...
+-[2023-09-19 11:19:44,181][73226] Decorrelating experience for 128 frames...
+-[2023-09-19 11:19:44,199][73220] Decorrelating experience for 128 frames...
+-[2023-09-19 11:19:44,200][73222] Decorrelating experience for 128 frames...
+-[2023-09-19 11:19:44,222][73224] Decorrelating experience for 128 frames...
+-[2023-09-19 11:19:44,243][73218] Decorrelating experience for 128 frames...
+-[2023-09-19 11:19:44,273][73223] Decorrelating experience for 192 frames...
+-[2023-09-19 11:19:44,277][73229] Decorrelating experience for 192 frames...
+-[2023-09-19 11:19:44,281][73221] Decorrelating experience for 192 frames...
+-[2023-09-19 11:19:44,284][73226] Decorrelating experience for 192 frames...
+-[2023-09-19 11:19:44,299][73222] Decorrelating experience for 192 frames...
+-[2023-09-19 11:19:44,304][73220] Decorrelating experience for 192 frames...
+-[2023-09-19 11:19:44,319][73224] Decorrelating experience for 192 frames...
+-[2023-09-19 11:19:44,368][73218] Decorrelating experience for 192 frames...
+-[2023-09-19 11:19:44,444][73223] Decorrelating experience for 256 frames...
+-[2023-09-19 11:19:44,447][73229] Decorrelating experience for 256 frames...
+-[2023-09-19 11:19:44,457][73226] Decorrelating experience for 256 frames...
+-[2023-09-19 11:19:44,462][73221] Decorrelating experience for 256 frames...
+-[2023-09-19 11:19:44,476][73222] Decorrelating experience for 256 frames...
+-[2023-09-19 11:19:44,492][73220] Decorrelating experience for 256 frames...
+-[2023-09-19 11:19:44,499][73224] Decorrelating experience for 256 frames...
+-[2023-09-19 11:19:44,575][73218] Decorrelating experience for 256 frames...
+-[2023-09-19 11:19:44,651][73223] Decorrelating experience for 320 frames...
+-[2023-09-19 11:19:44,657][73229] Decorrelating experience for 320 frames...
+-[2023-09-19 11:19:44,666][73226] Decorrelating experience for 320 frames...
+-[2023-09-19 11:19:44,681][73221] Decorrelating experience for 320 frames...
+-[2023-09-19 11:19:44,689][73222] Decorrelating experience for 320 frames...
+-[2023-09-19 11:19:44,707][73220] Decorrelating experience for 320 frames...
+-[2023-09-19 11:19:44,714][73224] Decorrelating experience for 320 frames...
+-[2023-09-19 11:19:44,803][73218] Decorrelating experience for 320 frames...
+-[2023-09-19 11:19:44,907][73223] Decorrelating experience for 384 frames...
+-[2023-09-19 11:19:44,915][73229] Decorrelating experience for 384 frames...
+-[2023-09-19 11:19:44,916][73226] Decorrelating experience for 384 frames...
+-[2023-09-19 11:19:44,933][73221] Decorrelating experience for 384 frames...
+-[2023-09-19 11:19:44,939][73222] Decorrelating experience for 384 frames...
+-[2023-09-19 11:19:44,969][73224] Decorrelating experience for 384 frames...
+-[2023-09-19 11:19:45,006][73220] Decorrelating experience for 384 frames...
+-[2023-09-19 11:19:45,067][73218] Decorrelating experience for 384 frames...
+-[2023-09-19 11:19:45,209][73223] Decorrelating experience for 448 frames...
+-[2023-09-19 11:19:45,221][73226] Decorrelating experience for 448 frames...
+-[2023-09-19 11:19:45,227][73229] Decorrelating experience for 448 frames...
+-[2023-09-19 11:19:45,253][73222] Decorrelating experience for 448 frames...
+-[2023-09-19 11:19:45,261][73221] Decorrelating experience for 448 frames...
+-[2023-09-19 11:19:45,302][73224] Decorrelating experience for 448 frames...
+-[2023-09-19 11:19:45,325][73220] Decorrelating experience for 448 frames...
+-[2023-09-19 11:19:45,392][73218] Decorrelating experience for 448 frames...
+-[2023-09-19 11:19:47,043][72530] Fps is (10 sec: nan, 60 sec: nan, 300 sec: nan). Total num frames: 2437120. Throughput: 0: nan, 1: nan. Samples: 5818. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
+-[2023-09-19 11:19:52,043][72530] Fps is (10 sec: 3276.7, 60 sec: 3276.7, 300 sec: 3276.7). Total num frames: 2453504. Throughput: 0: 1049.2, 1: 1064.0. Samples: 16384. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:19:52,340][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000002424_1241088.pth...
+-[2023-09-19 11:19:52,343][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000002384_1220608.pth...
+-[2023-09-19 11:19:52,345][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000002392_1224704.pth
+-[2023-09-19 11:19:52,348][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000002352_1204224.pth
+-[2023-09-19 11:19:57,043][72530] Fps is (10 sec: 4096.0, 60 sec: 4096.0, 300 sec: 4096.0). Total num frames: 2478080. Throughput: 0: 1910.2, 1: 1911.2. Samples: 44032. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:19:57,045][72530] Avg episode reward: [(0, '67743.941'), (1, '43579.059')]
+-[2023-09-19 11:20:00,740][72530] Heartbeat connected on Batcher_0
+-[2023-09-19 11:20:00,743][72530] Heartbeat connected on LearnerWorker_p0
+-[2023-09-19 11:20:00,746][72530] Heartbeat connected on Batcher_1
+-[2023-09-19 11:20:00,749][72530] Heartbeat connected on LearnerWorker_p1
+-[2023-09-19 11:20:00,755][72530] Heartbeat connected on InferenceWorker_p0-w0
+-[2023-09-19 11:20:00,760][72530] Heartbeat connected on InferenceWorker_p1-w0
+-[2023-09-19 11:20:00,761][72530] Heartbeat connected on RolloutWorker_w0
+-[2023-09-19 11:20:00,767][72530] Heartbeat connected on RolloutWorker_w2
+-[2023-09-19 11:20:00,769][72530] Heartbeat connected on RolloutWorker_w3
+-[2023-09-19 11:20:00,771][72530] Heartbeat connected on RolloutWorker_w1
+-[2023-09-19 11:20:00,772][72530] Heartbeat connected on RolloutWorker_w4
+-[2023-09-19 11:20:00,779][72530] Heartbeat connected on RolloutWorker_w6
+-[2023-09-19 11:20:00,782][72530] Heartbeat connected on RolloutWorker_w7
+-[2023-09-19 11:20:00,783][72530] Heartbeat connected on RolloutWorker_w5
+-[2023-09-19 11:20:02,043][72530] Fps is (10 sec: 6144.1, 60 sec: 5188.3, 300 sec: 5188.3). Total num frames: 2514944. Throughput: 0: 1864.9, 1: 1865.5. Samples: 61774. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:20:02,043][72530] Avg episode reward: [(0, '99962.574'), (1, '74154.644')]
+-[2023-09-19 11:20:02,049][73145] Updated weights for policy 0, policy_version 2480 (0.0015)
+-[2023-09-19 11:20:02,049][73219] Updated weights for policy 1, policy_version 2440 (0.0013)
+-[2023-09-19 11:20:07,043][72530] Fps is (10 sec: 7372.7, 60 sec: 5734.3, 300 sec: 5734.3). Total num frames: 2551808. Throughput: 0: 2437.4, 1: 2437.7. Samples: 103320. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:20:07,045][72530] Avg episode reward: [(0, '117948.527'), (1, '103367.832')]
+-[2023-09-19 11:20:07,048][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000002512_1286144.pth...
+-[2023-09-19 11:20:07,048][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000002472_1265664.pth...
+-[2023-09-19 11:20:07,055][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000002400_1228800.pth
+-[2023-09-19 11:20:07,057][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000002360_1208320.pth
+-[2023-09-19 11:20:12,043][72530] Fps is (10 sec: 6963.0, 60 sec: 5898.2, 300 sec: 5898.2). Total num frames: 2584576. Throughput: 0: 2806.0, 1: 2806.1. Samples: 146122. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0)
+-[2023-09-19 11:20:12,045][72530] Avg episode reward: [(0, '124390.108'), (1, '110149.801')]
+-[2023-09-19 11:20:13,613][73219] Updated weights for policy 1, policy_version 2520 (0.0012)
+-[2023-09-19 11:20:13,613][73145] Updated weights for policy 0, policy_version 2560 (0.0014)
+-[2023-09-19 11:20:17,043][72530] Fps is (10 sec: 6553.7, 60 sec: 6007.5, 300 sec: 6007.5). Total num frames: 2617344. Throughput: 0: 3030.0, 1: 3030.3. Samples: 187626. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0)
+-[2023-09-19 11:20:17,047][72530] Avg episode reward: [(0, '133247.381'), (1, '124425.608')]
+-[2023-09-19 11:20:22,043][72530] Fps is (10 sec: 6553.5, 60 sec: 6085.4, 300 sec: 6085.4). Total num frames: 2650112. Throughput: 0: 2890.3, 1: 2890.4. Samples: 208144. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0)
+-[2023-09-19 11:20:22,044][72530] Avg episode reward: [(0, '134256.432'), (1, '126597.151')]
+-[2023-09-19 11:20:22,047][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000002568_1314816.pth...
+-[2023-09-19 11:20:22,049][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000002608_1335296.pth...
+-[2023-09-19 11:20:22,056][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000002384_1220608.pth
+-[2023-09-19 11:20:22,058][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000002424_1241088.pth
+-[2023-09-19 11:20:26,328][73219] Updated weights for policy 1, policy_version 2600 (0.0014)
+-[2023-09-19 11:20:26,329][73145] Updated weights for policy 0, policy_version 2640 (0.0014)
+-[2023-09-19 11:20:27,043][72530] Fps is (10 sec: 6553.5, 60 sec: 6144.0, 300 sec: 6144.0). Total num frames: 2682880. Throughput: 0: 2979.6, 1: 2979.8. Samples: 244194. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:20:27,044][72530] Avg episode reward: [(0, '152920.116'), (1, '149441.210')]
+-[2023-09-19 11:20:32,043][72530] Fps is (10 sec: 6553.8, 60 sec: 6189.5, 300 sec: 6189.5). Total num frames: 2715648. Throughput: 0: 3119.2, 1: 3119.5. Samples: 286558. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0)
+-[2023-09-19 11:20:32,044][72530] Avg episode reward: [(0, '154007.595'), (1, '152818.612')]
+-[2023-09-19 11:20:37,043][72530] Fps is (10 sec: 6553.7, 60 sec: 6225.9, 300 sec: 6225.9). Total num frames: 2748416. Throughput: 0: 3203.5, 1: 3202.2. Samples: 304640. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:20:37,044][72530] Avg episode reward: [(0, '152855.520'), (1, '157930.094')]
+-[2023-09-19 11:20:37,051][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000002664_1363968.pth...
+-[2023-09-19 11:20:37,051][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000002704_1384448.pth...
+-[2023-09-19 11:20:37,058][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000002472_1265664.pth
+-[2023-09-19 11:20:37,059][73131] Saving new best policy, reward=157930.094!
+-[2023-09-19 11:20:37,059][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000002512_1286144.pth
+-[2023-09-19 11:20:39,045][73219] Updated weights for policy 1, policy_version 2680 (0.0013)
+-[2023-09-19 11:20:39,046][73145] Updated weights for policy 0, policy_version 2720 (0.0015)
+-[2023-09-19 11:20:42,043][72530] Fps is (10 sec: 6553.5, 60 sec: 6255.7, 300 sec: 6255.7). Total num frames: 2781184. Throughput: 0: 3306.8, 1: 3306.8. Samples: 341646. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:20:42,044][72530] Avg episode reward: [(0, '151664.402'), (1, '158564.220')]
+-[2023-09-19 11:20:42,045][73131] Saving new best policy, reward=158564.220!
+-[2023-09-19 11:20:47,043][72530] Fps is (10 sec: 6553.6, 60 sec: 6280.5, 300 sec: 6280.5). Total num frames: 2813952. Throughput: 0: 3562.3, 1: 3562.2. Samples: 382380. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0)
+-[2023-09-19 11:20:47,044][72530] Avg episode reward: [(0, '145105.303'), (1, '155856.908')]
+-[2023-09-19 11:20:51,525][73145] Updated weights for policy 0, policy_version 2800 (0.0016)
+-[2023-09-19 11:20:51,526][73219] Updated weights for policy 1, policy_version 2760 (0.0014)
+-[2023-09-19 11:20:52,043][72530] Fps is (10 sec: 6553.6, 60 sec: 6553.6, 300 sec: 6301.5). Total num frames: 2846720. Throughput: 0: 3312.4, 1: 3313.6. Samples: 401490. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
+-[2023-09-19 11:20:52,044][72530] Avg episode reward: [(0, '144121.200'), (1, '155856.908')]
+-[2023-09-19 11:20:52,053][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000002800_1433600.pth...
+-[2023-09-19 11:20:52,053][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000002760_1413120.pth...
+-[2023-09-19 11:20:52,058][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000002608_1335296.pth
+-[2023-09-19 11:20:52,065][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000002568_1314816.pth
+-[2023-09-19 11:20:57,043][72530] Fps is (10 sec: 6553.6, 60 sec: 6690.1, 300 sec: 6319.5). Total num frames: 2879488. Throughput: 0: 3240.4, 1: 3240.4. Samples: 437758. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
+-[2023-09-19 11:20:57,044][72530] Avg episode reward: [(0, '142988.097'), (1, '155707.131')]
+-[2023-09-19 11:21:02,043][72530] Fps is (10 sec: 6553.6, 60 sec: 6621.8, 300 sec: 6335.1). Total num frames: 2912256. Throughput: 0: 3233.5, 1: 3233.3. Samples: 478634. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:21:02,045][72530] Avg episode reward: [(0, '144052.838'), (1, '155707.131')]
+-[2023-09-19 11:21:04,172][73219] Updated weights for policy 1, policy_version 2840 (0.0013)
+-[2023-09-19 11:21:04,172][73145] Updated weights for policy 0, policy_version 2880 (0.0010)
+-[2023-09-19 11:21:07,043][72530] Fps is (10 sec: 6553.6, 60 sec: 6553.6, 300 sec: 6348.8). Total num frames: 2945024. Throughput: 0: 3220.4, 1: 3220.5. Samples: 497982. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0)
+-[2023-09-19 11:21:07,044][72530] Avg episode reward: [(0, '145667.627'), (1, '156028.379')]
+-[2023-09-19 11:21:07,054][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000002856_1462272.pth...
+-[2023-09-19 11:21:07,054][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000002896_1482752.pth...
+-[2023-09-19 11:21:07,061][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000002664_1363968.pth
+-[2023-09-19 11:21:07,063][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000002704_1384448.pth
+-[2023-09-19 11:21:12,043][72530] Fps is (10 sec: 6553.6, 60 sec: 6553.6, 300 sec: 6360.8). Total num frames: 2977792. Throughput: 0: 3292.6, 1: 3293.6. Samples: 540574. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0)
+-[2023-09-19 11:21:12,045][72530] Avg episode reward: [(0, '147376.857'), (1, '156100.448')]
+-[2023-09-19 11:21:16,935][73219] Updated weights for policy 1, policy_version 2920 (0.0012)
+-[2023-09-19 11:21:16,935][73145] Updated weights for policy 0, policy_version 2960 (0.0013)
+-[2023-09-19 11:21:17,043][72530] Fps is (10 sec: 6553.6, 60 sec: 6553.6, 300 sec: 6371.5). Total num frames: 3010560. Throughput: 0: 3192.5, 1: 3192.8. Samples: 573896. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
+-[2023-09-19 11:21:17,044][72530] Avg episode reward: [(0, '153646.249'), (1, '157825.450')]
+-[2023-09-19 11:21:22,043][72530] Fps is (10 sec: 5734.5, 60 sec: 6417.1, 300 sec: 6294.9). Total num frames: 3035136. Throughput: 0: 3218.0, 1: 3217.9. Samples: 594256. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0)
+-[2023-09-19 11:21:22,044][72530] Avg episode reward: [(0, '156927.936'), (1, '157825.450')]
+-[2023-09-19 11:21:22,051][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000002944_1507328.pth...
+-[2023-09-19 11:21:22,052][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000002984_1527808.pth...
+-[2023-09-19 11:21:22,060][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000002800_1433600.pth
+-[2023-09-19 11:21:22,060][73130] Saving new best policy, reward=156927.936!
+-[2023-09-19 11:21:22,060][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000002760_1413120.pth
+-[2023-09-19 11:21:27,043][72530] Fps is (10 sec: 5734.5, 60 sec: 6417.1, 300 sec: 6307.8). Total num frames: 3067904. Throughput: 0: 3210.2, 1: 3210.0. Samples: 630558. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0)
+-[2023-09-19 11:21:27,045][72530] Avg episode reward: [(0, '158809.152'), (1, '159261.146')]
+-[2023-09-19 11:21:27,046][73130] Saving new best policy, reward=158809.152!
+-[2023-09-19 11:21:27,046][73131] Saving new best policy, reward=159261.146!
+-[2023-09-19 11:21:29,937][73145] Updated weights for policy 0, policy_version 3040 (0.0014)
+-[2023-09-19 11:21:29,937][73219] Updated weights for policy 1, policy_version 3000 (0.0015)
+-[2023-09-19 11:21:32,043][72530] Fps is (10 sec: 6553.5, 60 sec: 6417.0, 300 sec: 6319.5). Total num frames: 3100672. Throughput: 0: 3202.6, 1: 3202.7. Samples: 670618. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:21:32,044][72530] Avg episode reward: [(0, '158669.703'), (1, '159261.146')]
+-[2023-09-19 11:21:37,043][72530] Fps is (10 sec: 6553.6, 60 sec: 6417.1, 300 sec: 6330.2). Total num frames: 3133440. Throughput: 0: 3194.8, 1: 3193.6. Samples: 688972. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:21:37,044][72530] Avg episode reward: [(0, '160207.000'), (1, '158900.446')]
+-[2023-09-19 11:21:37,053][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000003040_1556480.pth...
+-[2023-09-19 11:21:37,053][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000003080_1576960.pth...
+-[2023-09-19 11:21:37,060][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000002856_1462272.pth
+-[2023-09-19 11:21:37,062][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000002896_1482752.pth
+-[2023-09-19 11:21:37,063][73130] Saving new best policy, reward=160207.000!
+-[2023-09-19 11:21:42,043][72530] Fps is (10 sec: 6553.7, 60 sec: 6417.1, 300 sec: 6339.9). Total num frames: 3166208. Throughput: 0: 3201.6, 1: 3201.7. Samples: 725908. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:21:42,044][72530] Avg episode reward: [(0, '160167.920'), (1, '158900.446')]
+-[2023-09-19 11:21:43,450][73219] Updated weights for policy 1, policy_version 3080 (0.0013)
+-[2023-09-19 11:21:43,451][73145] Updated weights for policy 0, policy_version 3120 (0.0018)
+-[2023-09-19 11:21:47,043][72530] Fps is (10 sec: 5734.4, 60 sec: 6280.5, 300 sec: 6280.5). Total num frames: 3190784. Throughput: 0: 3112.9, 1: 3113.1. Samples: 758804. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:21:47,045][72530] Avg episode reward: [(0, '160649.680'), (1, '159123.148')]
+-[2023-09-19 11:21:47,046][73130] Saving new best policy, reward=160649.680!
+-[2023-09-19 11:21:52,043][72530] Fps is (10 sec: 5734.3, 60 sec: 6280.5, 300 sec: 6291.4). Total num frames: 3223552. Throughput: 0: 3114.0, 1: 3115.4. Samples: 778308. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0)
+-[2023-09-19 11:21:52,044][72530] Avg episode reward: [(0, '159415.266'), (1, '160065.227')]
+-[2023-09-19 11:21:52,055][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000003168_1622016.pth...
+-[2023-09-19 11:21:52,055][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000003128_1601536.pth...
+-[2023-09-19 11:21:52,061][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000002944_1507328.pth
+-[2023-09-19 11:21:52,061][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000002984_1527808.pth
+-[2023-09-19 11:21:52,062][73131] Saving new best policy, reward=160065.227!
+-[2023-09-19 11:21:56,561][73145] Updated weights for policy 0, policy_version 3200 (0.0015)
+-[2023-09-19 11:21:56,561][73219] Updated weights for policy 1, policy_version 3160 (0.0015)
+-[2023-09-19 11:21:57,043][72530] Fps is (10 sec: 6553.6, 60 sec: 6280.5, 300 sec: 6301.5). Total num frames: 3256320. Throughput: 0: 3061.8, 1: 3060.8. Samples: 816090. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0)
+-[2023-09-19 11:21:57,044][72530] Avg episode reward: [(0, '159883.769'), (1, '159603.128')]
+-[2023-09-19 11:22:02,043][72530] Fps is (10 sec: 6553.7, 60 sec: 6280.5, 300 sec: 6310.9). Total num frames: 3289088. Throughput: 0: 3110.9, 1: 3110.3. Samples: 853850. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
+-[2023-09-19 11:22:02,044][72530] Avg episode reward: [(0, '160168.162'), (1, '158805.251')]
+-[2023-09-19 11:22:07,043][72530] Fps is (10 sec: 6553.5, 60 sec: 6280.5, 300 sec: 6319.5). Total num frames: 3321856. Throughput: 0: 3100.6, 1: 3100.8. Samples: 873320. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
+-[2023-09-19 11:22:07,044][72530] Avg episode reward: [(0, '159368.135'), (1, '158166.073')]
+-[2023-09-19 11:22:07,055][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000003224_1650688.pth...
+-[2023-09-19 11:22:07,055][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000003264_1671168.pth...
+-[2023-09-19 11:22:07,064][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000003040_1556480.pth
+-[2023-09-19 11:22:07,065][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000003080_1576960.pth
+-[2023-09-19 11:22:09,339][73145] Updated weights for policy 0, policy_version 3280 (0.0016)
+-[2023-09-19 11:22:09,339][73219] Updated weights for policy 1, policy_version 3240 (0.0013)
+-[2023-09-19 11:22:12,043][72530] Fps is (10 sec: 6553.7, 60 sec: 6280.5, 300 sec: 6327.6). Total num frames: 3354624. Throughput: 0: 3134.1, 1: 3134.3. Samples: 912634. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:22:12,044][72530] Avg episode reward: [(0, '154750.825'), (1, '157929.657')]
+-[2023-09-19 11:22:17,043][72530] Fps is (10 sec: 5734.4, 60 sec: 6144.0, 300 sec: 6280.5). Total num frames: 3379200. Throughput: 0: 3098.0, 1: 3098.2. Samples: 949448. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:22:17,045][72530] Avg episode reward: [(0, '152601.903'), (1, '153832.123')]
+-[2023-09-19 11:22:22,043][72530] Fps is (10 sec: 5734.3, 60 sec: 6280.5, 300 sec: 6289.3). Total num frames: 3411968. Throughput: 0: 3112.9, 1: 3113.0. Samples: 969138. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
+-[2023-09-19 11:22:22,044][72530] Avg episode reward: [(0, '152992.401'), (1, '152373.243')]
+-[2023-09-19 11:22:22,054][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000003312_1695744.pth...
+-[2023-09-19 11:22:22,054][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000003352_1716224.pth...
+-[2023-09-19 11:22:22,063][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000003128_1601536.pth
+-[2023-09-19 11:22:22,064][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000003168_1622016.pth
+-[2023-09-19 11:22:22,748][73219] Updated weights for policy 1, policy_version 3320 (0.0013)
+-[2023-09-19 11:22:22,749][73145] Updated weights for policy 0, policy_version 3360 (0.0014)
+-[2023-09-19 11:22:27,043][72530] Fps is (10 sec: 6553.7, 60 sec: 6280.5, 300 sec: 6297.6). Total num frames: 3444736. Throughput: 0: 3104.4, 1: 3104.3. Samples: 1005296. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:22:27,044][72530] Avg episode reward: [(0, '152409.297'), (1, '152400.063')]
+-[2023-09-19 11:22:32,043][72530] Fps is (10 sec: 6553.6, 60 sec: 6280.5, 300 sec: 6305.4). Total num frames: 3477504. Throughput: 0: 3183.3, 1: 3183.3. Samples: 1045302. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
+-[2023-09-19 11:22:32,044][72530] Avg episode reward: [(0, '150571.798'), (1, '152330.295')]
+-[2023-09-19 11:22:35,267][73145] Updated weights for policy 0, policy_version 3440 (0.0013)
+-[2023-09-19 11:22:35,268][73219] Updated weights for policy 1, policy_version 3400 (0.0014)
+-[2023-09-19 11:22:37,043][72530] Fps is (10 sec: 6553.4, 60 sec: 6280.5, 300 sec: 6312.6). Total num frames: 3510272. Throughput: 0: 3180.8, 1: 3180.2. Samples: 1064554. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:22:37,044][72530] Avg episode reward: [(0, '150024.495'), (1, '153833.309')]
+-[2023-09-19 11:22:37,054][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000003408_1744896.pth...
+-[2023-09-19 11:22:37,054][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000003448_1765376.pth...
+-[2023-09-19 11:22:37,060][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000003264_1671168.pth
+-[2023-09-19 11:22:37,061][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000003224_1650688.pth
+-[2023-09-19 11:22:42,043][72530] Fps is (10 sec: 6553.7, 60 sec: 6280.5, 300 sec: 6319.5). Total num frames: 3543040. Throughput: 0: 3161.4, 1: 3161.5. Samples: 1100622. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:22:42,044][72530] Avg episode reward: [(0, '153738.816'), (1, '154391.331')]
+-[2023-09-19 11:22:47,043][72530] Fps is (10 sec: 5734.5, 60 sec: 6280.5, 300 sec: 6280.5). Total num frames: 3567616. Throughput: 0: 3163.8, 1: 3165.1. Samples: 1138652. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:22:47,044][72530] Avg episode reward: [(0, '154735.807'), (1, '155587.330')]
+-[2023-09-19 11:22:48,507][73145] Updated weights for policy 0, policy_version 3520 (0.0012)
+-[2023-09-19 11:22:48,508][73219] Updated weights for policy 1, policy_version 3480 (0.0013)
+-[2023-09-19 11:22:52,043][72530] Fps is (10 sec: 5734.3, 60 sec: 6280.5, 300 sec: 6287.9). Total num frames: 3600384. Throughput: 0: 3151.2, 1: 3151.2. Samples: 1156926. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0)
+-[2023-09-19 11:22:52,044][72530] Avg episode reward: [(0, '155558.003'), (1, '158444.382')]
+-[2023-09-19 11:22:52,053][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000003496_1789952.pth...
+-[2023-09-19 11:22:52,053][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000003536_1810432.pth...
+-[2023-09-19 11:22:52,059][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000003312_1695744.pth
+-[2023-09-19 11:22:52,062][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000003352_1716224.pth
+-[2023-09-19 11:22:57,043][72530] Fps is (10 sec: 5734.3, 60 sec: 6144.0, 300 sec: 6251.8). Total num frames: 3624960. Throughput: 0: 3076.0, 1: 3076.3. Samples: 1189490. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:22:57,044][72530] Avg episode reward: [(0, '156213.048'), (1, '159905.417')]
+-[2023-09-19 11:23:02,043][72530] Fps is (10 sec: 5734.5, 60 sec: 6144.0, 300 sec: 6259.5). Total num frames: 3657728. Throughput: 0: 3051.2, 1: 3051.2. Samples: 1224052. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:23:02,044][72530] Avg episode reward: [(0, '154952.583'), (1, '160034.837')]
+-[2023-09-19 11:23:03,139][73219] Updated weights for policy 1, policy_version 3560 (0.0011)
+-[2023-09-19 11:23:03,140][73145] Updated weights for policy 0, policy_version 3600 (0.0014)
+-[2023-09-19 11:23:07,043][72530] Fps is (10 sec: 5734.4, 60 sec: 6007.5, 300 sec: 6225.9). Total num frames: 3682304. Throughput: 0: 3014.6, 1: 3014.8. Samples: 1240462. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
+-[2023-09-19 11:23:07,045][72530] Avg episode reward: [(0, '154952.583'), (1, '160050.141')]
+-[2023-09-19 11:23:07,056][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000003576_1830912.pth...
+-[2023-09-19 11:23:07,057][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000003616_1851392.pth...
+-[2023-09-19 11:23:07,061][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000003448_1765376.pth
+-[2023-09-19 11:23:07,061][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000003408_1744896.pth
+-[2023-09-19 11:23:12,043][72530] Fps is (10 sec: 5734.3, 60 sec: 6007.5, 300 sec: 6233.9). Total num frames: 3715072. Throughput: 0: 3031.9, 1: 3032.3. Samples: 1278182. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:23:12,045][72530] Avg episode reward: [(0, '151313.141'), (1, '159602.087')]
+-[2023-09-19 11:23:16,373][73219] Updated weights for policy 1, policy_version 3640 (0.0012)
+-[2023-09-19 11:23:16,374][73145] Updated weights for policy 0, policy_version 3680 (0.0011)
+-[2023-09-19 11:23:17,043][72530] Fps is (10 sec: 6553.7, 60 sec: 6144.0, 300 sec: 6241.5). Total num frames: 3747840. Throughput: 0: 2998.0, 1: 2998.0. Samples: 1315120. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:23:17,044][72530] Avg episode reward: [(0, '151313.141'), (1, '159523.019')]
+-[2023-09-19 11:23:22,043][72530] Fps is (10 sec: 6553.6, 60 sec: 6144.0, 300 sec: 6248.8). Total num frames: 3780608. Throughput: 0: 3006.6, 1: 3007.0. Samples: 1335164. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0)
+-[2023-09-19 11:23:22,044][72530] Avg episode reward: [(0, '152570.175'), (1, '158236.314')]
+-[2023-09-19 11:23:22,053][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000003712_1900544.pth...
+-[2023-09-19 11:23:22,053][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000003672_1880064.pth...
+-[2023-09-19 11:23:22,060][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000003536_1810432.pth
+-[2023-09-19 11:23:22,062][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000003496_1789952.pth
+-[2023-09-19 11:23:27,043][72530] Fps is (10 sec: 6553.5, 60 sec: 6144.0, 300 sec: 6255.7). Total num frames: 3813376. Throughput: 0: 2986.7, 1: 2986.5. Samples: 1369418. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:23:27,045][72530] Avg episode reward: [(0, '152570.175'), (1, '158236.314')]
+-[2023-09-19 11:23:29,330][73219] Updated weights for policy 1, policy_version 3720 (0.0013)
+-[2023-09-19 11:23:29,331][73145] Updated weights for policy 0, policy_version 3760 (0.0014)
+-[2023-09-19 11:23:32,043][72530] Fps is (10 sec: 5734.4, 60 sec: 6007.5, 300 sec: 6225.9). Total num frames: 3837952. Throughput: 0: 2803.1, 1: 2802.0. Samples: 1390884. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0)
+-[2023-09-19 11:23:32,044][72530] Avg episode reward: [(0, '152939.553'), (1, '157598.636')]
+-[2023-09-19 11:23:37,043][72530] Fps is (10 sec: 5734.5, 60 sec: 6007.5, 300 sec: 6233.0). Total num frames: 3870720. Throughput: 0: 3009.5, 1: 3009.5. Samples: 1427778. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0)
+-[2023-09-19 11:23:37,044][72530] Avg episode reward: [(0, '152939.553'), (1, '157598.636')]
+-[2023-09-19 11:23:37,053][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000003800_1945600.pth...
+-[2023-09-19 11:23:37,053][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000003760_1925120.pth...
+-[2023-09-19 11:23:37,059][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000003616_1851392.pth
+-[2023-09-19 11:23:37,062][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000003576_1830912.pth
+-[2023-09-19 11:23:42,043][72530] Fps is (10 sec: 6553.7, 60 sec: 6007.5, 300 sec: 6239.9). Total num frames: 3903488. Throughput: 0: 3062.4, 1: 3061.9. Samples: 1465082. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:23:42,044][72530] Avg episode reward: [(0, '155045.334'), (1, '157877.174')]
+-[2023-09-19 11:23:42,591][73219] Updated weights for policy 1, policy_version 3800 (0.0013)
+-[2023-09-19 11:23:42,592][73145] Updated weights for policy 0, policy_version 3840 (0.0013)
+-[2023-09-19 11:23:47,043][72530] Fps is (10 sec: 5734.2, 60 sec: 6007.4, 300 sec: 6212.3). Total num frames: 3928064. Throughput: 0: 3055.4, 1: 3056.6. Samples: 1499094. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:23:47,044][72530] Avg episode reward: [(0, '155518.647'), (1, '157877.174')]
+-[2023-09-19 11:23:52,043][72530] Fps is (10 sec: 5734.4, 60 sec: 6007.5, 300 sec: 6219.2). Total num frames: 3960832. Throughput: 0: 3090.5, 1: 3090.4. Samples: 1518604. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0)
+-[2023-09-19 11:23:52,044][72530] Avg episode reward: [(0, '156419.731'), (1, '159794.628')]
+-[2023-09-19 11:23:52,052][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000003848_1970176.pth...
+-[2023-09-19 11:23:52,052][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000003888_1990656.pth...
+-[2023-09-19 11:23:52,060][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000003672_1880064.pth
+-[2023-09-19 11:23:52,061][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000003712_1900544.pth
+-[2023-09-19 11:23:56,865][73219] Updated weights for policy 1, policy_version 3880 (0.0012)
+-[2023-09-19 11:23:56,866][73145] Updated weights for policy 0, policy_version 3920 (0.0014)
+-[2023-09-19 11:23:57,043][72530] Fps is (10 sec: 6553.8, 60 sec: 6144.0, 300 sec: 6225.9). Total num frames: 3993600. Throughput: 0: 3037.8, 1: 3037.7. Samples: 1551576. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:23:57,044][72530] Avg episode reward: [(0, '155910.674'), (1, '159794.628')]
+-[2023-09-19 11:24:02,043][72530] Fps is (10 sec: 5734.3, 60 sec: 6007.4, 300 sec: 6200.2). Total num frames: 4018176. Throughput: 0: 2986.6, 1: 2986.6. Samples: 1583914. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:24:02,045][72530] Avg episode reward: [(0, '155254.236'), (1, '160650.698')]
+-[2023-09-19 11:24:02,046][73131] Saving new best policy, reward=160650.698!
+-[2023-09-19 11:24:07,043][72530] Fps is (10 sec: 5734.4, 60 sec: 6144.0, 300 sec: 6207.0). Total num frames: 4050944. Throughput: 0: 2980.8, 1: 2979.8. Samples: 1603390. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:24:07,044][72530] Avg episode reward: [(0, '155932.263'), (1, '160981.958')]
+-[2023-09-19 11:24:07,053][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000003936_2015232.pth...
+-[2023-09-19 11:24:07,053][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000003976_2035712.pth...
+-[2023-09-19 11:24:07,060][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000003800_1945600.pth
+-[2023-09-19 11:24:07,062][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000003760_1925120.pth
+-[2023-09-19 11:24:07,062][73131] Saving new best policy, reward=160981.958!
+-[2023-09-19 11:24:10,788][73145] Updated weights for policy 0, policy_version 4000 (0.0014)
+-[2023-09-19 11:24:10,788][73219] Updated weights for policy 1, policy_version 3960 (0.0013)
+-[2023-09-19 11:24:12,043][72530] Fps is (10 sec: 5734.6, 60 sec: 6007.5, 300 sec: 6182.6). Total num frames: 4075520. Throughput: 0: 3006.8, 1: 3006.8. Samples: 1640028. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:24:12,044][72530] Avg episode reward: [(0, '156741.192'), (1, '161232.794')]
+-[2023-09-19 11:24:12,051][73131] Saving new best policy, reward=161232.794!
+-[2023-09-19 11:24:17,043][72530] Fps is (10 sec: 6553.6, 60 sec: 6144.0, 300 sec: 6219.9). Total num frames: 4116480. Throughput: 0: 3213.3, 1: 3213.3. Samples: 1680080. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:24:17,044][72530] Avg episode reward: [(0, '158187.015'), (1, '161349.690')]
+-[2023-09-19 11:24:17,045][73131] Saving new best policy, reward=161349.690!
+-[2023-09-19 11:24:22,043][72530] Fps is (10 sec: 7372.6, 60 sec: 6144.0, 300 sec: 6225.9). Total num frames: 4149248. Throughput: 0: 3037.6, 1: 3037.4. Samples: 1701154. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:24:22,044][72530] Avg episode reward: [(0, '158725.033'), (1, '161643.895')]
+-[2023-09-19 11:24:22,054][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000004032_2064384.pth...
+-[2023-09-19 11:24:22,054][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000004072_2084864.pth...
+-[2023-09-19 11:24:22,061][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000003848_1970176.pth
+-[2023-09-19 11:24:22,061][73131] Saving new best policy, reward=161643.895!
+-[2023-09-19 11:24:22,063][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000003888_1990656.pth
+-[2023-09-19 11:24:23,177][73219] Updated weights for policy 1, policy_version 4040 (0.0014)
+-[2023-09-19 11:24:23,178][73145] Updated weights for policy 0, policy_version 4080 (0.0016)
+-[2023-09-19 11:24:27,043][72530] Fps is (10 sec: 5734.3, 60 sec: 6007.5, 300 sec: 6202.5). Total num frames: 4173824. Throughput: 0: 3023.4, 1: 3023.4. Samples: 1737188. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:24:27,044][72530] Avg episode reward: [(0, '155903.476'), (1, '161815.854')]
+-[2023-09-19 11:24:27,045][73131] Saving new best policy, reward=161815.854!
+-[2023-09-19 11:24:32,043][72530] Fps is (10 sec: 6553.7, 60 sec: 6280.5, 300 sec: 6237.4). Total num frames: 4214784. Throughput: 0: 3098.6, 1: 3097.1. Samples: 1777900. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0)
+-[2023-09-19 11:24:32,044][72530] Avg episode reward: [(0, '154152.668'), (1, '161862.881')]
+-[2023-09-19 11:24:32,045][73131] Saving new best policy, reward=161862.881!
+-[2023-09-19 11:24:36,067][73145] Updated weights for policy 0, policy_version 4160 (0.0013)
+-[2023-09-19 11:24:36,069][73219] Updated weights for policy 1, policy_version 4120 (0.0014)
+-[2023-09-19 11:24:37,043][72530] Fps is (10 sec: 6553.5, 60 sec: 6144.0, 300 sec: 6214.6). Total num frames: 4239360. Throughput: 0: 3068.9, 1: 3068.7. Samples: 1794800. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0)
+-[2023-09-19 11:24:37,044][72530] Avg episode reward: [(0, '151755.204'), (1, '161941.149')]
+-[2023-09-19 11:24:37,055][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000004160_2129920.pth...
+-[2023-09-19 11:24:37,055][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000004120_2109440.pth...
+-[2023-09-19 11:24:37,062][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000003976_2035712.pth
+-[2023-09-19 11:24:37,064][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000003936_2015232.pth
+-[2023-09-19 11:24:37,065][73131] Saving new best policy, reward=161941.149!
+-[2023-09-19 11:24:42,043][72530] Fps is (10 sec: 5734.4, 60 sec: 6144.0, 300 sec: 6220.4). Total num frames: 4272128. Throughput: 0: 3155.4, 1: 3155.3. Samples: 1835558. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0)
+-[2023-09-19 11:24:42,044][72530] Avg episode reward: [(0, '150680.731'), (1, '161901.771')]
+-[2023-09-19 11:24:47,043][72530] Fps is (10 sec: 6553.7, 60 sec: 6280.6, 300 sec: 6275.9). Total num frames: 4304896. Throughput: 0: 3207.8, 1: 3207.7. Samples: 1872614. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:24:47,044][72530] Avg episode reward: [(0, '148141.874'), (1, '161823.095')]
+-[2023-09-19 11:24:48,828][73219] Updated weights for policy 1, policy_version 4200 (0.0010)
+-[2023-09-19 11:24:48,829][73145] Updated weights for policy 0, policy_version 4240 (0.0014)
+-[2023-09-19 11:24:52,043][72530] Fps is (10 sec: 6553.6, 60 sec: 6280.5, 300 sec: 6303.7). Total num frames: 4337664. Throughput: 0: 3210.0, 1: 3211.3. Samples: 1892352. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:24:52,044][72530] Avg episode reward: [(0, '144621.889'), (1, '160527.319')]
+-[2023-09-19 11:24:52,052][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000004216_2158592.pth...
+-[2023-09-19 11:24:52,052][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000004256_2179072.pth...
+-[2023-09-19 11:24:52,059][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000004032_2064384.pth
+-[2023-09-19 11:24:52,062][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000004072_2084864.pth
+-[2023-09-19 11:24:57,043][72530] Fps is (10 sec: 6553.6, 60 sec: 6280.5, 300 sec: 6289.8). Total num frames: 4370432. Throughput: 0: 3240.7, 1: 3240.7. Samples: 1931690. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:24:57,044][72530] Avg episode reward: [(0, '144800.686'), (1, '160295.845')]
+-[2023-09-19 11:25:01,923][73219] Updated weights for policy 1, policy_version 4280 (0.0013)
+-[2023-09-19 11:25:01,923][73145] Updated weights for policy 0, policy_version 4320 (0.0013)
+-[2023-09-19 11:25:02,043][72530] Fps is (10 sec: 6553.5, 60 sec: 6417.1, 300 sec: 6275.9). Total num frames: 4403200. Throughput: 0: 3184.6, 1: 3184.7. Samples: 1966700. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:25:02,044][72530] Avg episode reward: [(0, '145084.319'), (1, '160219.957')]
+-[2023-09-19 11:25:07,043][72530] Fps is (10 sec: 5734.4, 60 sec: 6280.5, 300 sec: 6248.1). Total num frames: 4427776. Throughput: 0: 3125.7, 1: 3127.1. Samples: 1982528. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:25:07,045][72530] Avg episode reward: [(0, '144470.225'), (1, '159962.850')]
+-[2023-09-19 11:25:07,055][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000004304_2203648.pth...
+-[2023-09-19 11:25:07,055][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000004344_2224128.pth...
+-[2023-09-19 11:25:07,062][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000004120_2109440.pth
+-[2023-09-19 11:25:07,062][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000004160_2129920.pth
+-[2023-09-19 11:25:12,043][72530] Fps is (10 sec: 5734.5, 60 sec: 6417.1, 300 sec: 6248.1). Total num frames: 4460544. Throughput: 0: 3189.5, 1: 3189.4. Samples: 2024240. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0)
+-[2023-09-19 11:25:12,044][72530] Avg episode reward: [(0, '144911.603'), (1, '159940.569')]
+-[2023-09-19 11:25:14,575][73145] Updated weights for policy 0, policy_version 4400 (0.0013)
+-[2023-09-19 11:25:14,577][73219] Updated weights for policy 1, policy_version 4360 (0.0014)
+-[2023-09-19 11:25:17,043][72530] Fps is (10 sec: 6553.7, 60 sec: 6280.5, 300 sec: 6248.1). Total num frames: 4493312. Throughput: 0: 3180.8, 1: 3181.4. Samples: 2064198. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:25:17,044][72530] Avg episode reward: [(0, '140838.640'), (1, '160023.760')]
+-[2023-09-19 11:25:22,043][72530] Fps is (10 sec: 7372.7, 60 sec: 6417.1, 300 sec: 6275.9). Total num frames: 4534272. Throughput: 0: 3210.7, 1: 3210.9. Samples: 2083770. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:25:22,044][72530] Avg episode reward: [(0, '145736.624'), (1, '161193.551')]
+-[2023-09-19 11:25:22,054][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000004408_2256896.pth...
+-[2023-09-19 11:25:22,054][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000004448_2277376.pth...
+-[2023-09-19 11:25:22,062][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000004256_2179072.pth
+-[2023-09-19 11:25:22,064][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000004216_2158592.pth
+-[2023-09-19 11:25:27,043][72530] Fps is (10 sec: 6553.6, 60 sec: 6417.1, 300 sec: 6248.1). Total num frames: 4558848. Throughput: 0: 3177.1, 1: 3178.3. Samples: 2121554. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:25:27,044][72530] Avg episode reward: [(0, '146210.154'), (1, '161328.801')]
+-[2023-09-19 11:25:27,759][73219] Updated weights for policy 1, policy_version 4440 (0.0013)
+-[2023-09-19 11:25:27,759][73145] Updated weights for policy 0, policy_version 4480 (0.0013)
+-[2023-09-19 11:25:32,043][72530] Fps is (10 sec: 5734.4, 60 sec: 6280.5, 300 sec: 6248.1). Total num frames: 4591616. Throughput: 0: 3156.1, 1: 3156.0. Samples: 2156656. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:25:32,044][72530] Avg episode reward: [(0, '148003.467'), (1, '161381.807')]
+-[2023-09-19 11:25:37,043][72530] Fps is (10 sec: 6553.5, 60 sec: 6417.1, 300 sec: 6248.1). Total num frames: 4624384. Throughput: 0: 3173.7, 1: 3172.3. Samples: 2177924. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:25:37,044][72530] Avg episode reward: [(0, '152496.039'), (1, '161644.736')]
+-[2023-09-19 11:25:37,054][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000004496_2301952.pth...
+-[2023-09-19 11:25:37,056][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000004536_2322432.pth...
+-[2023-09-19 11:25:37,063][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000004304_2203648.pth
+-[2023-09-19 11:25:37,071][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000004344_2224128.pth
+-[2023-09-19 11:25:40,045][73219] Updated weights for policy 1, policy_version 4520 (0.0014)
+-[2023-09-19 11:25:40,045][73145] Updated weights for policy 0, policy_version 4560 (0.0014)
+-[2023-09-19 11:25:42,043][72530] Fps is (10 sec: 6553.6, 60 sec: 6417.1, 300 sec: 6248.1). Total num frames: 4657152. Throughput: 0: 3196.5, 1: 3196.4. Samples: 2219366. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
+-[2023-09-19 11:25:42,044][72530] Avg episode reward: [(0, '151440.031'), (1, '161613.003')]
+-[2023-09-19 11:25:47,043][72530] Fps is (10 sec: 6553.8, 60 sec: 6417.1, 300 sec: 6248.1). Total num frames: 4689920. Throughput: 0: 3225.5, 1: 3225.4. Samples: 2256988. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:25:47,044][72530] Avg episode reward: [(0, '155863.155'), (1, '161674.332')]
+-[2023-09-19 11:25:52,043][72530] Fps is (10 sec: 6553.6, 60 sec: 6417.1, 300 sec: 6248.1). Total num frames: 4722688. Throughput: 0: 3263.8, 1: 3262.1. Samples: 2276194. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:25:52,044][72530] Avg episode reward: [(0, '154315.726'), (1, '161202.405')]
+-[2023-09-19 11:25:52,052][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000004592_2351104.pth...
+-[2023-09-19 11:25:52,052][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000004632_2371584.pth...
+-[2023-09-19 11:25:52,059][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000004408_2256896.pth
+-[2023-09-19 11:25:52,059][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000004448_2277376.pth
+-[2023-09-19 11:25:52,782][73219] Updated weights for policy 1, policy_version 4600 (0.0014)
+-[2023-09-19 11:25:52,782][73145] Updated weights for policy 0, policy_version 4640 (0.0014)
+-[2023-09-19 11:25:57,043][72530] Fps is (10 sec: 6553.6, 60 sec: 6417.1, 300 sec: 6248.1). Total num frames: 4755456. Throughput: 0: 3211.2, 1: 3211.4. Samples: 2313256. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:25:57,044][72530] Avg episode reward: [(0, '150010.060'), (1, '160917.790')]
+-[2023-09-19 11:26:02,043][72530] Fps is (10 sec: 6553.5, 60 sec: 6417.1, 300 sec: 6248.1). Total num frames: 4788224. Throughput: 0: 3193.2, 1: 3192.7. Samples: 2351560. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0)
+-[2023-09-19 11:26:02,045][72530] Avg episode reward: [(0, '150263.831'), (1, '161029.917')]
+-[2023-09-19 11:26:05,903][73219] Updated weights for policy 1, policy_version 4680 (0.0013)
+-[2023-09-19 11:26:05,903][73145] Updated weights for policy 0, policy_version 4720 (0.0012)
+-[2023-09-19 11:26:07,043][72530] Fps is (10 sec: 5734.3, 60 sec: 6417.1, 300 sec: 6220.4). Total num frames: 4812800. Throughput: 0: 3179.7, 1: 3179.7. Samples: 2369942. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:26:07,044][72530] Avg episode reward: [(0, '146564.474'), (1, '161044.989')]
+-[2023-09-19 11:26:07,055][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000004680_2396160.pth...
+-[2023-09-19 11:26:07,055][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000004720_2416640.pth...
+-[2023-09-19 11:26:07,063][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000004536_2322432.pth
+-[2023-09-19 11:26:07,063][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000004496_2301952.pth
+-[2023-09-19 11:26:12,043][72530] Fps is (10 sec: 5734.4, 60 sec: 6417.0, 300 sec: 6220.4). Total num frames: 4845568. Throughput: 0: 3166.9, 1: 3166.1. Samples: 2406540. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0)
+-[2023-09-19 11:26:12,045][72530] Avg episode reward: [(0, '146583.424'), (1, '161100.378')]
+-[2023-09-19 11:26:17,043][72530] Fps is (10 sec: 5734.5, 60 sec: 6280.5, 300 sec: 6220.4). Total num frames: 4870144. Throughput: 0: 3143.0, 1: 3143.1. Samples: 2439528. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0)
+-[2023-09-19 11:26:17,044][72530] Avg episode reward: [(0, '141842.532'), (1, '161215.328')]
+-[2023-09-19 11:26:19,884][73219] Updated weights for policy 1, policy_version 4760 (0.0016)
+-[2023-09-19 11:26:19,884][73145] Updated weights for policy 0, policy_version 4800 (0.0015)
+-[2023-09-19 11:26:22,043][72530] Fps is (10 sec: 5734.5, 60 sec: 6144.0, 300 sec: 6220.4). Total num frames: 4902912. Throughput: 0: 3118.8, 1: 3118.8. Samples: 2458616. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
+-[2023-09-19 11:26:22,044][72530] Avg episode reward: [(0, '142452.610'), (1, '161748.126')]
+-[2023-09-19 11:26:22,053][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000004768_2441216.pth...
+-[2023-09-19 11:26:22,054][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000004808_2461696.pth...
+-[2023-09-19 11:26:22,061][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000004592_2351104.pth
+-[2023-09-19 11:26:22,064][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000004632_2371584.pth
+-[2023-09-19 11:26:27,043][72530] Fps is (10 sec: 6553.6, 60 sec: 6280.5, 300 sec: 6220.4). Total num frames: 4935680. Throughput: 0: 3120.4, 1: 3120.6. Samples: 2500210. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
+-[2023-09-19 11:26:27,044][72530] Avg episode reward: [(0, '137895.579'), (1, '162103.130')]
+-[2023-09-19 11:26:27,045][73131] Saving new best policy, reward=162103.130!
+-[2023-09-19 11:26:32,043][72530] Fps is (10 sec: 6553.7, 60 sec: 6280.5, 300 sec: 6220.4). Total num frames: 4968448. Throughput: 0: 3138.1, 1: 3139.4. Samples: 2539476. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:26:32,044][72530] Avg episode reward: [(0, '135551.322'), (1, '162133.015')]
+-[2023-09-19 11:26:32,045][73131] Saving new best policy, reward=162133.015!
+-[2023-09-19 11:26:32,157][73219] Updated weights for policy 1, policy_version 4840 (0.0010)
+-[2023-09-19 11:26:32,158][73145] Updated weights for policy 0, policy_version 4880 (0.0012)
+-[2023-09-19 11:26:37,043][72530] Fps is (10 sec: 6553.5, 60 sec: 6280.5, 300 sec: 6220.4). Total num frames: 5001216. Throughput: 0: 3107.1, 1: 3108.5. Samples: 2555894. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
+-[2023-09-19 11:26:37,044][72530] Avg episode reward: [(0, '131208.771'), (1, '162213.080')]
+-[2023-09-19 11:26:37,054][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000004904_2510848.pth...
+-[2023-09-19 11:26:37,054][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000004864_2490368.pth...
+-[2023-09-19 11:26:37,064][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000004680_2396160.pth
+-[2023-09-19 11:26:37,064][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000004720_2416640.pth
+-[2023-09-19 11:26:37,065][73131] Saving new best policy, reward=162213.080!
+-[2023-09-19 11:26:42,043][72530] Fps is (10 sec: 6553.6, 60 sec: 6280.5, 300 sec: 6248.1). Total num frames: 5033984. Throughput: 0: 3145.9, 1: 3145.9. Samples: 2596386. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:26:42,044][72530] Avg episode reward: [(0, '130942.941'), (1, '162247.080')]
+-[2023-09-19 11:26:42,045][73131] Saving new best policy, reward=162247.080!
+-[2023-09-19 11:26:44,999][73145] Updated weights for policy 0, policy_version 4960 (0.0011)
+-[2023-09-19 11:26:44,999][73219] Updated weights for policy 1, policy_version 4920 (0.0015)
+-[2023-09-19 11:26:47,043][72530] Fps is (10 sec: 6553.7, 60 sec: 6280.5, 300 sec: 6248.1). Total num frames: 5066752. Throughput: 0: 3150.9, 1: 3150.9. Samples: 2635140. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:26:47,044][72530] Avg episode reward: [(0, '129912.953'), (1, '162118.110')]
+-[2023-09-19 11:26:52,043][72530] Fps is (10 sec: 6553.6, 60 sec: 6280.5, 300 sec: 6248.1). Total num frames: 5099520. Throughput: 0: 3158.5, 1: 3159.3. Samples: 2654242. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:26:52,044][72530] Avg episode reward: [(0, '128999.147'), (1, '162160.112')]
+-[2023-09-19 11:26:52,050][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000005000_2560000.pth...
+-[2023-09-19 11:26:52,050][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000004960_2539520.pth...
+-[2023-09-19 11:26:52,057][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000004808_2461696.pth
+-[2023-09-19 11:26:52,059][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000004768_2441216.pth
+-[2023-09-19 11:26:57,043][72530] Fps is (10 sec: 6553.5, 60 sec: 6280.5, 300 sec: 6248.1). Total num frames: 5132288. Throughput: 0: 3168.7, 1: 3168.5. Samples: 2691716. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0)
+-[2023-09-19 11:26:57,045][72530] Avg episode reward: [(0, '133141.196'), (1, '161915.344')]
+-[2023-09-19 11:26:57,786][73219] Updated weights for policy 1, policy_version 5000 (0.0015)
+-[2023-09-19 11:26:57,787][73145] Updated weights for policy 0, policy_version 5040 (0.0011)
+-[2023-09-19 11:27:02,043][72530] Fps is (10 sec: 6553.6, 60 sec: 6280.5, 300 sec: 6248.1). Total num frames: 5165056. Throughput: 0: 3210.7, 1: 3210.9. Samples: 2728500. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0)
+-[2023-09-19 11:27:02,044][72530] Avg episode reward: [(0, '134217.012'), (1, '161927.050')]
+-[2023-09-19 11:27:07,043][72530] Fps is (10 sec: 5734.5, 60 sec: 6280.5, 300 sec: 6220.4). Total num frames: 5189632. Throughput: 0: 3215.4, 1: 3215.5. Samples: 2748004. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0)
+-[2023-09-19 11:27:07,044][72530] Avg episode reward: [(0, '139484.494'), (1, '161928.042')]
+-[2023-09-19 11:27:07,058][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000005056_2588672.pth...
+-[2023-09-19 11:27:07,062][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000004864_2490368.pth
+-[2023-09-19 11:27:07,070][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000005096_2609152.pth...
+-[2023-09-19 11:27:07,073][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000004904_2510848.pth
+-[2023-09-19 11:27:10,937][73145] Updated weights for policy 0, policy_version 5120 (0.0015)
+-[2023-09-19 11:27:10,937][73219] Updated weights for policy 1, policy_version 5080 (0.0015)
+-[2023-09-19 11:27:12,043][72530] Fps is (10 sec: 5734.5, 60 sec: 6280.6, 300 sec: 6248.1). Total num frames: 5222400. Throughput: 0: 3173.6, 1: 3173.6. Samples: 2785834. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0)
+-[2023-09-19 11:27:12,044][72530] Avg episode reward: [(0, '140906.115'), (1, '161939.285')]
+-[2023-09-19 11:27:17,043][72530] Fps is (10 sec: 6553.5, 60 sec: 6417.1, 300 sec: 6248.1). Total num frames: 5255168. Throughput: 0: 3151.1, 1: 3149.6. Samples: 2823006. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:27:17,045][72530] Avg episode reward: [(0, '145817.026'), (1, '161027.902')]
+-[2023-09-19 11:27:22,043][72530] Fps is (10 sec: 6553.6, 60 sec: 6417.1, 300 sec: 6248.1). Total num frames: 5287936. Throughput: 0: 3185.7, 1: 3185.7. Samples: 2842604. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:27:22,044][72530] Avg episode reward: [(0, '142531.824'), (1, '161093.623')]
+-[2023-09-19 11:27:22,055][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000005184_2654208.pth...
+-[2023-09-19 11:27:22,056][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000005144_2633728.pth...
+-[2023-09-19 11:27:22,061][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000005000_2560000.pth
+-[2023-09-19 11:27:22,064][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000004960_2539520.pth
+-[2023-09-19 11:27:23,721][73145] Updated weights for policy 0, policy_version 5200 (0.0010)
+-[2023-09-19 11:27:23,721][73219] Updated weights for policy 1, policy_version 5160 (0.0013)
+-[2023-09-19 11:27:27,043][72530] Fps is (10 sec: 6553.7, 60 sec: 6417.1, 300 sec: 6248.1). Total num frames: 5320704. Throughput: 0: 3188.8, 1: 3189.0. Samples: 2883390. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0)
+-[2023-09-19 11:27:27,044][72530] Avg episode reward: [(0, '142889.954'), (1, '161067.955')]
+-[2023-09-19 11:27:32,043][72530] Fps is (10 sec: 6553.6, 60 sec: 6417.0, 300 sec: 6248.1). Total num frames: 5353472. Throughput: 0: 3127.8, 1: 3128.0. Samples: 2916652. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:27:32,044][72530] Avg episode reward: [(0, '142889.954'), (1, '161121.140')]
+-[2023-09-19 11:27:37,043][72530] Fps is (10 sec: 5734.3, 60 sec: 6280.5, 300 sec: 6220.4). Total num frames: 5378048. Throughput: 0: 3133.1, 1: 3132.4. Samples: 2936188. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:27:37,045][72530] Avg episode reward: [(0, '142062.299'), (1, '159603.215')]
+-[2023-09-19 11:27:37,054][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000005232_2678784.pth...
+-[2023-09-19 11:27:37,055][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000005272_2699264.pth...
+-[2023-09-19 11:27:37,063][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000005056_2588672.pth
+-[2023-09-19 11:27:37,066][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000005096_2609152.pth
+-[2023-09-19 11:27:37,396][73145] Updated weights for policy 0, policy_version 5280 (0.0011)
+-[2023-09-19 11:27:37,396][73219] Updated weights for policy 1, policy_version 5240 (0.0014)
+-[2023-09-19 11:27:42,043][72530] Fps is (10 sec: 5734.3, 60 sec: 6280.5, 300 sec: 6248.1). Total num frames: 5410816. Throughput: 0: 3131.2, 1: 3132.0. Samples: 2973558. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:27:42,045][72530] Avg episode reward: [(0, '142062.299'), (1, '159574.648')]
+-[2023-09-19 11:27:47,043][72530] Fps is (10 sec: 6553.6, 60 sec: 6280.5, 300 sec: 6248.1). Total num frames: 5443584. Throughput: 0: 3132.0, 1: 3132.0. Samples: 3010382. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
+-[2023-09-19 11:27:47,045][72530] Avg episode reward: [(0, '143548.226'), (1, '160565.889')]
+-[2023-09-19 11:27:50,044][73145] Updated weights for policy 0, policy_version 5360 (0.0013)
+-[2023-09-19 11:27:50,045][73219] Updated weights for policy 1, policy_version 5320 (0.0012)
+-[2023-09-19 11:27:52,043][72530] Fps is (10 sec: 6553.6, 60 sec: 6280.5, 300 sec: 6275.9). Total num frames: 5476352. Throughput: 0: 3144.9, 1: 3145.5. Samples: 3031074. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:27:52,044][72530] Avg episode reward: [(0, '143548.226'), (1, '160563.875')]
+-[2023-09-19 11:27:52,054][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000005368_2748416.pth...
+-[2023-09-19 11:27:52,055][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000005328_2727936.pth...
+-[2023-09-19 11:27:52,061][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000005184_2654208.pth
+-[2023-09-19 11:27:52,062][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000005144_2633728.pth
+-[2023-09-19 11:27:57,043][72530] Fps is (10 sec: 5734.4, 60 sec: 6144.0, 300 sec: 6248.1). Total num frames: 5500928. Throughput: 0: 3089.5, 1: 3090.1. Samples: 3063918. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:27:57,045][72530] Avg episode reward: [(0, '146270.433'), (1, '160418.331')]
+-[2023-09-19 11:28:02,043][72530] Fps is (10 sec: 5734.6, 60 sec: 6144.0, 300 sec: 6275.9). Total num frames: 5533696. Throughput: 0: 3077.2, 1: 3077.4. Samples: 3099964. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0)
+-[2023-09-19 11:28:02,044][72530] Avg episode reward: [(0, '146167.425'), (1, '160418.331')]
+-[2023-09-19 11:28:04,104][73219] Updated weights for policy 1, policy_version 5400 (0.0013)
+-[2023-09-19 11:28:04,105][73145] Updated weights for policy 0, policy_version 5440 (0.0014)
+-[2023-09-19 11:28:07,043][72530] Fps is (10 sec: 6553.6, 60 sec: 6280.5, 300 sec: 6275.9). Total num frames: 5566464. Throughput: 0: 3076.4, 1: 3075.6. Samples: 3119446. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:28:07,044][72530] Avg episode reward: [(0, '146743.667'), (1, '161871.065')]
+-[2023-09-19 11:28:07,052][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000005456_2793472.pth...
+-[2023-09-19 11:28:07,052][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000005416_2772992.pth...
+-[2023-09-19 11:28:07,058][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000005272_2699264.pth
+-[2023-09-19 11:28:07,062][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000005232_2678784.pth
+-[2023-09-19 11:28:12,043][72530] Fps is (10 sec: 6553.5, 60 sec: 6280.5, 300 sec: 6275.9). Total num frames: 5599232. Throughput: 0: 3039.7, 1: 3039.5. Samples: 3156956. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:28:12,044][72530] Avg episode reward: [(0, '146503.770'), (1, '161818.415')]
+-[2023-09-19 11:28:17,043][72530] Fps is (10 sec: 5734.3, 60 sec: 6144.0, 300 sec: 6248.1). Total num frames: 5623808. Throughput: 0: 2895.2, 1: 2895.1. Samples: 3177218. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
+-[2023-09-19 11:28:17,044][72530] Avg episode reward: [(0, '146720.459'), (1, '161769.023')]
+-[2023-09-19 11:28:17,068][73145] Updated weights for policy 0, policy_version 5520 (0.0013)
+-[2023-09-19 11:28:17,069][73219] Updated weights for policy 1, policy_version 5480 (0.0012)
+-[2023-09-19 11:28:22,043][72530] Fps is (10 sec: 5734.3, 60 sec: 6144.0, 300 sec: 6248.1). Total num frames: 5656576. Throughput: 0: 3086.3, 1: 3086.2. Samples: 3213950. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0)
+-[2023-09-19 11:28:22,044][72530] Avg episode reward: [(0, '147474.306'), (1, '161768.790')]
+-[2023-09-19 11:28:22,055][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000005504_2818048.pth...
+-[2023-09-19 11:28:22,055][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000005544_2838528.pth...
+-[2023-09-19 11:28:22,062][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000005328_2727936.pth
+-[2023-09-19 11:28:22,065][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000005368_2748416.pth
+-[2023-09-19 11:28:27,043][72530] Fps is (10 sec: 6553.6, 60 sec: 6144.0, 300 sec: 6275.9). Total num frames: 5689344. Throughput: 0: 3045.5, 1: 3044.6. Samples: 3247612. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:28:27,044][72530] Avg episode reward: [(0, '146171.268'), (1, '161578.478')]
+-[2023-09-19 11:28:30,639][73219] Updated weights for policy 1, policy_version 5560 (0.0007)
+-[2023-09-19 11:28:30,640][73145] Updated weights for policy 0, policy_version 5600 (0.0014)
+-[2023-09-19 11:28:32,043][72530] Fps is (10 sec: 5734.4, 60 sec: 6007.5, 300 sec: 6248.1). Total num frames: 5713920. Throughput: 0: 3050.4, 1: 3051.6. Samples: 3284968. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:28:32,044][72530] Avg episode reward: [(0, '143678.262'), (1, '161606.329')]
+-[2023-09-19 11:28:37,043][72530] Fps is (10 sec: 5734.4, 60 sec: 6144.0, 300 sec: 6248.1). Total num frames: 5746688. Throughput: 0: 3003.7, 1: 3003.7. Samples: 3301410. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:28:37,044][72530] Avg episode reward: [(0, '147339.327'), (1, '161677.535')]
+-[2023-09-19 11:28:37,052][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000005632_2883584.pth...
+-[2023-09-19 11:28:37,052][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000005592_2863104.pth...
+-[2023-09-19 11:28:37,059][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000005456_2793472.pth
+-[2023-09-19 11:28:37,061][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000005416_2772992.pth
+-[2023-09-19 11:28:42,043][72530] Fps is (10 sec: 6553.7, 60 sec: 6144.0, 300 sec: 6275.9). Total num frames: 5779456. Throughput: 0: 3087.8, 1: 3087.2. Samples: 3341792. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0)
+-[2023-09-19 11:28:42,044][72530] Avg episode reward: [(0, '149917.742'), (1, '161865.342')]
+-[2023-09-19 11:28:43,733][73145] Updated weights for policy 0, policy_version 5680 (0.0015)
+-[2023-09-19 11:28:43,734][73219] Updated weights for policy 1, policy_version 5640 (0.0014)
+-[2023-09-19 11:28:47,043][72530] Fps is (10 sec: 6553.6, 60 sec: 6144.0, 300 sec: 6275.9). Total num frames: 5812224. Throughput: 0: 3101.5, 1: 3101.5. Samples: 3379098. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:28:47,044][72530] Avg episode reward: [(0, '150038.622'), (1, '161982.019')]
+-[2023-09-19 11:28:52,043][72530] Fps is (10 sec: 6553.6, 60 sec: 6144.0, 300 sec: 6275.9). Total num frames: 5844992. Throughput: 0: 3141.9, 1: 3141.4. Samples: 3402194. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
+-[2023-09-19 11:28:52,044][72530] Avg episode reward: [(0, '144197.749'), (1, '162024.019')]
+-[2023-09-19 11:28:52,065][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000005696_2916352.pth...
+-[2023-09-19 11:28:52,067][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000005736_2936832.pth...
+-[2023-09-19 11:28:52,069][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000005504_2818048.pth
+-[2023-09-19 11:28:52,072][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000005544_2838528.pth
+-[2023-09-19 11:28:56,545][73145] Updated weights for policy 0, policy_version 5760 (0.0009)
+-[2023-09-19 11:28:56,546][73219] Updated weights for policy 1, policy_version 5720 (0.0014)
+-[2023-09-19 11:28:57,043][72530] Fps is (10 sec: 6553.7, 60 sec: 6280.5, 300 sec: 6303.7). Total num frames: 5877760. Throughput: 0: 3141.5, 1: 3142.4. Samples: 3439730. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:28:57,044][72530] Avg episode reward: [(0, '138885.538'), (1, '162345.734')]
+-[2023-09-19 11:28:57,045][73131] Saving new best policy, reward=162345.734!
+-[2023-09-19 11:29:02,043][72530] Fps is (10 sec: 5734.4, 60 sec: 6144.0, 300 sec: 6275.9). Total num frames: 5902336. Throughput: 0: 3289.1, 1: 3289.5. Samples: 3473254. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:29:02,044][72530] Avg episode reward: [(0, '134517.899'), (1, '162329.045')]
+-[2023-09-19 11:29:07,043][72530] Fps is (10 sec: 6553.5, 60 sec: 6280.5, 300 sec: 6331.4). Total num frames: 5943296. Throughput: 0: 3101.0, 1: 3100.8. Samples: 3493030. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:29:07,045][72530] Avg episode reward: [(0, '128642.101'), (1, '162318.341')]
+-[2023-09-19 11:29:07,056][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000005784_2961408.pth...
+-[2023-09-19 11:29:07,056][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000005824_2981888.pth...
+-[2023-09-19 11:29:07,062][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000005592_2863104.pth
+-[2023-09-19 11:29:07,064][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000005632_2883584.pth
+-[2023-09-19 11:29:09,339][73145] Updated weights for policy 0, policy_version 5840 (0.0012)
+-[2023-09-19 11:29:09,340][73219] Updated weights for policy 1, policy_version 5800 (0.0013)
+-[2023-09-19 11:29:12,043][72530] Fps is (10 sec: 7372.7, 60 sec: 6280.5, 300 sec: 6303.7). Total num frames: 5976064. Throughput: 0: 3166.1, 1: 3166.1. Samples: 3532560. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:29:12,044][72530] Avg episode reward: [(0, '118954.396'), (1, '162291.376')]
+-[2023-09-19 11:29:17,043][72530] Fps is (10 sec: 6553.7, 60 sec: 6417.1, 300 sec: 6303.7). Total num frames: 6008832. Throughput: 0: 3187.8, 1: 3186.9. Samples: 3571832. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0)
+-[2023-09-19 11:29:17,044][72530] Avg episode reward: [(0, '114412.470'), (1, '162295.847')]
+-[2023-09-19 11:29:21,826][73145] Updated weights for policy 0, policy_version 5920 (0.0012)
+-[2023-09-19 11:29:21,826][73219] Updated weights for policy 1, policy_version 5880 (0.0015)
+-[2023-09-19 11:29:22,043][72530] Fps is (10 sec: 6553.6, 60 sec: 6417.1, 300 sec: 6331.4). Total num frames: 6041600. Throughput: 0: 3238.0, 1: 3237.2. Samples: 3592796. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:29:22,044][72530] Avg episode reward: [(0, '112785.270'), (1, '162279.161')]
+-[2023-09-19 11:29:22,053][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000005880_3010560.pth...
+-[2023-09-19 11:29:22,053][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000005920_3031040.pth...
+-[2023-09-19 11:29:22,057][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000005696_2916352.pth
+-[2023-09-19 11:29:22,061][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000005736_2936832.pth
+-[2023-09-19 11:29:27,043][72530] Fps is (10 sec: 5734.4, 60 sec: 6280.5, 300 sec: 6275.9). Total num frames: 6066176. Throughput: 0: 3176.2, 1: 3176.2. Samples: 3627652. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:29:27,044][72530] Avg episode reward: [(0, '112913.414'), (1, '161752.422')]
+-[2023-09-19 11:29:32,053][72530] Fps is (10 sec: 5728.9, 60 sec: 6416.0, 300 sec: 6303.5). Total num frames: 6098944. Throughput: 0: 3140.7, 1: 3142.2. Samples: 3661888. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:29:32,055][72530] Avg episode reward: [(0, '114352.426'), (1, '160799.718')]
+-[2023-09-19 11:29:36,186][73145] Updated weights for policy 0, policy_version 6000 (0.0013)
+-[2023-09-19 11:29:36,187][73219] Updated weights for policy 1, policy_version 5960 (0.0013)
+-[2023-09-19 11:29:37,043][72530] Fps is (10 sec: 5734.3, 60 sec: 6280.5, 300 sec: 6275.9). Total num frames: 6123520. Throughput: 0: 3071.6, 1: 3072.0. Samples: 3678658. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:29:37,044][72530] Avg episode reward: [(0, '114436.532'), (1, '160786.962')]
+-[2023-09-19 11:29:37,055][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000005960_3051520.pth...
+-[2023-09-19 11:29:37,055][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000006000_3072000.pth...
+-[2023-09-19 11:29:37,061][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000005784_2961408.pth
+-[2023-09-19 11:29:37,067][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000005824_2981888.pth
+-[2023-09-19 11:29:42,043][72530] Fps is (10 sec: 5740.0, 60 sec: 6280.5, 300 sec: 6275.9). Total num frames: 6156288. Throughput: 0: 3094.3, 1: 3094.0. Samples: 3718202. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:29:42,044][72530] Avg episode reward: [(0, '115826.562'), (1, '160797.026')]
+-[2023-09-19 11:29:47,043][72530] Fps is (10 sec: 6553.7, 60 sec: 6280.5, 300 sec: 6275.9). Total num frames: 6189056. Throughput: 0: 3107.9, 1: 3107.4. Samples: 3752942. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
+-[2023-09-19 11:29:47,044][72530] Avg episode reward: [(0, '116442.200'), (1, '160802.531')]
+-[2023-09-19 11:29:49,303][73219] Updated weights for policy 1, policy_version 6040 (0.0013)
+-[2023-09-19 11:29:49,304][73145] Updated weights for policy 0, policy_version 6080 (0.0015)
+-[2023-09-19 11:29:52,043][72530] Fps is (10 sec: 5734.3, 60 sec: 6144.0, 300 sec: 6248.1). Total num frames: 6213632. Throughput: 0: 3115.6, 1: 3116.0. Samples: 3773450. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
+-[2023-09-19 11:29:52,044][72530] Avg episode reward: [(0, '116782.945'), (1, '160812.704')]
+-[2023-09-19 11:29:52,055][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000006048_3096576.pth...
+-[2023-09-19 11:29:52,055][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000006088_3117056.pth...
+-[2023-09-19 11:29:52,064][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000005880_3010560.pth
+-[2023-09-19 11:29:52,066][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000005920_3031040.pth
+-[2023-09-19 11:29:57,043][72530] Fps is (10 sec: 5734.4, 60 sec: 6144.0, 300 sec: 6248.1). Total num frames: 6246400. Throughput: 0: 3059.6, 1: 3059.6. Samples: 3807922. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:29:57,044][72530] Avg episode reward: [(0, '116782.945'), (1, '160801.177')]
+-[2023-09-19 11:30:02,043][72530] Fps is (10 sec: 6144.0, 60 sec: 6212.2, 300 sec: 6262.0). Total num frames: 6275072. Throughput: 0: 2823.3, 1: 2823.1. Samples: 3825920. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:30:02,045][72530] Avg episode reward: [(0, '113033.870'), (1, '161341.845')]
+-[2023-09-19 11:30:03,323][73145] Updated weights for policy 0, policy_version 6160 (0.0013)
+-[2023-09-19 11:30:03,323][73219] Updated weights for policy 1, policy_version 6120 (0.0015)
+-[2023-09-19 11:30:07,043][72530] Fps is (10 sec: 5734.3, 60 sec: 6007.5, 300 sec: 6248.1). Total num frames: 6303744. Throughput: 0: 2978.1, 1: 2978.2. Samples: 3860830. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:30:07,045][72530] Avg episode reward: [(0, '113033.870'), (1, '161341.845')]
+-[2023-09-19 11:30:07,055][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000006136_3141632.pth...
+-[2023-09-19 11:30:07,055][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000006176_3162112.pth...
+-[2023-09-19 11:30:07,064][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000006000_3072000.pth
+-[2023-09-19 11:30:07,066][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000005960_3051520.pth
+-[2023-09-19 11:30:12,043][72530] Fps is (10 sec: 6144.1, 60 sec: 6007.5, 300 sec: 6248.1). Total num frames: 6336512. Throughput: 0: 3016.4, 1: 3017.1. Samples: 3899160. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0)
+-[2023-09-19 11:30:12,044][72530] Avg episode reward: [(0, '110251.349'), (1, '161327.497')]
+-[2023-09-19 11:30:16,823][73219] Updated weights for policy 1, policy_version 6200 (0.0013)
+-[2023-09-19 11:30:16,823][73145] Updated weights for policy 0, policy_version 6240 (0.0011)
+-[2023-09-19 11:30:17,043][72530] Fps is (10 sec: 6553.8, 60 sec: 6007.5, 300 sec: 6220.4). Total num frames: 6369280. Throughput: 0: 3019.8, 1: 3018.5. Samples: 3933552. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0)
+-[2023-09-19 11:30:17,044][72530] Avg episode reward: [(0, '110867.577'), (1, '161327.497')]
+-[2023-09-19 11:30:22,043][72530] Fps is (10 sec: 5734.3, 60 sec: 5870.9, 300 sec: 6220.4). Total num frames: 6393856. Throughput: 0: 3036.0, 1: 3036.0. Samples: 3951900. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:30:22,044][72530] Avg episode reward: [(0, '112712.732'), (1, '161204.256')]
+-[2023-09-19 11:30:22,056][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000006264_3207168.pth...
+-[2023-09-19 11:30:22,056][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000006224_3186688.pth...
+-[2023-09-19 11:30:22,063][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000006088_3117056.pth
+-[2023-09-19 11:30:22,065][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000006048_3096576.pth
+-[2023-09-19 11:30:27,043][72530] Fps is (10 sec: 4915.1, 60 sec: 5870.9, 300 sec: 6192.6). Total num frames: 6418432. Throughput: 0: 2950.9, 1: 2950.4. Samples: 3983760. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:30:27,044][72530] Avg episode reward: [(0, '113392.546'), (1, '161125.113')]
+-[2023-09-19 11:30:31,119][73145] Updated weights for policy 0, policy_version 6320 (0.0012)
+-[2023-09-19 11:30:31,119][73219] Updated weights for policy 1, policy_version 6280 (0.0013)
+-[2023-09-19 11:30:32,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5871.9, 300 sec: 6192.6). Total num frames: 6451200. Throughput: 0: 2960.9, 1: 2961.4. Samples: 4019448. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:30:32,044][72530] Avg episode reward: [(0, '113475.235'), (1, '161107.375')]
+-[2023-09-19 11:30:37,043][72530] Fps is (10 sec: 5734.3, 60 sec: 5870.9, 300 sec: 6164.8). Total num frames: 6475776. Throughput: 0: 2884.0, 1: 2883.7. Samples: 4032994. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:30:37,045][72530] Avg episode reward: [(0, '118367.276'), (1, '160625.932')]
+-[2023-09-19 11:30:37,054][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000006344_3248128.pth...
+-[2023-09-19 11:30:37,055][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000006304_3227648.pth...
+-[2023-09-19 11:30:37,061][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000006176_3162112.pth
+-[2023-09-19 11:30:37,064][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000006136_3141632.pth
+-[2023-09-19 11:30:42,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5870.9, 300 sec: 6164.8). Total num frames: 6508544. Throughput: 0: 2926.3, 1: 2927.1. Samples: 4071324. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:30:42,044][72530] Avg episode reward: [(0, '121712.371'), (1, '160963.772')]
+-[2023-09-19 11:30:44,991][73145] Updated weights for policy 0, policy_version 6400 (0.0014)
+-[2023-09-19 11:30:44,991][73219] Updated weights for policy 1, policy_version 6360 (0.0016)
+-[2023-09-19 11:30:47,043][72530] Fps is (10 sec: 6553.7, 60 sec: 5870.9, 300 sec: 6164.8). Total num frames: 6541312. Throughput: 0: 3155.9, 1: 3155.8. Samples: 4109948. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:30:47,044][72530] Avg episode reward: [(0, '130906.514'), (1, '160996.680')]
+-[2023-09-19 11:30:52,043][72530] Fps is (10 sec: 6553.6, 60 sec: 6007.5, 300 sec: 6164.8). Total num frames: 6574080. Throughput: 0: 2977.7, 1: 2978.5. Samples: 4128860. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0)
+-[2023-09-19 11:30:52,044][72530] Avg episode reward: [(0, '132721.030'), (1, '160740.250')]
+-[2023-09-19 11:30:52,053][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000006400_3276800.pth...
+-[2023-09-19 11:30:52,053][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000006440_3297280.pth...
+-[2023-09-19 11:30:52,060][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000006264_3207168.pth
+-[2023-09-19 11:30:52,061][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000006224_3186688.pth
+-[2023-09-19 11:30:57,043][72530] Fps is (10 sec: 6553.7, 60 sec: 6007.5, 300 sec: 6164.8). Total num frames: 6606848. Throughput: 0: 2999.1, 1: 2998.3. Samples: 4169040. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:30:57,044][72530] Avg episode reward: [(0, '135319.795'), (1, '160381.100')]
+-[2023-09-19 11:30:57,551][73145] Updated weights for policy 0, policy_version 6480 (0.0013)
+-[2023-09-19 11:30:57,551][73219] Updated weights for policy 1, policy_version 6440 (0.0014)
+-[2023-09-19 11:31:02,043][72530] Fps is (10 sec: 6553.7, 60 sec: 6075.8, 300 sec: 6192.6). Total num frames: 6639616. Throughput: 0: 2999.7, 1: 2999.9. Samples: 4203534. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:31:02,044][72530] Avg episode reward: [(0, '138147.376'), (1, '160443.505')]
+-[2023-09-19 11:31:07,043][72530] Fps is (10 sec: 5734.4, 60 sec: 6007.5, 300 sec: 6164.8). Total num frames: 6664192. Throughput: 0: 2995.4, 1: 2995.4. Samples: 4221484. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
+-[2023-09-19 11:31:07,044][72530] Avg episode reward: [(0, '140607.383'), (1, '160444.041')]
+-[2023-09-19 11:31:07,054][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000006488_3321856.pth...
+-[2023-09-19 11:31:07,054][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000006528_3342336.pth...
+-[2023-09-19 11:31:07,061][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000006304_3227648.pth
+-[2023-09-19 11:31:07,062][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000006344_3248128.pth
+-[2023-09-19 11:31:11,438][73219] Updated weights for policy 1, policy_version 6520 (0.0012)
+-[2023-09-19 11:31:11,438][73145] Updated weights for policy 0, policy_version 6560 (0.0013)
+-[2023-09-19 11:31:12,043][72530] Fps is (10 sec: 5734.3, 60 sec: 6007.5, 300 sec: 6192.6). Total num frames: 6696960. Throughput: 0: 3048.7, 1: 3048.4. Samples: 4258132. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0)
+-[2023-09-19 11:31:12,044][72530] Avg episode reward: [(0, '140794.377'), (1, '161324.369')]
+-[2023-09-19 11:31:17,043][72530] Fps is (10 sec: 6553.6, 60 sec: 6007.4, 300 sec: 6192.6). Total num frames: 6729728. Throughput: 0: 3077.7, 1: 3077.3. Samples: 4296424. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:31:17,045][72530] Avg episode reward: [(0, '146158.608'), (1, '161421.999')]
+-[2023-09-19 11:31:22,043][72530] Fps is (10 sec: 6553.7, 60 sec: 6144.0, 300 sec: 6192.6). Total num frames: 6762496. Throughput: 0: 3152.2, 1: 3152.3. Samples: 4316696. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:31:22,044][72530] Avg episode reward: [(0, '147169.785'), (1, '161725.816')]
+-[2023-09-19 11:31:22,057][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000006624_3391488.pth...
+-[2023-09-19 11:31:22,057][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000006584_3371008.pth...
+-[2023-09-19 11:31:22,064][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000006400_3276800.pth
+-[2023-09-19 11:31:22,065][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000006440_3297280.pth
+-[2023-09-19 11:31:24,435][73145] Updated weights for policy 0, policy_version 6640 (0.0016)
+-[2023-09-19 11:31:24,436][73219] Updated weights for policy 1, policy_version 6600 (0.0016)
+-[2023-09-19 11:31:27,043][72530] Fps is (10 sec: 5734.4, 60 sec: 6144.0, 300 sec: 6164.8). Total num frames: 6787072. Throughput: 0: 3107.4, 1: 3106.5. Samples: 4350952. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
+-[2023-09-19 11:31:27,044][72530] Avg episode reward: [(0, '147753.216'), (1, '161687.670')]
+-[2023-09-19 11:31:32,043][72530] Fps is (10 sec: 5734.5, 60 sec: 6144.0, 300 sec: 6164.8). Total num frames: 6819840. Throughput: 0: 3071.0, 1: 3071.2. Samples: 4386346. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0)
+-[2023-09-19 11:31:32,044][72530] Avg episode reward: [(0, '147753.216'), (1, '161687.670')]
+-[2023-09-19 11:31:37,043][72530] Fps is (10 sec: 6553.5, 60 sec: 6280.5, 300 sec: 6164.8). Total num frames: 6852608. Throughput: 0: 3060.3, 1: 3059.2. Samples: 4404236. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:31:37,044][72530] Avg episode reward: [(0, '155757.680'), (1, '162057.882')]
+-[2023-09-19 11:31:37,056][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000006672_3416064.pth...
+-[2023-09-19 11:31:37,056][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000006712_3436544.pth...
+-[2023-09-19 11:31:37,064][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000006528_3342336.pth
+-[2023-09-19 11:31:37,065][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000006488_3321856.pth
+-[2023-09-19 11:31:38,241][73145] Updated weights for policy 0, policy_version 6720 (0.0015)
+-[2023-09-19 11:31:38,242][73219] Updated weights for policy 1, policy_version 6680 (0.0014)
+-[2023-09-19 11:31:42,043][72530] Fps is (10 sec: 5734.3, 60 sec: 6144.0, 300 sec: 6137.1). Total num frames: 6877184. Throughput: 0: 3009.5, 1: 3010.6. Samples: 4439946. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:31:42,045][72530] Avg episode reward: [(0, '155757.680'), (1, '162057.882')]
+-[2023-09-19 11:31:47,043][72530] Fps is (10 sec: 5734.6, 60 sec: 6144.0, 300 sec: 6137.1). Total num frames: 6909952. Throughput: 0: 3026.3, 1: 3026.0. Samples: 4475886. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
+-[2023-09-19 11:31:47,044][72530] Avg episode reward: [(0, '156604.047'), (1, '162030.805')]
+-[2023-09-19 11:31:51,596][73145] Updated weights for policy 0, policy_version 6800 (0.0012)
+-[2023-09-19 11:31:51,596][73219] Updated weights for policy 1, policy_version 6760 (0.0015)
+-[2023-09-19 11:31:52,043][72530] Fps is (10 sec: 6553.7, 60 sec: 6144.0, 300 sec: 6137.1). Total num frames: 6942720. Throughput: 0: 3052.5, 1: 3052.3. Samples: 4496200. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0)
+-[2023-09-19 11:31:52,044][72530] Avg episode reward: [(0, '154864.725'), (1, '162040.931')]
+-[2023-09-19 11:31:52,052][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000006800_3481600.pth...
+-[2023-09-19 11:31:52,052][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000006760_3461120.pth...
+-[2023-09-19 11:31:52,059][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000006624_3391488.pth
+-[2023-09-19 11:31:52,061][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000006584_3371008.pth
+-[2023-09-19 11:31:57,043][72530] Fps is (10 sec: 6553.5, 60 sec: 6144.0, 300 sec: 6137.1). Total num frames: 6975488. Throughput: 0: 3054.7, 1: 3054.8. Samples: 4533058. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
+-[2023-09-19 11:31:57,044][72530] Avg episode reward: [(0, '150963.742'), (1, '162180.754')]
+-[2023-09-19 11:32:02,043][72530] Fps is (10 sec: 5734.4, 60 sec: 6007.5, 300 sec: 6137.1). Total num frames: 7000064. Throughput: 0: 3051.5, 1: 3052.9. Samples: 4571120. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
+-[2023-09-19 11:32:02,044][72530] Avg episode reward: [(0, '150392.522'), (1, '162181.685')]
+-[2023-09-19 11:32:04,785][73145] Updated weights for policy 0, policy_version 6880 (0.0009)
+-[2023-09-19 11:32:04,786][73219] Updated weights for policy 1, policy_version 6840 (0.0010)
+-[2023-09-19 11:32:07,043][72530] Fps is (10 sec: 5734.3, 60 sec: 6144.0, 300 sec: 6137.1). Total num frames: 7032832. Throughput: 0: 3026.7, 1: 3026.7. Samples: 4589098. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0)
+-[2023-09-19 11:32:07,044][72530] Avg episode reward: [(0, '145583.491'), (1, '162297.023')]
+-[2023-09-19 11:32:07,056][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000006848_3506176.pth...
+-[2023-09-19 11:32:07,056][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000006888_3526656.pth...
+-[2023-09-19 11:32:07,060][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000006672_3416064.pth
+-[2023-09-19 11:32:07,064][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000006712_3436544.pth
+-[2023-09-19 11:32:12,043][72530] Fps is (10 sec: 6553.5, 60 sec: 6144.0, 300 sec: 6137.1). Total num frames: 7065600. Throughput: 0: 3022.0, 1: 3022.0. Samples: 4622936. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
+-[2023-09-19 11:32:12,045][72530] Avg episode reward: [(0, '144862.441'), (1, '162339.817')]
+-[2023-09-19 11:32:17,043][72530] Fps is (10 sec: 5734.4, 60 sec: 6007.5, 300 sec: 6109.3). Total num frames: 7090176. Throughput: 0: 3051.5, 1: 3052.3. Samples: 4661014. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
+-[2023-09-19 11:32:17,045][72530] Avg episode reward: [(0, '140160.091'), (1, '162747.216')]
+-[2023-09-19 11:32:17,046][73131] Saving new best policy, reward=162747.216!
+-[2023-09-19 11:32:18,733][73145] Updated weights for policy 0, policy_version 6960 (0.0013)
+-[2023-09-19 11:32:18,734][73219] Updated weights for policy 1, policy_version 6920 (0.0014)
+-[2023-09-19 11:32:22,043][72530] Fps is (10 sec: 5734.4, 60 sec: 6007.5, 300 sec: 6109.3). Total num frames: 7122944. Throughput: 0: 3035.2, 1: 3036.6. Samples: 4677464. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
+-[2023-09-19 11:32:22,045][72530] Avg episode reward: [(0, '138598.620'), (1, '162798.619')]
+-[2023-09-19 11:32:22,055][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000006936_3551232.pth...
+-[2023-09-19 11:32:22,056][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000006976_3571712.pth...
+-[2023-09-19 11:32:22,062][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000006760_3461120.pth
+-[2023-09-19 11:32:22,063][73131] Saving new best policy, reward=162798.619!
+-[2023-09-19 11:32:22,065][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000006800_3481600.pth
+-[2023-09-19 11:32:27,043][72530] Fps is (10 sec: 5734.4, 60 sec: 6007.5, 300 sec: 6081.5). Total num frames: 7147520. Throughput: 0: 3005.6, 1: 3006.0. Samples: 4710464. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0)
+-[2023-09-19 11:32:27,044][72530] Avg episode reward: [(0, '140889.402'), (1, '162879.076')]
+-[2023-09-19 11:32:27,046][73131] Saving new best policy, reward=162879.076!
+-[2023-09-19 11:32:32,043][72530] Fps is (10 sec: 5734.4, 60 sec: 6007.4, 300 sec: 6109.3). Total num frames: 7180288. Throughput: 0: 3006.3, 1: 3006.6. Samples: 4746466. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
+-[2023-09-19 11:32:32,045][72530] Avg episode reward: [(0, '146675.404'), (1, '162955.653')]
+-[2023-09-19 11:32:32,046][73131] Saving new best policy, reward=162955.653!
+-[2023-09-19 11:32:33,165][73219] Updated weights for policy 1, policy_version 7000 (0.0013)
+-[2023-09-19 11:32:33,166][73145] Updated weights for policy 0, policy_version 7040 (0.0014)
+-[2023-09-19 11:32:37,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5870.9, 300 sec: 6081.5). Total num frames: 7204864. Throughput: 0: 2926.2, 1: 2927.6. Samples: 4759620. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
+-[2023-09-19 11:32:37,044][72530] Avg episode reward: [(0, '146675.404'), (1, '162959.948')]
+-[2023-09-19 11:32:37,054][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000007016_3592192.pth...
+-[2023-09-19 11:32:37,054][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000007056_3612672.pth...
+-[2023-09-19 11:32:37,060][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000006888_3526656.pth
+-[2023-09-19 11:32:37,061][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000006848_3506176.pth
+-[2023-09-19 11:32:37,061][73131] Saving new best policy, reward=162959.948!
+-[2023-09-19 11:32:42,043][72530] Fps is (10 sec: 4915.2, 60 sec: 5870.9, 300 sec: 6053.7). Total num frames: 7229440. Throughput: 0: 2894.3, 1: 2894.4. Samples: 4793548. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0)
+-[2023-09-19 11:32:42,045][72530] Avg episode reward: [(0, '152846.566'), (1, '163027.662')]
+-[2023-09-19 11:32:42,046][73131] Saving new best policy, reward=163027.662!
+-[2023-09-19 11:32:47,043][72530] Fps is (10 sec: 5734.5, 60 sec: 5870.9, 300 sec: 6053.8). Total num frames: 7262208. Throughput: 0: 2871.0, 1: 2869.7. Samples: 4829452. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:32:47,044][72530] Avg episode reward: [(0, '152846.566'), (1, '163027.662')]
+-[2023-09-19 11:32:47,786][73145] Updated weights for policy 0, policy_version 7120 (0.0013)
+-[2023-09-19 11:32:47,786][73219] Updated weights for policy 1, policy_version 7080 (0.0013)
+-[2023-09-19 11:32:52,043][72530] Fps is (10 sec: 6553.5, 60 sec: 5870.9, 300 sec: 6081.5). Total num frames: 7294976. Throughput: 0: 2870.4, 1: 2870.4. Samples: 4847430. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0)
+-[2023-09-19 11:32:52,044][72530] Avg episode reward: [(0, '158683.654'), (1, '163077.657')]
+-[2023-09-19 11:32:52,054][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000007104_3637248.pth...
+-[2023-09-19 11:32:52,054][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000007144_3657728.pth...
+-[2023-09-19 11:32:52,061][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000006936_3551232.pth
+-[2023-09-19 11:32:52,061][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000006976_3571712.pth
+-[2023-09-19 11:32:52,062][73131] Saving new best policy, reward=163077.657!
+-[2023-09-19 11:32:57,043][72530] Fps is (10 sec: 5734.3, 60 sec: 5734.4, 300 sec: 6053.7). Total num frames: 7319552. Throughput: 0: 2884.6, 1: 2885.0. Samples: 4882566. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0)
+-[2023-09-19 11:32:57,044][72530] Avg episode reward: [(0, '159312.798'), (1, '163099.001')]
+-[2023-09-19 11:32:57,046][73131] Saving new best policy, reward=163099.001!
+-[2023-09-19 11:33:01,325][73145] Updated weights for policy 0, policy_version 7200 (0.0015)
+-[2023-09-19 11:33:01,326][73219] Updated weights for policy 1, policy_version 7160 (0.0014)
+-[2023-09-19 11:33:02,043][72530] Fps is (10 sec: 5734.5, 60 sec: 5870.9, 300 sec: 6053.8). Total num frames: 7352320. Throughput: 0: 2874.4, 1: 2873.4. Samples: 4919666. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:33:02,044][72530] Avg episode reward: [(0, '154677.624'), (1, '162411.671')]
+-[2023-09-19 11:33:07,043][72530] Fps is (10 sec: 6553.6, 60 sec: 5870.9, 300 sec: 6053.7). Total num frames: 7385088. Throughput: 0: 2888.5, 1: 2887.3. Samples: 4937376. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:33:07,044][72530] Avg episode reward: [(0, '154955.709'), (1, '162052.665')]
+-[2023-09-19 11:33:07,054][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000007232_3702784.pth...
+-[2023-09-19 11:33:07,054][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000007192_3682304.pth...
+-[2023-09-19 11:33:07,059][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000007056_3612672.pth
+-[2023-09-19 11:33:07,063][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000007016_3592192.pth
+-[2023-09-19 11:33:12,043][72530] Fps is (10 sec: 6553.5, 60 sec: 5870.9, 300 sec: 6081.5). Total num frames: 7417856. Throughput: 0: 2946.5, 1: 2945.3. Samples: 4975594. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:33:12,044][72530] Avg episode reward: [(0, '152248.569'), (1, '160136.631')]
+-[2023-09-19 11:33:14,671][73219] Updated weights for policy 1, policy_version 7240 (0.0012)
+-[2023-09-19 11:33:14,672][73145] Updated weights for policy 0, policy_version 7280 (0.0010)
+-[2023-09-19 11:33:17,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5870.9, 300 sec: 6053.7). Total num frames: 7442432. Throughput: 0: 2951.6, 1: 2951.3. Samples: 5012094. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:33:17,044][72530] Avg episode reward: [(0, '148744.362'), (1, '160112.522')]
+-[2023-09-19 11:33:22,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5870.9, 300 sec: 6053.7). Total num frames: 7475200. Throughput: 0: 3001.9, 1: 3001.6. Samples: 5029778. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:33:22,044][72530] Avg episode reward: [(0, '143773.891'), (1, '160005.506')]
+-[2023-09-19 11:33:22,055][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000007280_3727360.pth...
+-[2023-09-19 11:33:22,055][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000007320_3747840.pth...
+-[2023-09-19 11:33:22,062][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000007144_3657728.pth
+-[2023-09-19 11:33:22,064][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000007104_3637248.pth
+-[2023-09-19 11:33:27,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5870.9, 300 sec: 6053.7). Total num frames: 7499776. Throughput: 0: 2989.4, 1: 2990.7. Samples: 5062652. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
+-[2023-09-19 11:33:27,045][72530] Avg episode reward: [(0, '140255.889'), (1, '159095.967')]
+-[2023-09-19 11:33:28,731][73145] Updated weights for policy 0, policy_version 7360 (0.0015)
+-[2023-09-19 11:33:28,731][73219] Updated weights for policy 1, policy_version 7320 (0.0015)
+-[2023-09-19 11:33:32,043][72530] Fps is (10 sec: 5734.5, 60 sec: 5870.9, 300 sec: 6053.8). Total num frames: 7532544. Throughput: 0: 2981.7, 1: 2982.1. Samples: 5097822. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
+-[2023-09-19 11:33:32,044][72530] Avg episode reward: [(0, '141984.249'), (1, '158018.359')]
+-[2023-09-19 11:33:37,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5870.9, 300 sec: 6026.0). Total num frames: 7557120. Throughput: 0: 2948.8, 1: 2948.9. Samples: 5112824. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
+-[2023-09-19 11:33:37,044][72530] Avg episode reward: [(0, '143692.297'), (1, '152337.381')]
+-[2023-09-19 11:33:37,055][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000007360_3768320.pth...
+-[2023-09-19 11:33:37,055][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000007400_3788800.pth...
+-[2023-09-19 11:33:37,063][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000007192_3682304.pth
+-[2023-09-19 11:33:37,066][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000007232_3702784.pth
+-[2023-09-19 11:33:42,043][72530] Fps is (10 sec: 5734.3, 60 sec: 6007.5, 300 sec: 6026.0). Total num frames: 7589888. Throughput: 0: 2966.8, 1: 2966.4. Samples: 5149558. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0)
+-[2023-09-19 11:33:42,045][72530] Avg episode reward: [(0, '143692.297'), (1, '151993.886')]
+-[2023-09-19 11:33:43,226][73219] Updated weights for policy 1, policy_version 7400 (0.0014)
+-[2023-09-19 11:33:43,228][73145] Updated weights for policy 0, policy_version 7440 (0.0015)
+-[2023-09-19 11:33:47,043][72530] Fps is (10 sec: 5734.6, 60 sec: 5870.9, 300 sec: 5998.2). Total num frames: 7614464. Throughput: 0: 2915.9, 1: 2916.2. Samples: 5182110. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0)
+-[2023-09-19 11:33:47,044][72530] Avg episode reward: [(0, '148573.588'), (1, '147997.923')]
+-[2023-09-19 11:33:52,043][72530] Fps is (10 sec: 5734.5, 60 sec: 5871.0, 300 sec: 5998.2). Total num frames: 7647232. Throughput: 0: 2925.6, 1: 2925.8. Samples: 5200686. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:33:52,044][72530] Avg episode reward: [(0, '148799.645'), (1, '147997.923')]
+-[2023-09-19 11:33:52,051][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000007448_3813376.pth...
+-[2023-09-19 11:33:52,052][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000007488_3833856.pth...
+-[2023-09-19 11:33:52,059][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000007280_3727360.pth
+-[2023-09-19 11:33:52,060][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000007320_3747840.pth
+-[2023-09-19 11:33:57,043][72530] Fps is (10 sec: 5734.3, 60 sec: 5870.9, 300 sec: 5998.2). Total num frames: 7671808. Throughput: 0: 2852.0, 1: 2851.8. Samples: 5232264. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:33:57,044][72530] Avg episode reward: [(0, '149325.137'), (1, '139943.474')]
+-[2023-09-19 11:33:57,818][73219] Updated weights for policy 1, policy_version 7480 (0.0015)
+-[2023-09-19 11:33:57,818][73145] Updated weights for policy 0, policy_version 7520 (0.0012)
+-[2023-09-19 11:34:02,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5870.9, 300 sec: 5970.4). Total num frames: 7704576. Throughput: 0: 2837.4, 1: 2838.8. Samples: 5267522. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:34:02,044][72530] Avg episode reward: [(0, '151014.673'), (1, '136184.034')]
+-[2023-09-19 11:34:07,043][72530] Fps is (10 sec: 5734.3, 60 sec: 5734.4, 300 sec: 5942.7). Total num frames: 7729152. Throughput: 0: 2822.8, 1: 2822.9. Samples: 5283834. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:34:07,045][72530] Avg episode reward: [(0, '151810.022'), (1, '129794.580')]
+-[2023-09-19 11:34:07,056][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000007528_3854336.pth...
+-[2023-09-19 11:34:07,056][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000007568_3874816.pth...
+-[2023-09-19 11:34:07,064][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000007400_3788800.pth
+-[2023-09-19 11:34:07,071][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000007360_3768320.pth
+-[2023-09-19 11:34:12,043][72530] Fps is (10 sec: 4915.2, 60 sec: 5597.9, 300 sec: 5914.9). Total num frames: 7753728. Throughput: 0: 2825.1, 1: 2824.1. Samples: 5316866. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
+-[2023-09-19 11:34:12,044][72530] Avg episode reward: [(0, '148050.631'), (1, '130670.879')]
+-[2023-09-19 11:34:12,371][73145] Updated weights for policy 0, policy_version 7600 (0.0013)
+-[2023-09-19 11:34:12,371][73219] Updated weights for policy 1, policy_version 7560 (0.0012)
+-[2023-09-19 11:34:17,043][72530] Fps is (10 sec: 5734.5, 60 sec: 5734.4, 300 sec: 5914.9). Total num frames: 7786496. Throughput: 0: 2825.1, 1: 2824.7. Samples: 5352062. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:34:17,044][72530] Avg episode reward: [(0, '149579.084'), (1, '130319.380')]
+-[2023-09-19 11:34:22,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5914.9). Total num frames: 7811072. Throughput: 0: 2840.5, 1: 2840.4. Samples: 5368464. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:34:22,044][72530] Avg episode reward: [(0, '149283.565'), (1, '126902.166')]
+-[2023-09-19 11:34:22,053][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000007608_3895296.pth...
+-[2023-09-19 11:34:22,054][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000007648_3915776.pth...
+-[2023-09-19 11:34:22,059][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000007448_3813376.pth
+-[2023-09-19 11:34:22,063][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000007488_3833856.pth
+-[2023-09-19 11:34:27,043][72530] Fps is (10 sec: 4915.2, 60 sec: 5597.9, 300 sec: 5887.3). Total num frames: 7835648. Throughput: 0: 2775.7, 1: 2776.0. Samples: 5399384. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:34:27,045][72530] Avg episode reward: [(0, '149283.565'), (1, '126902.166')]
+-[2023-09-19 11:34:27,264][73219] Updated weights for policy 1, policy_version 7640 (0.0012)
+-[2023-09-19 11:34:27,264][73145] Updated weights for policy 0, policy_version 7680 (0.0015)
+-[2023-09-19 11:34:32,043][72530] Fps is (10 sec: 5734.5, 60 sec: 5597.9, 300 sec: 5914.9). Total num frames: 7868416. Throughput: 0: 2824.0, 1: 2824.0. Samples: 5436266. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:34:32,044][72530] Avg episode reward: [(0, '144232.887'), (1, '135739.316')]
+-[2023-09-19 11:34:37,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5887.1). Total num frames: 7892992. Throughput: 0: 2799.2, 1: 2799.5. Samples: 5452628. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:34:37,044][72530] Avg episode reward: [(0, '144291.890'), (1, '135739.316')]
+-[2023-09-19 11:34:37,055][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000007688_3936256.pth...
+-[2023-09-19 11:34:37,055][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000007728_3956736.pth...
+-[2023-09-19 11:34:37,062][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000007528_3854336.pth
+-[2023-09-19 11:34:37,062][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000007568_3874816.pth
+-[2023-09-19 11:34:42,043][72530] Fps is (10 sec: 5324.8, 60 sec: 5529.6, 300 sec: 5873.3). Total num frames: 7921664. Throughput: 0: 2800.1, 1: 2800.4. Samples: 5484288. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:34:42,044][72530] Avg episode reward: [(0, '144843.661'), (1, '143710.582')]
+-[2023-09-19 11:34:42,048][73219] Updated weights for policy 1, policy_version 7720 (0.0013)
+-[2023-09-19 11:34:42,048][73145] Updated weights for policy 0, policy_version 7760 (0.0015)
+-[2023-09-19 11:34:47,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5597.8, 300 sec: 5887.1). Total num frames: 7950336. Throughput: 0: 2757.9, 1: 2756.6. Samples: 5515674. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0)
+-[2023-09-19 11:34:47,044][72530] Avg episode reward: [(0, '143205.243'), (1, '147140.750')]
+-[2023-09-19 11:34:52,043][72530] Fps is (10 sec: 5324.6, 60 sec: 5461.3, 300 sec: 5859.4). Total num frames: 7974912. Throughput: 0: 2780.3, 1: 2779.1. Samples: 5534010. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0)
+-[2023-09-19 11:34:52,044][72530] Avg episode reward: [(0, '141821.454'), (1, '149043.623')]
+-[2023-09-19 11:34:52,061][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000007776_3981312.pth...
+-[2023-09-19 11:34:52,063][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000007816_4001792.pth...
+-[2023-09-19 11:34:52,065][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000007608_3895296.pth
+-[2023-09-19 11:34:52,066][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000007648_3915776.pth
+-[2023-09-19 11:34:56,255][73145] Updated weights for policy 0, policy_version 7840 (0.0012)
+-[2023-09-19 11:34:56,255][73219] Updated weights for policy 1, policy_version 7800 (0.0014)
+-[2023-09-19 11:34:57,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5873.2). Total num frames: 8007680. Throughput: 0: 2815.3, 1: 2815.3. Samples: 5570242. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:34:57,044][72530] Avg episode reward: [(0, '138372.363'), (1, '156468.221')]
+-[2023-09-19 11:35:02,043][72530] Fps is (10 sec: 5734.6, 60 sec: 5461.3, 300 sec: 5859.4). Total num frames: 8032256. Throughput: 0: 2781.8, 1: 2782.4. Samples: 5602448. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:35:02,044][72530] Avg episode reward: [(0, '138372.363'), (1, '157445.674')]
+-[2023-09-19 11:35:07,043][72530] Fps is (10 sec: 5734.3, 60 sec: 5597.9, 300 sec: 5859.4). Total num frames: 8065024. Throughput: 0: 2774.6, 1: 2774.7. Samples: 5618186. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:35:07,044][72530] Avg episode reward: [(0, '142866.072'), (1, '153809.911')]
+-[2023-09-19 11:35:07,055][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000007896_4042752.pth...
+-[2023-09-19 11:35:07,055][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000007856_4022272.pth...
+-[2023-09-19 11:35:07,061][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000007728_3956736.pth
+-[2023-09-19 11:35:07,064][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000007688_3936256.pth
+-[2023-09-19 11:35:11,540][73219] Updated weights for policy 1, policy_version 7880 (0.0011)
+-[2023-09-19 11:35:11,541][73145] Updated weights for policy 0, policy_version 7920 (0.0013)
+-[2023-09-19 11:35:12,043][72530] Fps is (10 sec: 5734.5, 60 sec: 5597.9, 300 sec: 5831.6). Total num frames: 8089600. Throughput: 0: 2803.7, 1: 2803.8. Samples: 5651722. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0)
+-[2023-09-19 11:35:12,044][72530] Avg episode reward: [(0, '143261.806'), (1, '153809.911')]
+-[2023-09-19 11:35:17,043][72530] Fps is (10 sec: 5734.5, 60 sec: 5597.9, 300 sec: 5859.4). Total num frames: 8122368. Throughput: 0: 2571.9, 1: 2571.7. Samples: 5667726. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:35:17,044][72530] Avg episode reward: [(0, '145757.121'), (1, '154277.285')]
+-[2023-09-19 11:35:22,043][72530] Fps is (10 sec: 5734.3, 60 sec: 5597.9, 300 sec: 5859.4). Total num frames: 8146944. Throughput: 0: 2785.8, 1: 2785.5. Samples: 5703340. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:35:22,045][72530] Avg episode reward: [(0, '147899.769'), (1, '154650.090')]
+-[2023-09-19 11:35:22,055][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000007936_4063232.pth...
+-[2023-09-19 11:35:22,055][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000007976_4083712.pth...
+-[2023-09-19 11:35:22,061][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000007816_4001792.pth
+-[2023-09-19 11:35:22,062][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000007776_3981312.pth
+-[2023-09-19 11:35:25,473][73145] Updated weights for policy 0, policy_version 8000 (0.0013)
+-[2023-09-19 11:35:25,474][73219] Updated weights for policy 1, policy_version 7960 (0.0013)
+-[2023-09-19 11:35:27,043][72530] Fps is (10 sec: 5734.5, 60 sec: 5734.4, 300 sec: 5859.4). Total num frames: 8179712. Throughput: 0: 2814.4, 1: 2814.4. Samples: 5737588. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0)
+-[2023-09-19 11:35:27,044][72530] Avg episode reward: [(0, '152749.656'), (1, '154559.667')]
+-[2023-09-19 11:35:32,043][72530] Fps is (10 sec: 5734.5, 60 sec: 5597.9, 300 sec: 5859.4). Total num frames: 8204288. Throughput: 0: 2811.2, 1: 2811.5. Samples: 5768692. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0)
+-[2023-09-19 11:35:32,044][72530] Avg episode reward: [(0, '154504.272'), (1, '154707.152')]
+-[2023-09-19 11:35:37,043][72530] Fps is (10 sec: 4915.2, 60 sec: 5597.9, 300 sec: 5831.6). Total num frames: 8228864. Throughput: 0: 2771.9, 1: 2773.0. Samples: 5783532. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:35:37,044][72530] Avg episode reward: [(0, '154504.272'), (1, '154289.118')]
+-[2023-09-19 11:35:37,055][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000008056_4124672.pth...
+-[2023-09-19 11:35:37,055][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000008016_4104192.pth...
+-[2023-09-19 11:35:37,062][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000007896_4042752.pth
+-[2023-09-19 11:35:37,064][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000007856_4022272.pth
+-[2023-09-19 11:35:41,038][73145] Updated weights for policy 0, policy_version 8080 (0.0011)
+-[2023-09-19 11:35:41,039][73219] Updated weights for policy 1, policy_version 8040 (0.0014)
+-[2023-09-19 11:35:42,043][72530] Fps is (10 sec: 4915.2, 60 sec: 5529.6, 300 sec: 5803.8). Total num frames: 8253440. Throughput: 0: 2734.4, 1: 2734.8. Samples: 5816354. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:35:42,044][72530] Avg episode reward: [(0, '161395.630'), (1, '158048.524')]
+-[2023-09-19 11:35:42,045][73130] Saving new best policy, reward=161395.630!
+-[2023-09-19 11:35:47,043][72530] Fps is (10 sec: 5734.3, 60 sec: 5597.9, 300 sec: 5803.8). Total num frames: 8286208. Throughput: 0: 2761.4, 1: 2761.2. Samples: 5850962. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:35:47,044][72530] Avg episode reward: [(0, '159754.689'), (1, '158048.524')]
+-[2023-09-19 11:35:52,043][72530] Fps is (10 sec: 5734.3, 60 sec: 5597.9, 300 sec: 5776.1). Total num frames: 8310784. Throughput: 0: 2780.5, 1: 2780.5. Samples: 5868434. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
+-[2023-09-19 11:35:52,045][72530] Avg episode reward: [(0, '160738.664'), (1, '159082.738')]
+-[2023-09-19 11:35:52,055][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000008096_4145152.pth...
+-[2023-09-19 11:35:52,055][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000008136_4165632.pth...
+-[2023-09-19 11:35:52,060][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000007936_4063232.pth
+-[2023-09-19 11:35:52,062][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000007976_4083712.pth
+-[2023-09-19 11:35:55,537][73145] Updated weights for policy 0, policy_version 8160 (0.0015)
+-[2023-09-19 11:35:55,537][73219] Updated weights for policy 1, policy_version 8120 (0.0014)
+-[2023-09-19 11:35:57,043][72530] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5748.3). Total num frames: 8335360. Throughput: 0: 2770.3, 1: 2770.4. Samples: 5901056. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
+-[2023-09-19 11:35:57,044][72530] Avg episode reward: [(0, '162764.036'), (1, '158805.704')]
+-[2023-09-19 11:35:57,046][73130] Saving new best policy, reward=162764.036!
+-[2023-09-19 11:36:02,043][72530] Fps is (10 sec: 5734.5, 60 sec: 5597.9, 300 sec: 5776.1). Total num frames: 8368128. Throughput: 0: 2965.8, 1: 2965.9. Samples: 5934650. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
+-[2023-09-19 11:36:02,044][72530] Avg episode reward: [(0, '162349.625'), (1, '156768.108')]
+-[2023-09-19 11:36:07,043][72530] Fps is (10 sec: 5734.5, 60 sec: 5461.4, 300 sec: 5748.3). Total num frames: 8392704. Throughput: 0: 2770.8, 1: 2770.8. Samples: 5952710. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:36:07,043][72530] Avg episode reward: [(0, '161456.743'), (1, '158066.203')]
+-[2023-09-19 11:36:07,051][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000008176_4186112.pth...
+-[2023-09-19 11:36:07,051][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000008216_4206592.pth...
+-[2023-09-19 11:36:07,059][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000008016_4104192.pth
+-[2023-09-19 11:36:07,063][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000008056_4124672.pth
+-[2023-09-19 11:36:10,148][73145] Updated weights for policy 0, policy_version 8240 (0.0015)
+-[2023-09-19 11:36:10,148][73219] Updated weights for policy 1, policy_version 8200 (0.0015)
+-[2023-09-19 11:36:12,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5597.8, 300 sec: 5748.3). Total num frames: 8425472. Throughput: 0: 2751.9, 1: 2751.9. Samples: 5985260. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:36:12,044][72530] Avg episode reward: [(0, '161456.743'), (1, '157423.763')]
+-[2023-09-19 11:36:17,043][72530] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5720.5). Total num frames: 8450048. Throughput: 0: 2744.1, 1: 2743.7. Samples: 6015644. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:36:17,044][72530] Avg episode reward: [(0, '161135.132'), (1, '158376.754')]
+-[2023-09-19 11:36:22,043][72530] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5720.5). Total num frames: 8474624. Throughput: 0: 2786.1, 1: 2785.0. Samples: 6034230. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0)
+-[2023-09-19 11:36:22,044][72530] Avg episode reward: [(0, '160598.162'), (1, '158376.754')]
+-[2023-09-19 11:36:22,053][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000008256_4227072.pth...
+-[2023-09-19 11:36:22,054][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000008296_4247552.pth...
+-[2023-09-19 11:36:22,063][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000008136_4165632.pth
+-[2023-09-19 11:36:22,063][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000008096_4145152.pth
+-[2023-09-19 11:36:25,677][73219] Updated weights for policy 1, policy_version 8280 (0.0011)
+-[2023-09-19 11:36:25,678][73145] Updated weights for policy 0, policy_version 8320 (0.0011)
+-[2023-09-19 11:36:27,043][72530] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5692.7). Total num frames: 8499200. Throughput: 0: 2751.8, 1: 2751.2. Samples: 6063990. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0)
+-[2023-09-19 11:36:27,044][72530] Avg episode reward: [(0, '159747.417'), (1, '153840.543')]
+-[2023-09-19 11:36:32,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5692.8). Total num frames: 8531968. Throughput: 0: 2749.7, 1: 2749.3. Samples: 6098416. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:36:32,044][72530] Avg episode reward: [(0, '154229.110'), (1, '153123.695')]
+-[2023-09-19 11:36:37,043][72530] Fps is (10 sec: 6553.6, 60 sec: 5597.9, 300 sec: 5720.5). Total num frames: 8564736. Throughput: 0: 2758.1, 1: 2758.1. Samples: 6116658. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0)
+-[2023-09-19 11:36:37,044][72530] Avg episode reward: [(0, '149061.433'), (1, '154038.880')]
+-[2023-09-19 11:36:37,051][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000008344_4272128.pth...
+-[2023-09-19 11:36:37,051][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000008384_4292608.pth...
+-[2023-09-19 11:36:37,057][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000008176_4186112.pth
+-[2023-09-19 11:36:37,057][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000008216_4206592.pth
+-[2023-09-19 11:36:39,594][73219] Updated weights for policy 1, policy_version 8360 (0.0015)
+-[2023-09-19 11:36:39,594][73145] Updated weights for policy 0, policy_version 8400 (0.0016)
+-[2023-09-19 11:36:42,043][72530] Fps is (10 sec: 5734.3, 60 sec: 5597.9, 300 sec: 5692.7). Total num frames: 8589312. Throughput: 0: 2789.9, 1: 2790.9. Samples: 6152192. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0)
+-[2023-09-19 11:36:42,044][72530] Avg episode reward: [(0, '144058.161'), (1, '154059.173')]
+-[2023-09-19 11:36:47,043][72530] Fps is (10 sec: 5734.3, 60 sec: 5597.9, 300 sec: 5692.7). Total num frames: 8622080. Throughput: 0: 2794.4, 1: 2794.6. Samples: 6186154. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:36:47,044][72530] Avg episode reward: [(0, '140921.567'), (1, '153742.312')]
+-[2023-09-19 11:36:52,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5665.0). Total num frames: 8646656. Throughput: 0: 2793.8, 1: 2793.7. Samples: 6204150. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0)
+-[2023-09-19 11:36:52,044][72530] Avg episode reward: [(0, '137894.258'), (1, '154893.749')]
+-[2023-09-19 11:36:52,052][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000008424_4313088.pth...
+-[2023-09-19 11:36:52,052][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000008464_4333568.pth...
+-[2023-09-19 11:36:52,058][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000008256_4227072.pth
+-[2023-09-19 11:36:52,059][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000008296_4247552.pth
+-[2023-09-19 11:36:53,707][73145] Updated weights for policy 0, policy_version 8480 (0.0014)
+-[2023-09-19 11:36:53,707][73219] Updated weights for policy 1, policy_version 8440 (0.0015)
+-[2023-09-19 11:36:57,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5734.4, 300 sec: 5692.7). Total num frames: 8679424. Throughput: 0: 2832.6, 1: 2832.4. Samples: 6240182. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0)
+-[2023-09-19 11:36:57,044][72530] Avg episode reward: [(0, '137894.258'), (1, '155112.103')]
+-[2023-09-19 11:37:02,043][72530] Fps is (10 sec: 6553.6, 60 sec: 5734.4, 300 sec: 5692.7). Total num frames: 8712192. Throughput: 0: 2894.2, 1: 2894.2. Samples: 6276120. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:37:02,045][72530] Avg episode reward: [(0, '135885.742'), (1, '160768.230')]
+-[2023-09-19 11:37:07,043][72530] Fps is (10 sec: 5734.3, 60 sec: 5734.4, 300 sec: 5665.0). Total num frames: 8736768. Throughput: 0: 2876.4, 1: 2876.3. Samples: 6293104. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:37:07,045][72530] Avg episode reward: [(0, '135885.742'), (1, '160768.230')]
+-[2023-09-19 11:37:07,054][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000008512_4358144.pth...
+-[2023-09-19 11:37:07,055][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000008552_4378624.pth...
+-[2023-09-19 11:37:07,062][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000008344_4272128.pth
+-[2023-09-19 11:37:07,063][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000008384_4292608.pth
+-[2023-09-19 11:37:07,529][73145] Updated weights for policy 0, policy_version 8560 (0.0012)
+-[2023-09-19 11:37:07,529][73219] Updated weights for policy 1, policy_version 8520 (0.0013)
+-[2023-09-19 11:37:12,043][72530] Fps is (10 sec: 5734.5, 60 sec: 5734.4, 300 sec: 5692.7). Total num frames: 8769536. Throughput: 0: 2951.7, 1: 2951.7. Samples: 6329646. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:37:12,044][72530] Avg episode reward: [(0, '142564.431'), (1, '161744.693')]
+-[2023-09-19 11:37:17,043][72530] Fps is (10 sec: 5734.5, 60 sec: 5734.4, 300 sec: 5665.0). Total num frames: 8794112. Throughput: 0: 2942.3, 1: 2942.5. Samples: 6363234. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0)
+-[2023-09-19 11:37:17,044][72530] Avg episode reward: [(0, '142915.479'), (1, '161744.693')]
+-[2023-09-19 11:37:21,639][73219] Updated weights for policy 1, policy_version 8600 (0.0011)
+-[2023-09-19 11:37:21,640][73145] Updated weights for policy 0, policy_version 8640 (0.0013)
+-[2023-09-19 11:37:22,043][72530] Fps is (10 sec: 5734.3, 60 sec: 5870.9, 300 sec: 5692.7). Total num frames: 8826880. Throughput: 0: 2933.3, 1: 2933.3. Samples: 6380658. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0)
+-[2023-09-19 11:37:22,045][72530] Avg episode reward: [(0, '143397.695'), (1, '160966.343')]
+-[2023-09-19 11:37:22,054][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000008600_4403200.pth...
+-[2023-09-19 11:37:22,054][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000008640_4423680.pth...
+-[2023-09-19 11:37:22,062][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000008424_4313088.pth
+-[2023-09-19 11:37:22,065][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000008464_4333568.pth
+-[2023-09-19 11:37:27,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5870.9, 300 sec: 5665.0). Total num frames: 8851456. Throughput: 0: 2899.7, 1: 2898.4. Samples: 6413104. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0)
+-[2023-09-19 11:37:27,044][72530] Avg episode reward: [(0, '144691.029'), (1, '161003.911')]
+-[2023-09-19 11:37:32,043][72530] Fps is (10 sec: 4915.3, 60 sec: 5734.4, 300 sec: 5665.0). Total num frames: 8876032. Throughput: 0: 2857.8, 1: 2857.5. Samples: 6443340. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0)
+-[2023-09-19 11:37:32,044][72530] Avg episode reward: [(0, '145505.352'), (1, '159886.354')]
+-[2023-09-19 11:37:37,043][72530] Fps is (10 sec: 4915.1, 60 sec: 5597.8, 300 sec: 5665.0). Total num frames: 8900608. Throughput: 0: 2838.1, 1: 2838.1. Samples: 6459580. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0)
+-[2023-09-19 11:37:37,045][72530] Avg episode reward: [(0, '148461.800'), (1, '159898.604')]
+-[2023-09-19 11:37:37,054][73145] Updated weights for policy 0, policy_version 8720 (0.0016)
+-[2023-09-19 11:37:37,054][73219] Updated weights for policy 1, policy_version 8680 (0.0016)
+-[2023-09-19 11:37:37,055][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000008720_4464640.pth...
+-[2023-09-19 11:37:37,055][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000008680_4444160.pth...
+-[2023-09-19 11:37:37,058][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000008512_4358144.pth
+-[2023-09-19 11:37:37,058][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000008552_4378624.pth
+-[2023-09-19 11:37:42,043][72530] Fps is (10 sec: 5734.3, 60 sec: 5734.4, 300 sec: 5665.0). Total num frames: 8933376. Throughput: 0: 2844.0, 1: 2844.8. Samples: 6496178. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0)
+-[2023-09-19 11:37:42,045][72530] Avg episode reward: [(0, '148461.800'), (1, '159908.679')]
+-[2023-09-19 11:37:47,043][72530] Fps is (10 sec: 5734.5, 60 sec: 5597.9, 300 sec: 5637.2). Total num frames: 8957952. Throughput: 0: 2809.0, 1: 2810.2. Samples: 6528986. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0)
+-[2023-09-19 11:37:47,044][72530] Avg episode reward: [(0, '139457.708'), (1, '160880.552')]
+-[2023-09-19 11:37:52,043][72530] Fps is (10 sec: 4915.2, 60 sec: 5597.9, 300 sec: 5637.2). Total num frames: 8982528. Throughput: 0: 2798.8, 1: 2799.8. Samples: 6545042. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:37:52,045][72530] Avg episode reward: [(0, '139457.708'), (1, '160880.552')]
+-[2023-09-19 11:37:52,056][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000008752_4481024.pth...
+-[2023-09-19 11:37:52,057][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000008792_4501504.pth...
+-[2023-09-19 11:37:52,062][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000008600_4403200.pth
+-[2023-09-19 11:37:52,064][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000008640_4423680.pth
+-[2023-09-19 11:37:52,458][73219] Updated weights for policy 1, policy_version 8760 (0.0012)
+-[2023-09-19 11:37:52,459][73145] Updated weights for policy 0, policy_version 8800 (0.0011)
+-[2023-09-19 11:37:57,043][72530] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5609.4). Total num frames: 9007104. Throughput: 0: 2704.4, 1: 2704.2. Samples: 6573032. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:37:57,044][72530] Avg episode reward: [(0, '140620.851'), (1, '160021.637')]
+-[2023-09-19 11:38:02,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5609.4). Total num frames: 9039872. Throughput: 0: 2697.8, 1: 2697.6. Samples: 6606026. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:38:02,045][72530] Avg episode reward: [(0, '142260.932'), (1, '161163.491')]
+-[2023-09-19 11:38:07,043][72530] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5581.7). Total num frames: 9064448. Throughput: 0: 2677.0, 1: 2676.9. Samples: 6621582. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0)
+-[2023-09-19 11:38:07,045][72530] Avg episode reward: [(0, '140483.928'), (1, '159989.158')]
+-[2023-09-19 11:38:07,055][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000008832_4521984.pth...
+-[2023-09-19 11:38:07,057][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000008872_4542464.pth...
+-[2023-09-19 11:38:07,063][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000008680_4444160.pth
+-[2023-09-19 11:38:07,063][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000008720_4464640.pth
+-[2023-09-19 11:38:07,390][73145] Updated weights for policy 0, policy_version 8880 (0.0012)
+-[2023-09-19 11:38:07,390][73219] Updated weights for policy 1, policy_version 8840 (0.0013)
+-[2023-09-19 11:38:12,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5609.4). Total num frames: 9097216. Throughput: 0: 2721.5, 1: 2721.4. Samples: 6658036. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:38:12,045][72530] Avg episode reward: [(0, '138787.732'), (1, '159982.414')]
+-[2023-09-19 11:38:17,043][72530] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5581.7). Total num frames: 9121792. Throughput: 0: 2759.0, 1: 2758.8. Samples: 6691642. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:38:17,044][72530] Avg episode reward: [(0, '138787.732'), (1, '159979.750')]
+-[2023-09-19 11:38:22,043][72530] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5581.7). Total num frames: 9146368. Throughput: 0: 2732.9, 1: 2733.0. Samples: 6705544. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:38:22,045][72530] Avg episode reward: [(0, '137723.465'), (1, '159412.068')]
+-[2023-09-19 11:38:22,056][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000008912_4562944.pth...
+-[2023-09-19 11:38:22,056][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000008952_4583424.pth...
+-[2023-09-19 11:38:22,063][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000008752_4481024.pth
+-[2023-09-19 11:38:22,064][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000008792_4501504.pth
+-[2023-09-19 11:38:22,663][73219] Updated weights for policy 1, policy_version 8920 (0.0014)
+-[2023-09-19 11:38:22,663][73145] Updated weights for policy 0, policy_version 8960 (0.0016)
+-[2023-09-19 11:38:27,043][72530] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5553.9). Total num frames: 9170944. Throughput: 0: 2668.7, 1: 2667.9. Samples: 6736324. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:38:27,044][72530] Avg episode reward: [(0, '137729.460'), (1, '159412.184')]
+-[2023-09-19 11:38:32,043][72530] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5581.7). Total num frames: 9203712. Throughput: 0: 2658.7, 1: 2657.8. Samples: 6768230. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:38:32,044][72530] Avg episode reward: [(0, '137016.334'), (1, '160295.806')]
+-[2023-09-19 11:38:37,043][72530] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5553.9). Total num frames: 9228288. Throughput: 0: 2671.2, 1: 2670.4. Samples: 6785414. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0)
+-[2023-09-19 11:38:37,044][72530] Avg episode reward: [(0, '135131.016'), (1, '159223.120')]
+-[2023-09-19 11:38:37,055][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000009032_4624384.pth...
+-[2023-09-19 11:38:37,055][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000008992_4603904.pth...
+-[2023-09-19 11:38:37,064][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000008832_4521984.pth
+-[2023-09-19 11:38:37,065][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000008872_4542464.pth
+-[2023-09-19 11:38:37,583][73145] Updated weights for policy 0, policy_version 9040 (0.0013)
+-[2023-09-19 11:38:37,583][73219] Updated weights for policy 1, policy_version 9000 (0.0014)
+-[2023-09-19 11:38:42,043][72530] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5553.9). Total num frames: 9252864. Throughput: 0: 2718.7, 1: 2718.9. Samples: 6817726. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0)
+-[2023-09-19 11:38:42,044][72530] Avg episode reward: [(0, '136734.966'), (1, '159206.896')]
+-[2023-09-19 11:38:47,043][72530] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5526.1). Total num frames: 9277440. Throughput: 0: 2507.6, 1: 2694.9. Samples: 6840140. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:38:47,044][72530] Avg episode reward: [(0, '137794.300'), (1, '161324.133')]
+-[2023-09-19 11:38:52,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5553.9). Total num frames: 9310208. Throughput: 0: 2701.8, 1: 2702.8. Samples: 6864788. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:38:52,044][72530] Avg episode reward: [(0, '137794.300'), (1, '161324.133')]
+-[2023-09-19 11:38:52,053][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000009112_4665344.pth...
+-[2023-09-19 11:38:52,053][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000009072_4644864.pth...
+-[2023-09-19 11:38:52,059][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000008912_4562944.pth
+-[2023-09-19 11:38:52,059][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000008952_4583424.pth
+-[2023-09-19 11:38:53,194][73219] Updated weights for policy 1, policy_version 9080 (0.0013)
+-[2023-09-19 11:38:53,194][73145] Updated weights for policy 0, policy_version 9120 (0.0011)
+-[2023-09-19 11:38:57,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5526.1). Total num frames: 9334784. Throughput: 0: 2646.8, 1: 2646.8. Samples: 6896248. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:38:57,044][72530] Avg episode reward: [(0, '137042.173'), (1, '160811.317')]
+-[2023-09-19 11:39:02,043][72530] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5526.1). Total num frames: 9359360. Throughput: 0: 2603.1, 1: 2603.4. Samples: 6925932. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
+-[2023-09-19 11:39:02,044][72530] Avg episode reward: [(0, '137522.213'), (1, '160783.376')]
+-[2023-09-19 11:39:07,043][72530] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5526.1). Total num frames: 9383936. Throughput: 0: 2590.8, 1: 2591.2. Samples: 6938732. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0)
+-[2023-09-19 11:39:07,044][72530] Avg episode reward: [(0, '138050.348'), (1, '161331.845')]
+-[2023-09-19 11:39:07,054][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000009184_4702208.pth...
+-[2023-09-19 11:39:07,054][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000009144_4681728.pth...
+-[2023-09-19 11:39:07,060][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000009032_4624384.pth
+-[2023-09-19 11:39:07,062][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000008992_4603904.pth
+-[2023-09-19 11:39:09,053][73219] Updated weights for policy 1, policy_version 9160 (0.0013)
+-[2023-09-19 11:39:09,054][73145] Updated weights for policy 0, policy_version 9200 (0.0011)
+-[2023-09-19 11:39:12,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5526.1). Total num frames: 9416704. Throughput: 0: 2658.6, 1: 2658.4. Samples: 6975588. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0)
+-[2023-09-19 11:39:12,044][72530] Avg episode reward: [(0, '140041.122'), (1, '160346.458')]
+-[2023-09-19 11:39:17,043][72530] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5526.1). Total num frames: 9441280. Throughput: 0: 2631.2, 1: 2630.8. Samples: 7005018. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:39:17,044][72530] Avg episode reward: [(0, '140041.122'), (1, '160346.458')]
+-[2023-09-19 11:39:22,043][72530] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5526.1). Total num frames: 9465856. Throughput: 0: 2645.9, 1: 2646.0. Samples: 7023548. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:39:22,045][72530] Avg episode reward: [(0, '141321.149'), (1, '160469.876')]
+-[2023-09-19 11:39:22,053][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000009264_4743168.pth...
+-[2023-09-19 11:39:22,053][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000009224_4722688.pth...
+-[2023-09-19 11:39:22,057][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000009112_4665344.pth
+-[2023-09-19 11:39:22,062][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000009072_4644864.pth
+-[2023-09-19 11:39:23,736][73145] Updated weights for policy 0, policy_version 9280 (0.0016)
+-[2023-09-19 11:39:23,736][73219] Updated weights for policy 1, policy_version 9240 (0.0012)
+-[2023-09-19 11:39:27,043][72530] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5526.1). Total num frames: 9498624. Throughput: 0: 2682.5, 1: 2682.2. Samples: 7059138. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:39:27,044][72530] Avg episode reward: [(0, '143117.745'), (1, '160469.876')]
+-[2023-09-19 11:39:32,043][72530] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5526.1). Total num frames: 9523200. Throughput: 0: 2906.0, 1: 2718.8. Samples: 7093254. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:39:32,044][72530] Avg episode reward: [(0, '139677.367'), (1, '160492.361')]
+-[2023-09-19 11:39:37,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5461.4, 300 sec: 5540.0). Total num frames: 9555968. Throughput: 0: 2725.9, 1: 2724.9. Samples: 7110074. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
+-[2023-09-19 11:39:37,044][72530] Avg episode reward: [(0, '137931.041'), (1, '160516.950')]
+-[2023-09-19 11:39:37,052][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000009352_4788224.pth...
+-[2023-09-19 11:39:37,052][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000009312_4767744.pth...
+-[2023-09-19 11:39:37,064][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000009184_4702208.pth
+-[2023-09-19 11:39:37,064][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000009144_4681728.pth
+-[2023-09-19 11:39:38,025][73219] Updated weights for policy 1, policy_version 9320 (0.0014)
+-[2023-09-19 11:39:38,025][73145] Updated weights for policy 0, policy_version 9360 (0.0014)
+-[2023-09-19 11:39:42,043][72530] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5526.1). Total num frames: 9580544. Throughput: 0: 2739.1, 1: 2740.1. Samples: 7142812. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:39:42,045][72530] Avg episode reward: [(0, '135675.016'), (1, '160545.833')]
+-[2023-09-19 11:39:47,043][72530] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5526.1). Total num frames: 9605120. Throughput: 0: 2730.0, 1: 2729.9. Samples: 7171628. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:39:47,044][72530] Avg episode reward: [(0, '134266.068'), (1, '160294.298')]
+-[2023-09-19 11:39:52,043][72530] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5498.4). Total num frames: 9629696. Throughput: 0: 2788.4, 1: 2787.8. Samples: 7189664. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:39:52,045][72530] Avg episode reward: [(0, '134266.068'), (1, '160294.298')]
+-[2023-09-19 11:39:52,054][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000009384_4804608.pth...
+-[2023-09-19 11:39:52,054][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000009424_4825088.pth...
+-[2023-09-19 11:39:52,061][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000009264_4743168.pth
+-[2023-09-19 11:39:52,063][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000009224_4722688.pth
+-[2023-09-19 11:39:53,740][73145] Updated weights for policy 0, policy_version 9440 (0.0014)
+-[2023-09-19 11:39:53,740][73219] Updated weights for policy 1, policy_version 9400 (0.0011)
+-[2023-09-19 11:39:57,043][72530] Fps is (10 sec: 5734.2, 60 sec: 5461.3, 300 sec: 5526.1). Total num frames: 9662464. Throughput: 0: 2746.2, 1: 2746.2. Samples: 7222744. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:39:57,045][72530] Avg episode reward: [(0, '127890.525'), (1, '162301.441')]
+-[2023-09-19 11:40:02,043][72530] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5498.4). Total num frames: 9687040. Throughput: 0: 2803.2, 1: 2803.9. Samples: 7257338. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0)
+-[2023-09-19 11:40:02,044][72530] Avg episode reward: [(0, '126377.631'), (1, '162308.865')]
+-[2023-09-19 11:40:07,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5597.8, 300 sec: 5526.1). Total num frames: 9719808. Throughput: 0: 2767.5, 1: 2767.4. Samples: 7272620. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
+-[2023-09-19 11:40:07,045][72530] Avg episode reward: [(0, '126851.345'), (1, '162306.418')]
+-[2023-09-19 11:40:07,055][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000009512_4870144.pth...
+-[2023-09-19 11:40:07,055][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000009472_4849664.pth...
+-[2023-09-19 11:40:07,062][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000009352_4788224.pth
+-[2023-09-19 11:40:07,065][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000009312_4767744.pth
+-[2023-09-19 11:40:08,284][73145] Updated weights for policy 0, policy_version 9520 (0.0013)
+-[2023-09-19 11:40:08,284][73219] Updated weights for policy 1, policy_version 9480 (0.0012)
+-[2023-09-19 11:40:12,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5498.4). Total num frames: 9744384. Throughput: 0: 2756.3, 1: 2757.5. Samples: 7307258. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
+-[2023-09-19 11:40:12,044][72530] Avg episode reward: [(0, '124049.731'), (1, '162755.710')]
+-[2023-09-19 11:40:17,043][72530] Fps is (10 sec: 5734.6, 60 sec: 5597.9, 300 sec: 5526.1). Total num frames: 9777152. Throughput: 0: 2743.8, 1: 2743.8. Samples: 7340196. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0)
+-[2023-09-19 11:40:17,044][72530] Avg episode reward: [(0, '125342.829'), (1, '162760.657')]
+-[2023-09-19 11:40:22,043][72530] Fps is (10 sec: 5734.3, 60 sec: 5597.9, 300 sec: 5498.4). Total num frames: 9801728. Throughput: 0: 2757.9, 1: 2758.1. Samples: 7358298. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0)
+-[2023-09-19 11:40:22,044][72530] Avg episode reward: [(0, '126869.413'), (1, '162774.053')]
+-[2023-09-19 11:40:22,055][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000009552_4890624.pth...
+-[2023-09-19 11:40:22,055][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000009592_4911104.pth...
+-[2023-09-19 11:40:22,063][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000009384_4804608.pth
+-[2023-09-19 11:40:22,063][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000009424_4825088.pth
+-[2023-09-19 11:40:22,807][73219] Updated weights for policy 1, policy_version 9560 (0.0014)
+-[2023-09-19 11:40:22,808][73145] Updated weights for policy 0, policy_version 9600 (0.0015)
+-[2023-09-19 11:40:27,043][72530] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5498.4). Total num frames: 9826304. Throughput: 0: 2762.2, 1: 2761.2. Samples: 7391364. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0)
+-[2023-09-19 11:40:27,044][72530] Avg episode reward: [(0, '126869.413'), (1, '163199.726')]
+-[2023-09-19 11:40:27,045][73131] Saving new best policy, reward=163199.726!
+-[2023-09-19 11:40:32,043][72530] Fps is (10 sec: 5734.5, 60 sec: 5597.9, 300 sec: 5526.1). Total num frames: 9859072. Throughput: 0: 2813.1, 1: 2813.0. Samples: 7424800. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0)
+-[2023-09-19 11:40:32,044][72530] Avg episode reward: [(0, '127876.969'), (1, '163246.788')]
+-[2023-09-19 11:40:32,045][73131] Saving new best policy, reward=163246.788!
+-[2023-09-19 11:40:37,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5526.1). Total num frames: 9883648. Throughput: 0: 2764.8, 1: 2765.1. Samples: 7438508. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0)
+-[2023-09-19 11:40:37,044][72530] Avg episode reward: [(0, '128261.706'), (1, '163246.788')]
+-[2023-09-19 11:40:37,051][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000009632_4931584.pth...
+-[2023-09-19 11:40:37,052][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000009672_4952064.pth...
+-[2023-09-19 11:40:37,058][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000009472_4849664.pth
+-[2023-09-19 11:40:37,062][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000009512_4870144.pth
+-[2023-09-19 11:40:37,743][73145] Updated weights for policy 0, policy_version 9680 (0.0015)
+-[2023-09-19 11:40:37,744][73219] Updated weights for policy 1, policy_version 9640 (0.0013)
+-[2023-09-19 11:40:42,043][72530] Fps is (10 sec: 4915.2, 60 sec: 5461.4, 300 sec: 5498.4). Total num frames: 9908224. Throughput: 0: 2790.9, 1: 2791.1. Samples: 7473936. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0)
+-[2023-09-19 11:40:42,044][72530] Avg episode reward: [(0, '127401.924'), (1, '163340.260')]
+-[2023-09-19 11:40:42,046][73131] Saving new best policy, reward=163340.260!
+-[2023-09-19 11:40:47,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5526.1). Total num frames: 9940992. Throughput: 0: 2779.8, 1: 2779.3. Samples: 7507494. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0)
+-[2023-09-19 11:40:47,044][72530] Avg episode reward: [(0, '126125.877'), (1, '163360.879')]
+-[2023-09-19 11:40:47,045][73131] Saving new best policy, reward=163360.879!
+-[2023-09-19 11:40:51,985][73219] Updated weights for policy 1, policy_version 9720 (0.0013)
+-[2023-09-19 11:40:51,986][73145] Updated weights for policy 0, policy_version 9760 (0.0013)
+-[2023-09-19 11:40:52,043][72530] Fps is (10 sec: 6553.6, 60 sec: 5734.4, 300 sec: 5553.9). Total num frames: 9973760. Throughput: 0: 2804.9, 1: 2805.1. Samples: 7525070. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0)
+-[2023-09-19 11:40:52,044][72530] Avg episode reward: [(0, '124501.715'), (1, '163360.926')]
+-[2023-09-19 11:40:52,053][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000009720_4976640.pth...
+-[2023-09-19 11:40:52,053][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000009760_4997120.pth...
+-[2023-09-19 11:40:52,059][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000009552_4890624.pth
+-[2023-09-19 11:40:52,060][73131] Saving new best policy, reward=163360.926!
+-[2023-09-19 11:40:52,063][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000009592_4911104.pth
+-[2023-09-19 11:40:57,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5526.1). Total num frames: 9998336. Throughput: 0: 2820.8, 1: 2820.6. Samples: 7561120. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0)
+-[2023-09-19 11:40:57,044][72530] Avg episode reward: [(0, '121716.208'), (1, '162980.361')]
+-[2023-09-19 11:41:02,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5734.4, 300 sec: 5553.9). Total num frames: 10031104. Throughput: 0: 2839.9, 1: 2840.1. Samples: 7595796. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0)
+-[2023-09-19 11:41:02,044][72530] Avg episode reward: [(0, '123047.712'), (1, '162118.736')]
+-[2023-09-19 11:41:05,816][73145] Updated weights for policy 0, policy_version 9840 (0.0013)
+-[2023-09-19 11:41:05,816][73219] Updated weights for policy 1, policy_version 9800 (0.0011)
+-[2023-09-19 11:41:07,043][72530] Fps is (10 sec: 5734.3, 60 sec: 5597.9, 300 sec: 5526.1). Total num frames: 10055680. Throughput: 0: 2842.4, 1: 2842.3. Samples: 7614106. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:41:07,044][72530] Avg episode reward: [(0, '121775.268'), (1, '162040.085')]
+-[2023-09-19 11:41:07,093][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000009808_5021696.pth...
+-[2023-09-19 11:41:07,097][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000009632_4931584.pth
+-[2023-09-19 11:41:07,108][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000009848_5042176.pth...
+-[2023-09-19 11:41:07,112][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000009672_4952064.pth
+-[2023-09-19 11:41:12,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5734.4, 300 sec: 5553.9). Total num frames: 10088448. Throughput: 0: 2884.6, 1: 2885.2. Samples: 7651008. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:41:12,044][72530] Avg episode reward: [(0, '121120.688'), (1, '162013.153')]
+-[2023-09-19 11:41:17,043][72530] Fps is (10 sec: 6553.6, 60 sec: 5734.4, 300 sec: 5581.7). Total num frames: 10121216. Throughput: 0: 2908.3, 1: 2908.4. Samples: 7686552. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:41:17,044][72530] Avg episode reward: [(0, '124879.108'), (1, '161974.000')]
+-[2023-09-19 11:41:19,279][73145] Updated weights for policy 0, policy_version 9920 (0.0012)
+-[2023-09-19 11:41:19,279][73219] Updated weights for policy 1, policy_version 9880 (0.0014)
+-[2023-09-19 11:41:22,043][72530] Fps is (10 sec: 6553.6, 60 sec: 5870.9, 300 sec: 5609.4). Total num frames: 10153984. Throughput: 0: 2966.0, 1: 2965.8. Samples: 7705438. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:41:22,044][72530] Avg episode reward: [(0, '124879.108'), (1, '161966.557')]
+-[2023-09-19 11:41:22,053][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000009936_5087232.pth...
+-[2023-09-19 11:41:22,054][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000009896_5066752.pth...
+-[2023-09-19 11:41:22,063][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000009720_4976640.pth
+-[2023-09-19 11:41:22,063][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000009760_4997120.pth
+-[2023-09-19 11:41:27,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5870.9, 300 sec: 5581.7). Total num frames: 10178560. Throughput: 0: 2936.0, 1: 2936.1. Samples: 7738182. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:41:27,045][72530] Avg episode reward: [(0, '127104.430'), (1, '161743.941')]
+-[2023-09-19 11:41:32,043][72530] Fps is (10 sec: 4915.2, 60 sec: 5734.4, 300 sec: 5553.9). Total num frames: 10203136. Throughput: 0: 2947.0, 1: 2947.1. Samples: 7772726. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:41:32,044][72530] Avg episode reward: [(0, '128493.741'), (1, '161743.941')]
+-[2023-09-19 11:41:33,872][73219] Updated weights for policy 1, policy_version 9960 (0.0008)
+-[2023-09-19 11:41:33,873][73145] Updated weights for policy 0, policy_version 10000 (0.0013)
+-[2023-09-19 11:41:37,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5870.9, 300 sec: 5581.7). Total num frames: 10235904. Throughput: 0: 2945.2, 1: 2945.2. Samples: 7790142. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:41:37,044][72530] Avg episode reward: [(0, '127668.095'), (1, '162203.421')]
+-[2023-09-19 11:41:37,054][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000009976_5107712.pth...
+-[2023-09-19 11:41:37,055][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000010016_5128192.pth...
+-[2023-09-19 11:41:37,061][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000009808_5021696.pth
+-[2023-09-19 11:41:37,064][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000009848_5042176.pth
+-[2023-09-19 11:41:42,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5870.9, 300 sec: 5553.9). Total num frames: 10260480. Throughput: 0: 2933.3, 1: 2932.4. Samples: 7825076. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:41:42,044][72530] Avg episode reward: [(0, '129918.117'), (1, '162258.975')]
+-[2023-09-19 11:41:47,043][72530] Fps is (10 sec: 5734.5, 60 sec: 5870.9, 300 sec: 5581.7). Total num frames: 10293248. Throughput: 0: 2916.2, 1: 2916.0. Samples: 7858242. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:41:47,044][72530] Avg episode reward: [(0, '127362.808'), (1, '162303.333')]
+-[2023-09-19 11:41:47,993][73219] Updated weights for policy 1, policy_version 10040 (0.0015)
+-[2023-09-19 11:41:47,993][73145] Updated weights for policy 0, policy_version 10080 (0.0013)
+-[2023-09-19 11:41:52,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5734.4, 300 sec: 5553.9). Total num frames: 10317824. Throughput: 0: 2920.8, 1: 2920.8. Samples: 7876978. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:41:52,044][72530] Avg episode reward: [(0, '126406.406'), (1, '162333.274')]
+-[2023-09-19 11:41:52,051][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000010096_5169152.pth...
+-[2023-09-19 11:41:52,051][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000010056_5148672.pth...
+-[2023-09-19 11:41:52,060][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000009936_5087232.pth
+-[2023-09-19 11:41:52,060][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000009896_5066752.pth
+-[2023-09-19 11:41:57,043][72530] Fps is (10 sec: 5734.5, 60 sec: 5870.9, 300 sec: 5553.9). Total num frames: 10350592. Throughput: 0: 2853.3, 1: 2852.7. Samples: 7907776. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:41:57,044][72530] Avg episode reward: [(0, '123833.586'), (1, '162357.732')]
+-[2023-09-19 11:42:02,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5734.4, 300 sec: 5553.9). Total num frames: 10375168. Throughput: 0: 2849.7, 1: 2849.6. Samples: 7943016. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:42:02,044][72530] Avg episode reward: [(0, '119983.882'), (1, '162619.479')]
+-[2023-09-19 11:42:02,675][73219] Updated weights for policy 1, policy_version 10120 (0.0014)
+-[2023-09-19 11:42:02,676][73145] Updated weights for policy 0, policy_version 10160 (0.0015)
+-[2023-09-19 11:42:07,043][72530] Fps is (10 sec: 4915.1, 60 sec: 5734.4, 300 sec: 5526.1). Total num frames: 10399744. Throughput: 0: 2834.9, 1: 2834.8. Samples: 7960578. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:42:07,045][72530] Avg episode reward: [(0, '119983.882'), (1, '162619.479')]
+-[2023-09-19 11:42:07,089][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000010144_5193728.pth...
+-[2023-09-19 11:42:07,090][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000010184_5214208.pth...
+-[2023-09-19 11:42:07,093][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000009976_5107712.pth
+-[2023-09-19 11:42:07,096][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000010016_5128192.pth
+-[2023-09-19 11:42:12,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5734.4, 300 sec: 5553.9). Total num frames: 10432512. Throughput: 0: 2856.8, 1: 2857.6. Samples: 7995330. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:42:12,044][72530] Avg episode reward: [(0, '117278.968'), (1, '162975.817')]
+-[2023-09-19 11:42:17,043][72530] Fps is (10 sec: 5734.5, 60 sec: 5597.9, 300 sec: 5526.1). Total num frames: 10457088. Throughput: 0: 2837.4, 1: 2838.5. Samples: 8028138. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:42:17,044][72530] Avg episode reward: [(0, '117278.968'), (1, '162975.817')]
+-[2023-09-19 11:42:17,136][73219] Updated weights for policy 1, policy_version 10200 (0.0013)
+-[2023-09-19 11:42:17,136][73145] Updated weights for policy 0, policy_version 10240 (0.0014)
+-[2023-09-19 11:42:22,043][72530] Fps is (10 sec: 5734.3, 60 sec: 5597.9, 300 sec: 5553.9). Total num frames: 10489856. Throughput: 0: 2827.2, 1: 2828.1. Samples: 8044630. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:42:22,044][72530] Avg episode reward: [(0, '121515.315'), (1, '162988.813')]
+-[2023-09-19 11:42:22,055][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000010224_5234688.pth...
+-[2023-09-19 11:42:22,055][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000010264_5255168.pth...
+-[2023-09-19 11:42:22,063][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000010056_5148672.pth
+-[2023-09-19 11:42:22,064][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000010096_5169152.pth
+-[2023-09-19 11:42:27,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5553.9). Total num frames: 10514432. Throughput: 0: 2792.9, 1: 2792.8. Samples: 8076430. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0)
+-[2023-09-19 11:42:27,044][72530] Avg episode reward: [(0, '118834.382'), (1, '162994.952')]
+-[2023-09-19 11:42:31,795][73145] Updated weights for policy 0, policy_version 10320 (0.0014)
+-[2023-09-19 11:42:31,795][73219] Updated weights for policy 1, policy_version 10280 (0.0014)
+-[2023-09-19 11:42:32,043][72530] Fps is (10 sec: 5734.5, 60 sec: 5734.4, 300 sec: 5581.7). Total num frames: 10547200. Throughput: 0: 2815.4, 1: 2815.5. Samples: 8111630. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0)
+-[2023-09-19 11:42:32,044][72530] Avg episode reward: [(0, '118369.672'), (1, '161883.949')]
+-[2023-09-19 11:42:37,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5553.9). Total num frames: 10571776. Throughput: 0: 2810.9, 1: 2810.8. Samples: 8129954. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0)
+-[2023-09-19 11:42:37,044][72530] Avg episode reward: [(0, '121189.235'), (1, '161513.570')]
+-[2023-09-19 11:42:37,051][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000010304_5275648.pth...
+-[2023-09-19 11:42:37,051][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000010344_5296128.pth...
+-[2023-09-19 11:42:37,057][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000010144_5193728.pth
+-[2023-09-19 11:42:37,058][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000010184_5214208.pth
+-[2023-09-19 11:42:42,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5734.4, 300 sec: 5581.7). Total num frames: 10604544. Throughput: 0: 2861.8, 1: 2861.8. Samples: 8165336. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:42:42,044][72530] Avg episode reward: [(0, '121261.492'), (1, '161513.431')]
+-[2023-09-19 11:42:45,967][73219] Updated weights for policy 1, policy_version 10360 (0.0013)
+-[2023-09-19 11:42:45,968][73145] Updated weights for policy 0, policy_version 10400 (0.0014)
+-[2023-09-19 11:42:47,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5581.7). Total num frames: 10629120. Throughput: 0: 2844.1, 1: 2844.1. Samples: 8198984. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:42:47,044][72530] Avg episode reward: [(0, '118032.842'), (1, '157614.308')]
+-[2023-09-19 11:42:52,043][72530] Fps is (10 sec: 5734.5, 60 sec: 5734.4, 300 sec: 5609.4). Total num frames: 10661888. Throughput: 0: 2843.3, 1: 2844.3. Samples: 8216516. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
+-[2023-09-19 11:42:52,044][72530] Avg episode reward: [(0, '118032.842'), (1, '156763.229')]
+-[2023-09-19 11:42:52,054][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000010392_5320704.pth...
+-[2023-09-19 11:42:52,054][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000010432_5341184.pth...
+-[2023-09-19 11:42:52,062][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000010224_5234688.pth
+-[2023-09-19 11:42:52,062][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000010264_5255168.pth
+-[2023-09-19 11:42:57,043][72530] Fps is (10 sec: 6553.7, 60 sec: 5734.4, 300 sec: 5609.4). Total num frames: 10694656. Throughput: 0: 2862.2, 1: 2861.2. Samples: 8252880. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:42:57,044][72530] Avg episode reward: [(0, '113836.289'), (1, '152570.666')]
+-[2023-09-19 11:42:59,347][73219] Updated weights for policy 1, policy_version 10440 (0.0013)
+-[2023-09-19 11:42:59,348][73145] Updated weights for policy 0, policy_version 10480 (0.0014)
+-[2023-09-19 11:43:02,043][72530] Fps is (10 sec: 5734.5, 60 sec: 5734.4, 300 sec: 5609.4). Total num frames: 10719232. Throughput: 0: 2911.6, 1: 2911.6. Samples: 8290182. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:43:02,044][72530] Avg episode reward: [(0, '113836.289'), (1, '152570.666')]
+-[2023-09-19 11:43:07,043][72530] Fps is (10 sec: 4915.1, 60 sec: 5734.4, 300 sec: 5581.7). Total num frames: 10743808. Throughput: 0: 2894.9, 1: 2894.2. Samples: 8305140. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0)
+-[2023-09-19 11:43:07,045][72530] Avg episode reward: [(0, '115267.182'), (1, '149740.570')]
+-[2023-09-19 11:43:07,055][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000010512_5382144.pth...
+-[2023-09-19 11:43:07,055][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000010472_5361664.pth...
+-[2023-09-19 11:43:07,064][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000010304_5275648.pth
+-[2023-09-19 11:43:07,065][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000010344_5296128.pth
+-[2023-09-19 11:43:12,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5734.4, 300 sec: 5609.4). Total num frames: 10776576. Throughput: 0: 2920.7, 1: 2921.1. Samples: 8339310. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0)
+-[2023-09-19 11:43:12,044][72530] Avg episode reward: [(0, '112738.453'), (1, '147363.933')]
+-[2023-09-19 11:43:13,928][73145] Updated weights for policy 0, policy_version 10560 (0.0015)
+-[2023-09-19 11:43:13,928][73219] Updated weights for policy 1, policy_version 10520 (0.0013)
+-[2023-09-19 11:43:17,043][72530] Fps is (10 sec: 6553.7, 60 sec: 5870.9, 300 sec: 5637.2). Total num frames: 10809344. Throughput: 0: 2925.9, 1: 2925.9. Samples: 8374958. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:43:17,044][72530] Avg episode reward: [(0, '112692.445'), (1, '139212.880')]
+-[2023-09-19 11:43:22,043][72530] Fps is (10 sec: 5734.3, 60 sec: 5734.4, 300 sec: 5637.2). Total num frames: 10833920. Throughput: 0: 2885.6, 1: 2885.7. Samples: 8389664. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:43:22,044][72530] Avg episode reward: [(0, '111524.427'), (1, '138648.058')]
+-[2023-09-19 11:43:22,054][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000010560_5406720.pth...
+-[2023-09-19 11:43:22,054][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000010600_5427200.pth...
+-[2023-09-19 11:43:22,059][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000010392_5320704.pth
+-[2023-09-19 11:43:22,060][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000010432_5341184.pth
+-[2023-09-19 11:43:27,043][72530] Fps is (10 sec: 4915.1, 60 sec: 5734.4, 300 sec: 5609.4). Total num frames: 10858496. Throughput: 0: 2801.5, 1: 2801.5. Samples: 8417468. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:43:27,044][72530] Avg episode reward: [(0, '111524.427'), (1, '136941.524')]
+-[2023-09-19 11:43:29,536][73145] Updated weights for policy 0, policy_version 10640 (0.0016)
+-[2023-09-19 11:43:29,536][73219] Updated weights for policy 1, policy_version 10600 (0.0013)
+-[2023-09-19 11:43:32,043][72530] Fps is (10 sec: 4915.3, 60 sec: 5597.9, 300 sec: 5609.4). Total num frames: 10883072. Throughput: 0: 2830.2, 1: 2830.5. Samples: 8453716. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:43:32,044][72530] Avg episode reward: [(0, '107385.986'), (1, '135321.775')]
+-[2023-09-19 11:43:37,043][72530] Fps is (10 sec: 5734.5, 60 sec: 5734.4, 300 sec: 5637.2). Total num frames: 10915840. Throughput: 0: 2819.7, 1: 2819.8. Samples: 8470292. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0)
+-[2023-09-19 11:43:37,044][72530] Avg episode reward: [(0, '107385.986'), (1, '135321.775')]
+-[2023-09-19 11:43:37,052][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000010640_5447680.pth...
+-[2023-09-19 11:43:37,052][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000010680_5468160.pth...
+-[2023-09-19 11:43:37,056][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000010512_5382144.pth
+-[2023-09-19 11:43:37,058][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000010472_5361664.pth
+-[2023-09-19 11:43:42,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5637.2). Total num frames: 10940416. Throughput: 0: 2781.7, 1: 2783.1. Samples: 8503296. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:43:42,044][72530] Avg episode reward: [(0, '100071.875'), (1, '136457.439')]
+-[2023-09-19 11:43:44,019][73219] Updated weights for policy 1, policy_version 10680 (0.0013)
+-[2023-09-19 11:43:44,019][73145] Updated weights for policy 0, policy_version 10720 (0.0016)
+-[2023-09-19 11:43:47,043][72530] Fps is (10 sec: 4915.1, 60 sec: 5597.9, 300 sec: 5609.4). Total num frames: 10964992. Throughput: 0: 2720.2, 1: 2719.9. Samples: 8534988. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:43:47,044][72530] Avg episode reward: [(0, '99838.586'), (1, '136457.439')]
+-[2023-09-19 11:43:52,043][72530] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5609.4). Total num frames: 10989568. Throughput: 0: 2733.8, 1: 2733.7. Samples: 8551178. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0)
+-[2023-09-19 11:43:52,044][72530] Avg episode reward: [(0, '96058.014'), (1, '144304.212')]
+-[2023-09-19 11:43:52,051][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000010752_5505024.pth...
+-[2023-09-19 11:43:52,051][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000010712_5484544.pth...
+-[2023-09-19 11:43:52,059][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000010600_5427200.pth
+-[2023-09-19 11:43:52,061][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000010560_5406720.pth
+-[2023-09-19 11:43:57,043][72530] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5609.4). Total num frames: 11014144. Throughput: 0: 2672.1, 1: 2671.8. Samples: 8579786. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0)
+-[2023-09-19 11:43:57,044][72530] Avg episode reward: [(0, '94439.101'), (1, '146370.302')]
+-[2023-09-19 11:44:00,053][73145] Updated weights for policy 0, policy_version 10800 (0.0011)
+-[2023-09-19 11:44:00,053][73219] Updated weights for policy 1, policy_version 10760 (0.0014)
+-[2023-09-19 11:44:02,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5637.2). Total num frames: 11046912. Throughput: 0: 2656.6, 1: 2656.7. Samples: 8614056. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:44:02,044][72530] Avg episode reward: [(0, '94439.101'), (1, '149966.737')]
+-[2023-09-19 11:44:07,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5609.4). Total num frames: 11071488. Throughput: 0: 2659.8, 1: 2659.7. Samples: 8629044. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:44:07,044][72530] Avg episode reward: [(0, '89650.521'), (1, '155598.656')]
+-[2023-09-19 11:44:07,053][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000010832_5545984.pth...
+-[2023-09-19 11:44:07,053][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000010792_5525504.pth...
+-[2023-09-19 11:44:07,059][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000010680_5468160.pth
+-[2023-09-19 11:44:07,062][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000010640_5447680.pth
+-[2023-09-19 11:44:12,043][72530] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5637.2). Total num frames: 11104256. Throughput: 0: 2748.8, 1: 2748.7. Samples: 8664854. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0)
+-[2023-09-19 11:44:12,044][72530] Avg episode reward: [(0, '89650.521'), (1, '155598.656')]
+-[2023-09-19 11:44:14,562][73219] Updated weights for policy 1, policy_version 10840 (0.0014)
+-[2023-09-19 11:44:14,562][73145] Updated weights for policy 0, policy_version 10880 (0.0013)
+-[2023-09-19 11:44:17,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5637.2). Total num frames: 11128832. Throughput: 0: 2724.0, 1: 2723.6. Samples: 8698854. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0)
+-[2023-09-19 11:44:17,044][72530] Avg episode reward: [(0, '87254.510'), (1, '160076.645')]
+-[2023-09-19 11:44:22,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5637.2). Total num frames: 11161600. Throughput: 0: 2733.2, 1: 2733.3. Samples: 8716288. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0)
+-[2023-09-19 11:44:22,044][72530] Avg episode reward: [(0, '85923.521'), (1, '161617.846')]
+-[2023-09-19 11:44:22,053][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000010880_5570560.pth...
+-[2023-09-19 11:44:22,054][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000010920_5591040.pth...
+-[2023-09-19 11:44:22,060][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000010712_5484544.pth
+-[2023-09-19 11:44:22,060][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000010752_5505024.pth
+-[2023-09-19 11:44:27,043][72530] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5637.2). Total num frames: 11186176. Throughput: 0: 2701.6, 1: 2700.4. Samples: 8746388. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:44:27,044][72530] Avg episode reward: [(0, '86413.887'), (1, '161983.883')]
+-[2023-09-19 11:44:29,421][73219] Updated weights for policy 1, policy_version 10920 (0.0014)
+-[2023-09-19 11:44:29,422][73145] Updated weights for policy 0, policy_version 10960 (0.0016)
+-[2023-09-19 11:44:32,043][72530] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5609.4). Total num frames: 11210752. Throughput: 0: 2730.4, 1: 2729.5. Samples: 8780682. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:44:32,044][72530] Avg episode reward: [(0, '88162.418'), (1, '162739.322')]
+-[2023-09-19 11:44:37,044][72530] Fps is (10 sec: 5734.2, 60 sec: 5461.3, 300 sec: 5637.2). Total num frames: 11243520. Throughput: 0: 2743.6, 1: 2743.8. Samples: 8798112. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
+-[2023-09-19 11:44:37,045][72530] Avg episode reward: [(0, '89655.979'), (1, '162764.902')]
+-[2023-09-19 11:44:37,054][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000010960_5611520.pth...
+-[2023-09-19 11:44:37,054][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000011000_5632000.pth...
+-[2023-09-19 11:44:37,061][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000010792_5525504.pth
+-[2023-09-19 11:44:37,064][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000010832_5545984.pth
+-[2023-09-19 11:44:42,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5637.2). Total num frames: 11268096. Throughput: 0: 2814.7, 1: 2814.5. Samples: 8833096. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
+-[2023-09-19 11:44:42,044][72530] Avg episode reward: [(0, '90951.227'), (1, '163562.679')]
+-[2023-09-19 11:44:42,045][73131] Saving new best policy, reward=163562.679!
+-[2023-09-19 11:44:43,549][73145] Updated weights for policy 0, policy_version 11040 (0.0014)
+-[2023-09-19 11:44:43,549][73219] Updated weights for policy 1, policy_version 11000 (0.0012)
+-[2023-09-19 11:44:47,043][72530] Fps is (10 sec: 5734.6, 60 sec: 5597.9, 300 sec: 5665.0). Total num frames: 11300864. Throughput: 0: 2823.4, 1: 2823.2. Samples: 8868152. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0)
+-[2023-09-19 11:44:47,044][72530] Avg episode reward: [(0, '90951.227'), (1, '163569.234')]
+-[2023-09-19 11:44:47,045][73131] Saving new best policy, reward=163569.234!
+-[2023-09-19 11:44:52,043][72530] Fps is (10 sec: 6553.4, 60 sec: 5734.4, 300 sec: 5665.0). Total num frames: 11333632. Throughput: 0: 2853.3, 1: 2853.4. Samples: 8885846. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0)
+-[2023-09-19 11:44:52,044][72530] Avg episode reward: [(0, '93196.735'), (1, '163602.622')]
+-[2023-09-19 11:44:52,055][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000011048_5656576.pth...
+-[2023-09-19 11:44:52,055][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000011088_5677056.pth...
+-[2023-09-19 11:44:52,062][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000010920_5591040.pth
+-[2023-09-19 11:44:52,064][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000010880_5570560.pth
+-[2023-09-19 11:44:52,064][73131] Saving new best policy, reward=163602.622!
+-[2023-09-19 11:44:57,043][72530] Fps is (10 sec: 5734.3, 60 sec: 5734.4, 300 sec: 5665.0). Total num frames: 11358208. Throughput: 0: 2817.7, 1: 2817.8. Samples: 8918454. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:44:57,045][72530] Avg episode reward: [(0, '93196.735'), (1, '163602.622')]
+-[2023-09-19 11:44:58,430][73145] Updated weights for policy 0, policy_version 11120 (0.0014)
+-[2023-09-19 11:44:58,430][73219] Updated weights for policy 1, policy_version 11080 (0.0010)
+-[2023-09-19 11:45:02,043][72530] Fps is (10 sec: 4915.3, 60 sec: 5597.9, 300 sec: 5637.2). Total num frames: 11382784. Throughput: 0: 2747.1, 1: 2747.7. Samples: 8946120. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:45:02,044][72530] Avg episode reward: [(0, '96123.404'), (1, '163617.376')]
+-[2023-09-19 11:45:02,046][73131] Saving new best policy, reward=163617.376!
+-[2023-09-19 11:45:07,043][72530] Fps is (10 sec: 4915.1, 60 sec: 5597.9, 300 sec: 5637.2). Total num frames: 11407360. Throughput: 0: 2726.9, 1: 2726.6. Samples: 8961696. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
+-[2023-09-19 11:45:07,044][72530] Avg episode reward: [(0, '97205.408'), (1, '163596.670')]
+-[2023-09-19 11:45:07,054][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000011160_5713920.pth...
+-[2023-09-19 11:45:07,054][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000011120_5693440.pth...
+-[2023-09-19 11:45:07,061][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000011000_5632000.pth
+-[2023-09-19 11:45:07,061][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000010960_5611520.pth
+-[2023-09-19 11:45:12,043][72530] Fps is (10 sec: 4915.3, 60 sec: 5461.4, 300 sec: 5609.4). Total num frames: 11431936. Throughput: 0: 2703.2, 1: 2703.2. Samples: 8989676. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
+-[2023-09-19 11:45:12,043][72530] Avg episode reward: [(0, '97205.408'), (1, '163596.670')]
+-[2023-09-19 11:45:15,308][73145] Updated weights for policy 0, policy_version 11200 (0.0014)
+-[2023-09-19 11:45:15,308][73219] Updated weights for policy 1, policy_version 11160 (0.0012)
+-[2023-09-19 11:45:17,043][72530] Fps is (10 sec: 4096.1, 60 sec: 5324.8, 300 sec: 5581.7). Total num frames: 11448320. Throughput: 0: 2651.6, 1: 2652.6. Samples: 9019372. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0)
+-[2023-09-19 11:45:17,044][72530] Avg episode reward: [(0, '102260.462'), (1, '163634.922')]
+-[2023-09-19 11:45:17,045][73131] Saving new best policy, reward=163634.922!
+-[2023-09-19 11:45:22,043][72530] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5609.4). Total num frames: 11481088. Throughput: 0: 2640.3, 1: 2641.3. Samples: 9035780. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0)
+-[2023-09-19 11:45:22,044][72530] Avg episode reward: [(0, '105256.610'), (1, '163636.135')]
+-[2023-09-19 11:45:22,053][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000011192_5730304.pth...
+-[2023-09-19 11:45:22,054][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000011232_5750784.pth...
+-[2023-09-19 11:45:22,063][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000011088_5677056.pth
+-[2023-09-19 11:45:22,063][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000011048_5656576.pth
+-[2023-09-19 11:45:22,064][73131] Saving new best policy, reward=163636.135!
+-[2023-09-19 11:45:27,043][72530] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5581.7). Total num frames: 11505664. Throughput: 0: 2614.9, 1: 2616.2. Samples: 9068494. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:45:27,044][72530] Avg episode reward: [(0, '106969.066'), (1, '163623.728')]
+-[2023-09-19 11:45:30,281][73145] Updated weights for policy 0, policy_version 11280 (0.0010)
+-[2023-09-19 11:45:30,281][73219] Updated weights for policy 1, policy_version 11240 (0.0014)
+-[2023-09-19 11:45:32,043][72530] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5609.4). Total num frames: 11538432. Throughput: 0: 2590.7, 1: 2592.2. Samples: 9101380. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:45:32,044][72530] Avg episode reward: [(0, '107549.962'), (1, '163617.201')]
+-[2023-09-19 11:45:37,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5609.4). Total num frames: 11563008. Throughput: 0: 2590.5, 1: 2590.6. Samples: 9118994. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:45:37,044][72530] Avg episode reward: [(0, '105811.432'), (1, '163639.722')]
+-[2023-09-19 11:45:37,053][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000011272_5771264.pth...
+-[2023-09-19 11:45:37,053][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000011312_5791744.pth...
+-[2023-09-19 11:45:37,060][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000011120_5693440.pth
+-[2023-09-19 11:45:37,060][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000011160_5713920.pth
+-[2023-09-19 11:45:37,061][73131] Saving new best policy, reward=163639.722!
+-[2023-09-19 11:45:42,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5609.4). Total num frames: 11595776. Throughput: 0: 2606.7, 1: 2606.6. Samples: 9153050. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:45:42,044][72530] Avg episode reward: [(0, '107882.450'), (1, '163839.533')]
+-[2023-09-19 11:45:42,044][73131] Saving new best policy, reward=163839.533!
+-[2023-09-19 11:45:44,762][73219] Updated weights for policy 1, policy_version 11320 (0.0013)
+-[2023-09-19 11:45:44,763][73145] Updated weights for policy 0, policy_version 11360 (0.0014)
+-[2023-09-19 11:45:47,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5581.7). Total num frames: 11620352. Throughput: 0: 2698.0, 1: 2697.3. Samples: 9188910. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:45:47,044][72530] Avg episode reward: [(0, '107882.450'), (1, '163858.005')]
+-[2023-09-19 11:45:47,046][73131] Saving new best policy, reward=163858.005!
+-[2023-09-19 11:45:52,043][72530] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5609.4). Total num frames: 11653120. Throughput: 0: 2722.0, 1: 2721.0. Samples: 9206630. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:45:52,044][72530] Avg episode reward: [(0, '105400.770'), (1, '163575.436')]
+-[2023-09-19 11:45:52,054][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000011360_5816320.pth...
+-[2023-09-19 11:45:52,054][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000011400_5836800.pth...
+-[2023-09-19 11:45:52,062][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000011192_5730304.pth
+-[2023-09-19 11:45:52,063][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000011232_5750784.pth
+-[2023-09-19 11:45:57,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5581.7). Total num frames: 11677696. Throughput: 0: 2764.1, 1: 2764.3. Samples: 9238454. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:45:57,044][72530] Avg episode reward: [(0, '105400.770'), (1, '163575.436')]
+-[2023-09-19 11:45:59,327][73219] Updated weights for policy 1, policy_version 11400 (0.0016)
+-[2023-09-19 11:45:59,327][73145] Updated weights for policy 0, policy_version 11440 (0.0016)
+-[2023-09-19 11:46:02,043][72530] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5581.7). Total num frames: 11702272. Throughput: 0: 2625.6, 1: 2624.6. Samples: 9255630. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0)
+-[2023-09-19 11:46:02,044][72530] Avg episode reward: [(0, '104718.135'), (1, '163329.699')]
+-[2023-09-19 11:46:07,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5581.7). Total num frames: 11735040. Throughput: 0: 2830.1, 1: 2829.0. Samples: 9290438. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0)
+-[2023-09-19 11:46:07,044][72530] Avg episode reward: [(0, '104541.048'), (1, '163378.382')]
+-[2023-09-19 11:46:07,052][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000011440_5857280.pth...
+-[2023-09-19 11:46:07,052][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000011480_5877760.pth...
+-[2023-09-19 11:46:07,061][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000011272_5771264.pth
+-[2023-09-19 11:46:07,061][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000011312_5791744.pth
+-[2023-09-19 11:46:12,043][72530] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5553.9). Total num frames: 11759616. Throughput: 0: 2839.9, 1: 2838.8. Samples: 9324034. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0)
+-[2023-09-19 11:46:12,044][72530] Avg episode reward: [(0, '106063.260'), (1, '163399.235')]
+-[2023-09-19 11:46:13,614][73219] Updated weights for policy 1, policy_version 11480 (0.0013)
+-[2023-09-19 11:46:13,614][73145] Updated weights for policy 0, policy_version 11520 (0.0014)
+-[2023-09-19 11:46:17,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5734.4, 300 sec: 5553.9). Total num frames: 11792384. Throughput: 0: 2832.0, 1: 2830.7. Samples: 9356202. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0)
+-[2023-09-19 11:46:17,044][72530] Avg episode reward: [(0, '105598.661'), (1, '162236.464')]
+-[2023-09-19 11:46:22,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5553.9). Total num frames: 11816960. Throughput: 0: 2812.6, 1: 2812.9. Samples: 9372142. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0)
+-[2023-09-19 11:46:22,044][72530] Avg episode reward: [(0, '105598.661'), (1, '158593.843')]
+-[2023-09-19 11:46:22,056][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000011520_5898240.pth...
+-[2023-09-19 11:46:22,056][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000011560_5918720.pth...
+-[2023-09-19 11:46:22,065][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000011360_5816320.pth
+-[2023-09-19 11:46:22,066][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000011400_5836800.pth
+-[2023-09-19 11:46:27,043][72530] Fps is (10 sec: 4915.2, 60 sec: 5597.9, 300 sec: 5553.9). Total num frames: 11841536. Throughput: 0: 2754.3, 1: 2754.3. Samples: 9400936. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0)
+-[2023-09-19 11:46:27,044][72530] Avg episode reward: [(0, '104505.657'), (1, '155073.280')]
+-[2023-09-19 11:46:30,228][73145] Updated weights for policy 0, policy_version 11600 (0.0013)
+-[2023-09-19 11:46:30,228][73219] Updated weights for policy 1, policy_version 11560 (0.0013)
+-[2023-09-19 11:46:32,043][72530] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5526.1). Total num frames: 11866112. Throughput: 0: 2687.7, 1: 2687.8. Samples: 9430808. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0)
+-[2023-09-19 11:46:32,044][72530] Avg episode reward: [(0, '105201.453'), (1, '155073.280')]
+-[2023-09-19 11:46:37,043][72530] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5526.1). Total num frames: 11890688. Throughput: 0: 2652.0, 1: 2653.2. Samples: 9445364. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0)
+-[2023-09-19 11:46:37,044][72530] Avg episode reward: [(0, '106467.037'), (1, '155392.306')]
+-[2023-09-19 11:46:37,053][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000011592_5935104.pth...
+-[2023-09-19 11:46:37,053][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000011632_5955584.pth...
+-[2023-09-19 11:46:37,061][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000011440_5857280.pth
+-[2023-09-19 11:46:37,062][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000011480_5877760.pth
+-[2023-09-19 11:46:42,043][72530] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5498.4). Total num frames: 11915264. Throughput: 0: 2662.8, 1: 2663.7. Samples: 9478146. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:46:42,044][72530] Avg episode reward: [(0, '108179.215'), (1, '155385.005')]
+-[2023-09-19 11:46:45,489][73145] Updated weights for policy 0, policy_version 11680 (0.0014)
+-[2023-09-19 11:46:45,490][73219] Updated weights for policy 1, policy_version 11640 (0.0014)
+-[2023-09-19 11:46:47,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5526.1). Total num frames: 11948032. Throughput: 0: 2837.7, 1: 2837.9. Samples: 9511032. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:46:47,044][72530] Avg episode reward: [(0, '108179.215'), (1, '155360.629')]
+-[2023-09-19 11:46:52,043][72530] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5498.4). Total num frames: 11972608. Throughput: 0: 2646.1, 1: 2645.9. Samples: 9528578. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:46:52,044][72530] Avg episode reward: [(0, '110744.067'), (1, '155267.645')]
+-[2023-09-19 11:46:52,055][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000011712_5996544.pth...
+-[2023-09-19 11:46:52,055][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000011672_5976064.pth...
+-[2023-09-19 11:46:52,061][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000011560_5918720.pth
+-[2023-09-19 11:46:52,064][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000011520_5898240.pth
+-[2023-09-19 11:46:57,043][72530] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5498.4). Total num frames: 11997184. Throughput: 0: 2648.3, 1: 2648.4. Samples: 9562384. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:46:57,044][72530] Avg episode reward: [(0, '110744.067'), (1, '155267.645')]
+-[2023-09-19 11:46:59,831][73145] Updated weights for policy 0, policy_version 11760 (0.0013)
+-[2023-09-19 11:46:59,832][73219] Updated weights for policy 1, policy_version 11720 (0.0013)
+-[2023-09-19 11:47:02,043][72530] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5526.1). Total num frames: 12029952. Throughput: 0: 2681.6, 1: 2681.6. Samples: 9597548. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0)
+-[2023-09-19 11:47:02,044][72530] Avg episode reward: [(0, '113492.232'), (1, '163938.746')]
+-[2023-09-19 11:47:02,046][73131] Saving new best policy, reward=163938.746!
+-[2023-09-19 11:47:07,043][72530] Fps is (10 sec: 6553.5, 60 sec: 5461.3, 300 sec: 5526.1). Total num frames: 12062720. Throughput: 0: 2695.1, 1: 2694.9. Samples: 9614692. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0)
+-[2023-09-19 11:47:07,044][72530] Avg episode reward: [(0, '114645.759'), (1, '163938.746')]
+-[2023-09-19 11:47:07,055][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000011760_6021120.pth...
+-[2023-09-19 11:47:07,055][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000011800_6041600.pth...
+-[2023-09-19 11:47:07,061][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000011592_5935104.pth
+-[2023-09-19 11:47:07,064][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000011632_5955584.pth
+-[2023-09-19 11:47:12,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5526.1). Total num frames: 12087296. Throughput: 0: 2755.8, 1: 2755.8. Samples: 9648956. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
+-[2023-09-19 11:47:12,044][72530] Avg episode reward: [(0, '117620.147'), (1, '164058.186')]
+-[2023-09-19 11:47:12,046][73131] Saving new best policy, reward=164058.186!
+-[2023-09-19 11:47:15,016][73145] Updated weights for policy 0, policy_version 11840 (0.0014)
+-[2023-09-19 11:47:15,017][73219] Updated weights for policy 1, policy_version 11800 (0.0013)
+-[2023-09-19 11:47:17,043][72530] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5498.4). Total num frames: 12111872. Throughput: 0: 2736.9, 1: 2737.0. Samples: 9677132. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
+-[2023-09-19 11:47:17,044][72530] Avg episode reward: [(0, '120342.444'), (1, '164061.858')]
+-[2023-09-19 11:47:17,045][73131] Saving new best policy, reward=164061.858!
+-[2023-09-19 11:47:22,043][72530] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5498.4). Total num frames: 12136448. Throughput: 0: 2756.4, 1: 2755.3. Samples: 9693392. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:47:22,045][72530] Avg episode reward: [(0, '121613.231'), (1, '164054.108')]
+-[2023-09-19 11:47:22,055][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000011832_6057984.pth...
+-[2023-09-19 11:47:22,055][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000011872_6078464.pth...
+-[2023-09-19 11:47:22,063][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000011672_5976064.pth
+-[2023-09-19 11:47:22,064][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000011712_5996544.pth
+-[2023-09-19 11:47:27,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5498.4). Total num frames: 12169216. Throughput: 0: 2794.7, 1: 2793.4. Samples: 9729608. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:47:27,044][72530] Avg episode reward: [(0, '120341.617'), (1, '164136.092')]
+-[2023-09-19 11:47:27,045][73131] Saving new best policy, reward=164136.092!
+-[2023-09-19 11:47:29,294][73145] Updated weights for policy 0, policy_version 11920 (0.0016)
+-[2023-09-19 11:47:29,294][73219] Updated weights for policy 1, policy_version 11880 (0.0016)
+-[2023-09-19 11:47:32,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5498.4). Total num frames: 12193792. Throughput: 0: 2811.6, 1: 2812.1. Samples: 9764102. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
+-[2023-09-19 11:47:32,044][72530] Avg episode reward: [(0, '120341.617'), (1, '163669.701')]
+-[2023-09-19 11:47:37,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5498.4). Total num frames: 12226560. Throughput: 0: 2781.4, 1: 2781.4. Samples: 9778906. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
+-[2023-09-19 11:47:37,044][72530] Avg episode reward: [(0, '118487.302'), (1, '163451.635')]
+-[2023-09-19 11:47:37,052][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000011920_6103040.pth...
+-[2023-09-19 11:47:37,052][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000011960_6123520.pth...
+-[2023-09-19 11:47:37,059][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000011800_6041600.pth
+-[2023-09-19 11:47:37,059][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000011760_6021120.pth
+-[2023-09-19 11:47:42,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5498.4). Total num frames: 12251136. Throughput: 0: 2801.6, 1: 2801.3. Samples: 9814516. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0)
+-[2023-09-19 11:47:42,044][72530] Avg episode reward: [(0, '119270.006'), (1, '163451.635')]
+-[2023-09-19 11:47:43,762][73145] Updated weights for policy 0, policy_version 12000 (0.0016)
+-[2023-09-19 11:47:43,762][73219] Updated weights for policy 1, policy_version 11960 (0.0015)
+-[2023-09-19 11:47:47,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5498.4). Total num frames: 12283904. Throughput: 0: 2806.5, 1: 2806.4. Samples: 9850126. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0)
+-[2023-09-19 11:47:47,044][72530] Avg episode reward: [(0, '118016.428'), (1, '163248.371')]
+-[2023-09-19 11:47:52,043][72530] Fps is (10 sec: 5734.5, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 12308480. Throughput: 0: 2818.1, 1: 2818.1. Samples: 9868322. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0)
+-[2023-09-19 11:47:52,044][72530] Avg episode reward: [(0, '115308.107'), (1, '163245.962')]
+-[2023-09-19 11:47:52,054][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000012040_6164480.pth...
+-[2023-09-19 11:47:52,054][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000012000_6144000.pth...
+-[2023-09-19 11:47:52,064][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000011872_6078464.pth
+-[2023-09-19 11:47:52,065][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000011832_6057984.pth
+-[2023-09-19 11:47:57,043][72530] Fps is (10 sec: 5734.3, 60 sec: 5734.4, 300 sec: 5498.4). Total num frames: 12341248. Throughput: 0: 2811.7, 1: 2811.7. Samples: 9902008. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0)
+-[2023-09-19 11:47:57,044][72530] Avg episode reward: [(0, '115899.171'), (1, '163286.602')]
+-[2023-09-19 11:47:57,983][73219] Updated weights for policy 1, policy_version 12040 (0.0014)
+-[2023-09-19 11:47:57,985][73145] Updated weights for policy 0, policy_version 12080 (0.0016)
+-[2023-09-19 11:48:02,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5498.4). Total num frames: 12365824. Throughput: 0: 2849.0, 1: 2849.1. Samples: 9933548. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
+-[2023-09-19 11:48:02,044][72530] Avg episode reward: [(0, '117424.425'), (1, '163330.945')]
+-[2023-09-19 11:48:07,043][72530] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 12390400. Throughput: 0: 2815.6, 1: 2815.7. Samples: 9946798. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
+-[2023-09-19 11:48:07,044][72530] Avg episode reward: [(0, '117424.425'), (1, '163807.050')]
+-[2023-09-19 11:48:07,052][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000012080_6184960.pth...
+-[2023-09-19 11:48:07,052][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000012120_6205440.pth...
+-[2023-09-19 11:48:07,059][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000011920_6103040.pth
+-[2023-09-19 11:48:07,060][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000011960_6123520.pth
+-[2023-09-19 11:48:12,043][72530] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 12414976. Throughput: 0: 2772.0, 1: 2772.1. Samples: 9979096. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0)
+-[2023-09-19 11:48:12,044][72530] Avg episode reward: [(0, '116643.698'), (1, '164043.715')]
+-[2023-09-19 11:48:13,637][73145] Updated weights for policy 0, policy_version 12160 (0.0014)
+-[2023-09-19 11:48:13,637][73219] Updated weights for policy 1, policy_version 12120 (0.0013)
+-[2023-09-19 11:48:17,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 12447744. Throughput: 0: 2761.6, 1: 2761.6. Samples: 10012644. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0)
+-[2023-09-19 11:48:17,044][72530] Avg episode reward: [(0, '116643.698'), (1, '164043.715')]
+-[2023-09-19 11:48:22,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 12472320. Throughput: 0: 2792.3, 1: 2792.3. Samples: 10030210. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:48:22,044][72530] Avg episode reward: [(0, '114977.442'), (1, '164100.748')]
+-[2023-09-19 11:48:22,052][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000012200_6246400.pth...
+-[2023-09-19 11:48:22,052][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000012160_6225920.pth...
+-[2023-09-19 11:48:22,059][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000012040_6164480.pth
+-[2023-09-19 11:48:22,061][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000012000_6144000.pth
+-[2023-09-19 11:48:27,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5498.4). Total num frames: 12505088. Throughput: 0: 2773.0, 1: 2773.1. Samples: 10064090. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:48:27,044][72530] Avg episode reward: [(0, '115199.567'), (1, '164068.846')]
+-[2023-09-19 11:48:28,286][73219] Updated weights for policy 1, policy_version 12200 (0.0013)
+-[2023-09-19 11:48:28,286][73145] Updated weights for policy 0, policy_version 12240 (0.0012)
+-[2023-09-19 11:48:32,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 12529664. Throughput: 0: 2711.3, 1: 2711.5. Samples: 10094152. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:48:32,044][72530] Avg episode reward: [(0, '111865.477'), (1, '163548.142')]
+-[2023-09-19 11:48:37,043][72530] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 12554240. Throughput: 0: 2682.5, 1: 2682.3. Samples: 10109738. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:48:37,044][72530] Avg episode reward: [(0, '107535.334'), (1, '163429.327')]
+-[2023-09-19 11:48:37,054][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000012240_6266880.pth...
+-[2023-09-19 11:48:37,054][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000012280_6287360.pth...
+-[2023-09-19 11:48:37,062][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000012080_6184960.pth
+-[2023-09-19 11:48:37,064][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000012120_6205440.pth
+-[2023-09-19 11:48:42,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5498.4). Total num frames: 12587008. Throughput: 0: 2703.6, 1: 2703.6. Samples: 10145332. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:48:42,044][72530] Avg episode reward: [(0, '107535.334'), (1, '162298.894')]
+-[2023-09-19 11:48:43,731][73145] Updated weights for policy 0, policy_version 12320 (0.0014)
+-[2023-09-19 11:48:43,732][73219] Updated weights for policy 1, policy_version 12280 (0.0012)
+-[2023-09-19 11:48:47,043][72530] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5498.4). Total num frames: 12611584. Throughput: 0: 2702.4, 1: 2702.2. Samples: 10176756. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:48:47,044][72530] Avg episode reward: [(0, '106316.522'), (1, '161408.497')]
+-[2023-09-19 11:48:52,043][72530] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5498.4). Total num frames: 12636160. Throughput: 0: 2750.1, 1: 2749.8. Samples: 10194294. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:48:52,044][72530] Avg episode reward: [(0, '106316.522'), (1, '161408.497')]
+-[2023-09-19 11:48:52,052][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000012320_6307840.pth...
+-[2023-09-19 11:48:52,052][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000012360_6328320.pth...
+-[2023-09-19 11:48:52,058][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000012160_6225920.pth
+-[2023-09-19 11:48:52,059][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000012200_6246400.pth
+-[2023-09-19 11:48:57,043][72530] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5470.6). Total num frames: 12660736. Throughput: 0: 2734.8, 1: 2734.8. Samples: 10225232. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:48:57,045][72530] Avg episode reward: [(0, '104226.634'), (1, '160377.599')]
+-[2023-09-19 11:48:58,673][73145] Updated weights for policy 0, policy_version 12400 (0.0012)
+-[2023-09-19 11:48:58,673][73219] Updated weights for policy 1, policy_version 12360 (0.0015)
+-[2023-09-19 11:49:02,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5498.4). Total num frames: 12693504. Throughput: 0: 2747.6, 1: 2746.8. Samples: 10259896. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:49:02,045][72530] Avg episode reward: [(0, '104136.332'), (1, '159195.252')]
+-[2023-09-19 11:49:07,043][72530] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 12718080. Throughput: 0: 2694.6, 1: 2695.7. Samples: 10272774. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:49:07,045][72530] Avg episode reward: [(0, '106355.574'), (1, '159230.111')]
+-[2023-09-19 11:49:07,055][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000012440_6369280.pth...
+-[2023-09-19 11:49:07,055][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000012400_6348800.pth...
+-[2023-09-19 11:49:07,062][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000012280_6287360.pth
+-[2023-09-19 11:49:07,062][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000012240_6266880.pth
+-[2023-09-19 11:49:12,043][72530] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 12742656. Throughput: 0: 2680.0, 1: 2680.4. Samples: 10305312. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:49:12,045][72530] Avg episode reward: [(0, '110372.318'), (1, '159771.618')]
+-[2023-09-19 11:49:14,377][73145] Updated weights for policy 0, policy_version 12480 (0.0012)
+-[2023-09-19 11:49:14,378][73219] Updated weights for policy 1, policy_version 12440 (0.0012)
+-[2023-09-19 11:49:17,043][72530] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 12767232. Throughput: 0: 2711.7, 1: 2712.5. Samples: 10338240. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:49:17,044][72530] Avg episode reward: [(0, '110372.318'), (1, '159771.618')]
+-[2023-09-19 11:49:22,043][72530] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 12800000. Throughput: 0: 2729.1, 1: 2729.3. Samples: 10355370. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:49:22,045][72530] Avg episode reward: [(0, '110181.871'), (1, '160985.288')]
+-[2023-09-19 11:49:22,055][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000012520_6410240.pth...
+-[2023-09-19 11:49:22,055][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000012480_6389760.pth...
+-[2023-09-19 11:49:22,066][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000012320_6307840.pth
+-[2023-09-19 11:49:22,066][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000012360_6328320.pth
+-[2023-09-19 11:49:27,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5470.6). Total num frames: 12824576. Throughput: 0: 2671.7, 1: 2671.6. Samples: 10385784. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:49:27,044][72530] Avg episode reward: [(0, '110198.661'), (1, '160985.288')]
+-[2023-09-19 11:49:29,030][73145] Updated weights for policy 0, policy_version 12560 (0.0012)
+-[2023-09-19 11:49:29,031][73219] Updated weights for policy 1, policy_version 12520 (0.0011)
+-[2023-09-19 11:49:32,043][72530] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 12857344. Throughput: 0: 2719.7, 1: 2720.0. Samples: 10421540. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:49:32,044][72530] Avg episode reward: [(0, '111544.611'), (1, '162823.390')]
+-[2023-09-19 11:49:37,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 12881920. Throughput: 0: 2719.0, 1: 2719.2. Samples: 10439012. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:49:37,044][72530] Avg episode reward: [(0, '112652.375'), (1, '162884.861')]
+-[2023-09-19 11:49:37,054][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000012600_6451200.pth...
+-[2023-09-19 11:49:37,054][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000012560_6430720.pth...
+-[2023-09-19 11:49:37,058][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000012440_6369280.pth
+-[2023-09-19 11:49:37,062][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000012400_6348800.pth
+-[2023-09-19 11:49:42,043][72530] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 12906496. Throughput: 0: 2710.0, 1: 2711.1. Samples: 10469180. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0)
+-[2023-09-19 11:49:42,045][72530] Avg episode reward: [(0, '112673.657'), (1, '163872.242')]
+-[2023-09-19 11:49:44,447][73219] Updated weights for policy 1, policy_version 12600 (0.0014)
+-[2023-09-19 11:49:44,448][73145] Updated weights for policy 0, policy_version 12640 (0.0013)
+-[2023-09-19 11:49:47,043][72530] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 12931072. Throughput: 0: 2683.4, 1: 2683.4. Samples: 10501404. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0)
+-[2023-09-19 11:49:47,044][72530] Avg episode reward: [(0, '113377.242'), (1, '163154.750')]
+-[2023-09-19 11:49:52,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 12963840. Throughput: 0: 2727.1, 1: 2727.0. Samples: 10518208. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0)
+-[2023-09-19 11:49:52,045][72530] Avg episode reward: [(0, '113377.242'), (1, '163154.750')]
+-[2023-09-19 11:49:52,053][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000012680_6492160.pth...
+-[2023-09-19 11:49:52,054][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000012640_6471680.pth...
+-[2023-09-19 11:49:52,058][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000012520_6410240.pth
+-[2023-09-19 11:49:52,061][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000012480_6389760.pth
+-[2023-09-19 11:49:57,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 12988416. Throughput: 0: 2708.9, 1: 2708.4. Samples: 10549088. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0)
+-[2023-09-19 11:49:57,044][72530] Avg episode reward: [(0, '113159.962'), (1, '161958.914')]
+-[2023-09-19 11:49:59,407][73219] Updated weights for policy 1, policy_version 12680 (0.0015)
+-[2023-09-19 11:49:59,407][73145] Updated weights for policy 0, policy_version 12720 (0.0014)
+-[2023-09-19 11:50:02,043][72530] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 13012992. Throughput: 0: 2709.9, 1: 2709.0. Samples: 10582090. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0)
+-[2023-09-19 11:50:02,044][72530] Avg episode reward: [(0, '113659.562'), (1, '161957.798')]
+-[2023-09-19 11:50:07,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 13045760. Throughput: 0: 2706.5, 1: 2706.4. Samples: 10598952. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:50:07,044][72530] Avg episode reward: [(0, '114392.887'), (1, '161274.669')]
+-[2023-09-19 11:50:07,054][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000012720_6512640.pth...
+-[2023-09-19 11:50:07,055][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000012760_6533120.pth...
+-[2023-09-19 11:50:07,061][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000012560_6430720.pth
+-[2023-09-19 11:50:07,061][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000012600_6451200.pth
+-[2023-09-19 11:50:12,043][72530] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5470.6). Total num frames: 13062144. Throughput: 0: 2697.0, 1: 2697.2. Samples: 10628524. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:50:12,044][72530] Avg episode reward: [(0, '113293.487'), (1, '160635.441')]
+-[2023-09-19 11:50:15,160][73145] Updated weights for policy 0, policy_version 12800 (0.0014)
+-[2023-09-19 11:50:15,160][73219] Updated weights for policy 1, policy_version 12760 (0.0016)
+-[2023-09-19 11:50:17,043][72530] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 13094912. Throughput: 0: 2646.0, 1: 2645.9. Samples: 10659676. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0)
+-[2023-09-19 11:50:17,044][72530] Avg episode reward: [(0, '113293.487'), (1, '160786.247')]
+-[2023-09-19 11:50:22,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5470.6). Total num frames: 13119488. Throughput: 0: 2645.4, 1: 2645.3. Samples: 10677092. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0)
+-[2023-09-19 11:50:22,044][72530] Avg episode reward: [(0, '113047.949'), (1, '161538.199')]
+-[2023-09-19 11:50:22,054][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000012792_6549504.pth...
+-[2023-09-19 11:50:22,054][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000012832_6569984.pth...
+-[2023-09-19 11:50:22,062][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000012640_6471680.pth
+-[2023-09-19 11:50:22,063][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000012680_6492160.pth
+-[2023-09-19 11:50:27,043][72530] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 13144064. Throughput: 0: 2674.3, 1: 2673.4. Samples: 10709824. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:50:27,044][72530] Avg episode reward: [(0, '113325.734'), (1, '161538.199')]
+-[2023-09-19 11:50:30,173][73219] Updated weights for policy 1, policy_version 12840 (0.0011)
+-[2023-09-19 11:50:30,174][73145] Updated weights for policy 0, policy_version 12880 (0.0019)
+-[2023-09-19 11:50:32,043][72530] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5470.6). Total num frames: 13176832. Throughput: 0: 2678.6, 1: 2678.5. Samples: 10742474. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:50:32,045][72530] Avg episode reward: [(0, '110953.125'), (1, '162797.965')]
+-[2023-09-19 11:50:37,043][72530] Fps is (10 sec: 5734.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 13201408. Throughput: 0: 2676.9, 1: 2675.9. Samples: 10759082. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
+-[2023-09-19 11:50:37,044][72530] Avg episode reward: [(0, '111513.061'), (1, '162852.658')]
+-[2023-09-19 11:50:37,056][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000012872_6590464.pth...
+-[2023-09-19 11:50:37,056][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000012912_6610944.pth...
+-[2023-09-19 11:50:37,061][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000012760_6533120.pth
+-[2023-09-19 11:50:37,065][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000012720_6512640.pth
+-[2023-09-19 11:50:42,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 13234176. Throughput: 0: 2723.3, 1: 2723.3. Samples: 10794184. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
+-[2023-09-19 11:50:42,044][72530] Avg episode reward: [(0, '113571.621'), (1, '162934.778')]
+-[2023-09-19 11:50:44,663][73145] Updated weights for policy 0, policy_version 12960 (0.0011)
+-[2023-09-19 11:50:44,664][73219] Updated weights for policy 1, policy_version 12920 (0.0014)
+-[2023-09-19 11:50:47,043][72530] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 13258752. Throughput: 0: 2728.1, 1: 2728.3. Samples: 10827630. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0)
+-[2023-09-19 11:50:47,044][72530] Avg episode reward: [(0, '113123.608'), (1, '163033.885')]
+-[2023-09-19 11:50:52,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 13291520. Throughput: 0: 2735.7, 1: 2735.9. Samples: 10845174. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0)
+-[2023-09-19 11:50:52,044][72530] Avg episode reward: [(0, '114036.709'), (1, '163233.390')]
+-[2023-09-19 11:50:52,053][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000012960_6635520.pth...
+-[2023-09-19 11:50:52,053][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000013000_6656000.pth...
+-[2023-09-19 11:50:52,060][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000012792_6549504.pth
+-[2023-09-19 11:50:52,063][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000012832_6569984.pth
+-[2023-09-19 11:50:57,043][72530] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 13316096. Throughput: 0: 2784.1, 1: 2784.4. Samples: 10879108. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:50:57,044][72530] Avg episode reward: [(0, '114403.782'), (1, '162804.648')]
+-[2023-09-19 11:50:58,834][73219] Updated weights for policy 1, policy_version 13000 (0.0013)
+-[2023-09-19 11:50:58,834][73145] Updated weights for policy 0, policy_version 13040 (0.0013)
+-[2023-09-19 11:51:02,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 13348864. Throughput: 0: 2823.3, 1: 2823.4. Samples: 10913776. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:51:02,045][72530] Avg episode reward: [(0, '114403.782'), (1, '162804.648')]
+-[2023-09-19 11:51:07,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 13373440. Throughput: 0: 2802.2, 1: 2802.3. Samples: 10929298. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:51:07,044][72530] Avg episode reward: [(0, '115552.472'), (1, '161727.982')]
+-[2023-09-19 11:51:07,056][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000013040_6676480.pth...
+-[2023-09-19 11:51:07,056][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000013080_6696960.pth...
+-[2023-09-19 11:51:07,062][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000012872_6590464.pth
+-[2023-09-19 11:51:07,062][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000012912_6610944.pth
+-[2023-09-19 11:51:12,043][72530] Fps is (10 sec: 4915.2, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 13398016. Throughput: 0: 2794.4, 1: 2794.4. Samples: 10961322. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:51:12,045][72530] Avg episode reward: [(0, '114818.267'), (1, '161727.982')]
+-[2023-09-19 11:51:14,001][73219] Updated weights for policy 1, policy_version 13080 (0.0013)
+-[2023-09-19 11:51:14,001][73145] Updated weights for policy 0, policy_version 13120 (0.0014)
+-[2023-09-19 11:51:17,043][72530] Fps is (10 sec: 5734.5, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 13430784. Throughput: 0: 2802.5, 1: 2802.7. Samples: 10994708. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:51:17,044][72530] Avg episode reward: [(0, '112267.470'), (1, '161652.380')]
+-[2023-09-19 11:51:22,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 13455360. Throughput: 0: 2816.0, 1: 2816.1. Samples: 11012526. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:51:22,044][72530] Avg episode reward: [(0, '113122.257'), (1, '162464.319')]
+-[2023-09-19 11:51:22,053][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000013120_6717440.pth...
+-[2023-09-19 11:51:22,053][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000013160_6737920.pth...
+-[2023-09-19 11:51:22,061][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000013000_6656000.pth
+-[2023-09-19 11:51:22,063][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000012960_6635520.pth
+-[2023-09-19 11:51:27,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5734.4, 300 sec: 5498.4). Total num frames: 13488128. Throughput: 0: 2804.3, 1: 2804.5. Samples: 11046580. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
+-[2023-09-19 11:51:27,044][72530] Avg episode reward: [(0, '114512.117'), (1, '162679.576')]
+-[2023-09-19 11:51:28,153][73145] Updated weights for policy 0, policy_version 13200 (0.0012)
+-[2023-09-19 11:51:28,154][73219] Updated weights for policy 1, policy_version 13160 (0.0017)
+-[2023-09-19 11:51:32,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5498.4). Total num frames: 13512704. Throughput: 0: 2817.9, 1: 2818.0. Samples: 11081242. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
+-[2023-09-19 11:51:32,044][72530] Avg episode reward: [(0, '115152.477'), (1, '162979.727')]
+-[2023-09-19 11:51:37,043][72530] Fps is (10 sec: 4915.2, 60 sec: 5597.9, 300 sec: 5498.4). Total num frames: 13537280. Throughput: 0: 2793.9, 1: 2793.8. Samples: 11096620. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0)
+-[2023-09-19 11:51:37,044][72530] Avg episode reward: [(0, '115152.477'), (1, '163119.801')]
+-[2023-09-19 11:51:37,050][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000013200_6758400.pth...
+-[2023-09-19 11:51:37,051][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000013240_6778880.pth...
+-[2023-09-19 11:51:37,055][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000013040_6676480.pth
+-[2023-09-19 11:51:37,060][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000013080_6696960.pth
+-[2023-09-19 11:51:42,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5498.4). Total num frames: 13570048. Throughput: 0: 2789.2, 1: 2788.7. Samples: 11130112. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0)
+-[2023-09-19 11:51:42,045][72530] Avg episode reward: [(0, '113913.820'), (1, '164168.870')]
+-[2023-09-19 11:51:42,046][73131] Saving new best policy, reward=164168.870!
+-[2023-09-19 11:51:43,105][73219] Updated weights for policy 1, policy_version 13240 (0.0012)
+-[2023-09-19 11:51:43,105][73145] Updated weights for policy 0, policy_version 13280 (0.0013)
+-[2023-09-19 11:51:47,043][72530] Fps is (10 sec: 5734.3, 60 sec: 5597.9, 300 sec: 5498.4). Total num frames: 13594624. Throughput: 0: 2792.0, 1: 2791.7. Samples: 11165042. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:51:47,045][72530] Avg episode reward: [(0, '113329.232'), (1, '164168.870')]
+-[2023-09-19 11:51:52,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5526.1). Total num frames: 13627392. Throughput: 0: 2810.2, 1: 2810.3. Samples: 11182220. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:51:52,044][72530] Avg episode reward: [(0, '115366.353'), (1, '164073.991')]
+-[2023-09-19 11:51:52,054][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000013288_6803456.pth...
+-[2023-09-19 11:51:52,054][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000013328_6823936.pth...
+-[2023-09-19 11:51:52,062][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000013160_6737920.pth
+-[2023-09-19 11:51:52,062][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000013120_6717440.pth
+-[2023-09-19 11:51:57,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5498.4). Total num frames: 13651968. Throughput: 0: 2834.8, 1: 2834.5. Samples: 11216442. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:51:57,044][72530] Avg episode reward: [(0, '112745.770'), (1, '164094.197')]
+-[2023-09-19 11:51:57,114][73145] Updated weights for policy 0, policy_version 13360 (0.0013)
+-[2023-09-19 11:51:57,114][73219] Updated weights for policy 1, policy_version 13320 (0.0014)
+-[2023-09-19 11:52:02,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5498.4). Total num frames: 13684736. Throughput: 0: 2842.9, 1: 2843.0. Samples: 11250572. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:52:02,044][72530] Avg episode reward: [(0, '112085.582'), (1, '164047.200')]
+-[2023-09-19 11:52:07,043][72530] Fps is (10 sec: 5734.3, 60 sec: 5597.9, 300 sec: 5498.4). Total num frames: 13709312. Throughput: 0: 2825.9, 1: 2825.9. Samples: 11266858. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:52:07,044][72530] Avg episode reward: [(0, '113004.087'), (1, '163717.311')]
+-[2023-09-19 11:52:07,056][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000013368_6844416.pth...
+-[2023-09-19 11:52:07,056][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000013408_6864896.pth...
+-[2023-09-19 11:52:07,062][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000013240_6778880.pth
+-[2023-09-19 11:52:07,063][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000013200_6758400.pth
+-[2023-09-19 11:52:11,691][73145] Updated weights for policy 0, policy_version 13440 (0.0009)
+-[2023-09-19 11:52:11,692][73219] Updated weights for policy 1, policy_version 13400 (0.0012)
+-[2023-09-19 11:52:12,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5734.4, 300 sec: 5526.1). Total num frames: 13742080. Throughput: 0: 2834.2, 1: 2834.1. Samples: 11301652. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:52:12,043][72530] Avg episode reward: [(0, '113246.114'), (1, '163818.756')]
+-[2023-09-19 11:52:17,043][72530] Fps is (10 sec: 5734.5, 60 sec: 5597.9, 300 sec: 5526.1). Total num frames: 13766656. Throughput: 0: 2831.7, 1: 2831.6. Samples: 11336090. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:52:17,044][72530] Avg episode reward: [(0, '112684.823'), (1, '163893.278')]
+-[2023-09-19 11:52:22,043][72530] Fps is (10 sec: 5734.2, 60 sec: 5734.4, 300 sec: 5526.1). Total num frames: 13799424. Throughput: 0: 2853.1, 1: 2853.3. Samples: 11353408. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:52:22,044][72530] Avg episode reward: [(0, '112684.823'), (1, '163936.233')]
+-[2023-09-19 11:52:22,054][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000013456_6889472.pth...
+-[2023-09-19 11:52:22,054][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000013496_6909952.pth...
+-[2023-09-19 11:52:22,059][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000013288_6803456.pth
+-[2023-09-19 11:52:22,063][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000013328_6823936.pth
+-[2023-09-19 11:52:26,737][73219] Updated weights for policy 1, policy_version 13480 (0.0011)
+-[2023-09-19 11:52:26,738][73145] Updated weights for policy 0, policy_version 13520 (0.0013)
+-[2023-09-19 11:52:27,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5526.1). Total num frames: 13824000. Throughput: 0: 2835.0, 1: 2835.0. Samples: 11385262. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
+-[2023-09-19 11:52:27,044][72530] Avg episode reward: [(0, '110980.059'), (1, '163809.491')]
+-[2023-09-19 11:52:32,043][72530] Fps is (10 sec: 4915.3, 60 sec: 5597.9, 300 sec: 5498.4). Total num frames: 13848576. Throughput: 0: 2781.7, 1: 2781.7. Samples: 11415394. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
+-[2023-09-19 11:52:32,044][72530] Avg episode reward: [(0, '110632.259'), (1, '163809.491')]
+-[2023-09-19 11:52:37,043][72530] Fps is (10 sec: 4915.2, 60 sec: 5597.9, 300 sec: 5498.4). Total num frames: 13873152. Throughput: 0: 2779.5, 1: 2779.4. Samples: 11432370. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
+-[2023-09-19 11:52:37,044][72530] Avg episode reward: [(0, '110937.608'), (1, '162945.052')]
+-[2023-09-19 11:52:37,055][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000013528_6926336.pth...
+-[2023-09-19 11:52:37,055][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000013568_6946816.pth...
+-[2023-09-19 11:52:37,065][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000013368_6844416.pth
+-[2023-09-19 11:52:37,070][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000013408_6864896.pth
+-[2023-09-19 11:52:41,868][73145] Updated weights for policy 0, policy_version 13600 (0.0011)
+-[2023-09-19 11:52:41,868][73219] Updated weights for policy 1, policy_version 13560 (0.0013)
+-[2023-09-19 11:52:42,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5498.4). Total num frames: 13905920. Throughput: 0: 2761.7, 1: 2761.8. Samples: 11464998. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0)
+-[2023-09-19 11:52:42,044][72530] Avg episode reward: [(0, '108749.531'), (1, '162877.908')]
+-[2023-09-19 11:52:47,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5498.4). Total num frames: 13930496. Throughput: 0: 2736.3, 1: 2736.0. Samples: 11496824. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0)
+-[2023-09-19 11:52:47,044][72530] Avg episode reward: [(0, '107670.741'), (1, '161974.202')]
+-[2023-09-19 11:52:52,043][72530] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 13955072. Throughput: 0: 2755.3, 1: 2755.3. Samples: 11514836. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0)
+-[2023-09-19 11:52:52,044][72530] Avg episode reward: [(0, '109926.959'), (1, '161647.451')]
+-[2023-09-19 11:52:52,084][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000013656_6991872.pth...
+-[2023-09-19 11:52:52,087][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000013616_6971392.pth...
+-[2023-09-19 11:52:52,090][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000013496_6909952.pth
+-[2023-09-19 11:52:52,092][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000013456_6889472.pth
+-[2023-09-19 11:52:56,529][73219] Updated weights for policy 1, policy_version 13640 (0.0015)
+-[2023-09-19 11:52:56,529][73145] Updated weights for policy 0, policy_version 13680 (0.0013)
+-[2023-09-19 11:52:57,043][72530] Fps is (10 sec: 5734.5, 60 sec: 5597.9, 300 sec: 5498.4). Total num frames: 13987840. Throughput: 0: 2750.2, 1: 2750.3. Samples: 11549176. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0)
+-[2023-09-19 11:52:57,044][72530] Avg episode reward: [(0, '109926.959'), (1, '161647.451')]
+-[2023-09-19 11:53:02,043][72530] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5498.4). Total num frames: 14012416. Throughput: 0: 2745.7, 1: 2746.6. Samples: 11583242. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:53:02,044][72530] Avg episode reward: [(0, '108812.138'), (1, '160242.020')]
+-[2023-09-19 11:53:07,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5526.1). Total num frames: 14045184. Throughput: 0: 2738.7, 1: 2739.8. Samples: 11599938. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:53:07,044][72530] Avg episode reward: [(0, '109280.885'), (1, '160242.020')]
+-[2023-09-19 11:53:07,053][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000013696_7012352.pth...
+-[2023-09-19 11:53:07,054][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000013736_7032832.pth...
+-[2023-09-19 11:53:07,060][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000013528_6926336.pth
+-[2023-09-19 11:53:07,061][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000013568_6946816.pth
+-[2023-09-19 11:53:10,573][73145] Updated weights for policy 0, policy_version 13760 (0.0015)
+-[2023-09-19 11:53:10,573][73219] Updated weights for policy 1, policy_version 13720 (0.0015)
+-[2023-09-19 11:53:12,043][72530] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5498.4). Total num frames: 14069760. Throughput: 0: 2777.5, 1: 2777.6. Samples: 11635244. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0)
+-[2023-09-19 11:53:12,044][72530] Avg episode reward: [(0, '107640.671'), (1, '160924.342')]
+-[2023-09-19 11:53:17,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5526.1). Total num frames: 14102528. Throughput: 0: 2813.6, 1: 2813.8. Samples: 11668628. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0)
+-[2023-09-19 11:53:17,045][72530] Avg episode reward: [(0, '106086.364'), (1, '160888.486')]
+-[2023-09-19 11:53:22,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5498.4). Total num frames: 14127104. Throughput: 0: 2820.8, 1: 2820.8. Samples: 11686240. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:53:22,044][72530] Avg episode reward: [(0, '105829.988'), (1, '160815.863')]
+-[2023-09-19 11:53:22,079][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000013824_7077888.pth...
+-[2023-09-19 11:53:22,082][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000013656_6991872.pth
+-[2023-09-19 11:53:22,084][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000013784_7057408.pth...
+-[2023-09-19 11:53:22,091][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000013616_6971392.pth
+-[2023-09-19 11:53:25,330][73145] Updated weights for policy 0, policy_version 13840 (0.0015)
+-[2023-09-19 11:53:25,331][73219] Updated weights for policy 1, policy_version 13800 (0.0013)
+-[2023-09-19 11:53:27,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5526.1). Total num frames: 14159872. Throughput: 0: 2819.4, 1: 2819.5. Samples: 11718750. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:53:27,044][72530] Avg episode reward: [(0, '105059.149'), (1, '160896.515')]
+-[2023-09-19 11:53:32,043][72530] Fps is (10 sec: 5734.5, 60 sec: 5597.9, 300 sec: 5526.1). Total num frames: 14184448. Throughput: 0: 2847.1, 1: 2847.4. Samples: 11753076. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:53:32,044][72530] Avg episode reward: [(0, '104051.203'), (1, '160838.692')]
+-[2023-09-19 11:53:37,043][72530] Fps is (10 sec: 4915.2, 60 sec: 5597.9, 300 sec: 5498.4). Total num frames: 14209024. Throughput: 0: 2817.1, 1: 2817.1. Samples: 11768374. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:53:37,044][72530] Avg episode reward: [(0, '108523.798'), (1, '161743.570')]
+-[2023-09-19 11:53:37,054][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000013856_7094272.pth...
+-[2023-09-19 11:53:37,054][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000013896_7114752.pth...
+-[2023-09-19 11:53:37,063][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000013736_7032832.pth
+-[2023-09-19 11:53:37,064][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000013696_7012352.pth
+-[2023-09-19 11:53:40,930][73145] Updated weights for policy 0, policy_version 13920 (0.0017)
+-[2023-09-19 11:53:40,930][73219] Updated weights for policy 1, policy_version 13880 (0.0016)
+-[2023-09-19 11:53:42,043][72530] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5498.4). Total num frames: 14233600. Throughput: 0: 2753.8, 1: 2753.5. Samples: 11797004. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:53:42,044][72530] Avg episode reward: [(0, '108523.798'), (1, '161743.570')]
+-[2023-09-19 11:53:47,043][72530] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5498.4). Total num frames: 14258176. Throughput: 0: 2724.0, 1: 2723.2. Samples: 11828370. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:53:47,044][72530] Avg episode reward: [(0, '108688.999'), (1, '160237.416')]
+-[2023-09-19 11:53:52,043][72530] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5498.4). Total num frames: 14282752. Throughput: 0: 2709.0, 1: 2708.0. Samples: 11843704. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:53:52,045][72530] Avg episode reward: [(0, '112242.915'), (1, '159716.483')]
+-[2023-09-19 11:53:52,054][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000013928_7131136.pth...
+-[2023-09-19 11:53:52,054][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000013968_7151616.pth...
+-[2023-09-19 11:53:52,064][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000013784_7057408.pth
+-[2023-09-19 11:53:52,064][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000013824_7077888.pth
+-[2023-09-19 11:53:57,043][72530] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5470.6). Total num frames: 14307328. Throughput: 0: 2611.5, 1: 2612.1. Samples: 11870304. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:53:57,044][72530] Avg episode reward: [(0, '112242.915'), (1, '159730.340')]
+-[2023-09-19 11:53:57,810][73145] Updated weights for policy 0, policy_version 14000 (0.0013)
+-[2023-09-19 11:53:57,810][73219] Updated weights for policy 1, policy_version 13960 (0.0012)
+-[2023-09-19 11:54:02,043][72530] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5470.6). Total num frames: 14331904. Throughput: 0: 2594.1, 1: 2593.9. Samples: 11902086. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:54:02,044][72530] Avg episode reward: [(0, '116633.173'), (1, '156732.668')]
+-[2023-09-19 11:54:07,043][72530] Fps is (10 sec: 4915.1, 60 sec: 5188.3, 300 sec: 5470.6). Total num frames: 14356480. Throughput: 0: 2554.6, 1: 2554.5. Samples: 11916152. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0)
+-[2023-09-19 11:54:07,044][72530] Avg episode reward: [(0, '119968.454'), (1, '156732.668')]
+-[2023-09-19 11:54:07,054][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000014000_7168000.pth...
+-[2023-09-19 11:54:07,054][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000014040_7188480.pth...
+-[2023-09-19 11:54:07,061][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000013856_7094272.pth
+-[2023-09-19 11:54:07,063][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000013896_7114752.pth
+-[2023-09-19 11:54:12,043][72530] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5470.6). Total num frames: 14381056. Throughput: 0: 2531.6, 1: 2531.5. Samples: 11946590. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0)
+-[2023-09-19 11:54:12,044][72530] Avg episode reward: [(0, '126021.713'), (1, '155674.672')]
+-[2023-09-19 11:54:13,622][73219] Updated weights for policy 1, policy_version 14040 (0.0013)
+-[2023-09-19 11:54:13,623][73145] Updated weights for policy 0, policy_version 14080 (0.0014)
+-[2023-09-19 11:54:17,043][72530] Fps is (10 sec: 5734.5, 60 sec: 5188.3, 300 sec: 5470.6). Total num frames: 14413824. Throughput: 0: 2509.2, 1: 2509.1. Samples: 11978896. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:54:17,044][72530] Avg episode reward: [(0, '128184.575'), (1, '154083.119')]
+-[2023-09-19 11:54:22,043][72530] Fps is (10 sec: 5734.4, 60 sec: 5188.3, 300 sec: 5470.6). Total num frames: 14438400. Throughput: 0: 2497.2, 1: 2498.2. Samples: 11993164. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:54:22,044][72530] Avg episode reward: [(0, '128184.575'), (1, '154040.425')]
+-[2023-09-19 11:54:22,052][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000014080_7208960.pth...
+-[2023-09-19 11:54:22,052][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000014120_7229440.pth...
+-[2023-09-19 11:54:22,058][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000013928_7131136.pth
+-[2023-09-19 11:54:22,061][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000013968_7151616.pth
+-[2023-09-19 11:54:27,043][72530] Fps is (10 sec: 4915.1, 60 sec: 5051.7, 300 sec: 5442.8). Total num frames: 14462976. Throughput: 0: 2535.1, 1: 2535.4. Samples: 12025176. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0)
+-[2023-09-19 11:54:27,044][72530] Avg episode reward: [(0, '140472.932'), (1, '154651.060')]
+-[2023-09-19 11:54:29,535][73145] Updated weights for policy 0, policy_version 14160 (0.0011)
+-[2023-09-19 11:54:29,536][73219] Updated weights for policy 1, policy_version 14120 (0.0014)
+-[2023-09-19 11:54:32,043][72530] Fps is (10 sec: 4915.3, 60 sec: 5051.7, 300 sec: 5442.8). Total num frames: 14487552. Throughput: 0: 2522.9, 1: 2522.9. Samples: 12055430. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0)
+-[2023-09-19 11:54:32,044][72530] Avg episode reward: [(0, '141718.503'), (1, '154651.060')]
+-[2023-09-19 11:54:37,043][72530] Fps is (10 sec: 4915.1, 60 sec: 5051.7, 300 sec: 5442.8). Total num frames: 14512128. Throughput: 0: 2513.4, 1: 2513.2. Samples: 12069904. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0)
+-[2023-09-19 11:54:37,044][72530] Avg episode reward: [(0, '150806.538'), (1, '155291.907')]
+-[2023-09-19 11:54:37,054][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000014152_7245824.pth...
+-[2023-09-19 11:54:37,055][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000014192_7266304.pth...
+-[2023-09-19 11:54:37,060][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000014000_7168000.pth
+-[2023-09-19 11:54:37,063][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000014040_7188480.pth
+-[2023-09-19 11:54:42,043][72530] Fps is (10 sec: 4915.1, 60 sec: 5051.7, 300 sec: 5442.8). Total num frames: 14536704. Throughput: 0: 2545.0, 1: 2545.5. Samples: 12099376. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0)
+-[2023-09-19 11:54:42,045][72530] Avg episode reward: [(0, '151204.698'), (1, '156645.148')]
+-[2023-09-19 11:54:46,277][73145] Updated weights for policy 0, policy_version 14240 (0.0011)
+-[2023-09-19 11:54:46,277][73219] Updated weights for policy 1, policy_version 14200 (0.0011)
+-[2023-09-19 11:54:47,043][72530] Fps is (10 sec: 4915.3, 60 sec: 5051.7, 300 sec: 5415.1). Total num frames: 14561280. Throughput: 0: 2519.7, 1: 2520.0. Samples: 12128874. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0)
+-[2023-09-19 11:54:47,044][72530] Avg episode reward: [(0, '151204.698'), (1, '156645.148')]
+-[2023-09-19 11:54:52,043][72530] Fps is (10 sec: 4915.2, 60 sec: 5051.7, 300 sec: 5415.0). Total num frames: 14585856. Throughput: 0: 2545.9, 1: 2545.9. Samples: 12145282. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0)
+-[2023-09-19 11:54:52,045][72530] Avg episode reward: [(0, '150668.353'), (1, '159741.496')]
+-[2023-09-19 11:54:52,055][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000014224_7282688.pth...
+-[2023-09-19 11:54:52,055][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000014264_7303168.pth...
+-[2023-09-19 11:54:52,061][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000014080_7208960.pth
+-[2023-09-19 11:54:52,065][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000014120_7229440.pth
+-[2023-09-19 11:54:57,043][72530] Fps is (10 sec: 4915.2, 60 sec: 5051.7, 300 sec: 5415.1). Total num frames: 14610432. Throughput: 0: 2537.3, 1: 2537.6. Samples: 12174958. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0)
+-[2023-09-19 11:54:57,045][72530] Avg episode reward: [(0, '151344.969'), (1, '159741.496')]
+-[2023-09-19 11:55:02,044][72530] Fps is (10 sec: 4914.7, 60 sec: 5051.6, 300 sec: 5387.3). Total num frames: 14635008. Throughput: 0: 2521.2, 1: 2521.7. Samples: 12205832. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:55:02,045][72530] Avg episode reward: [(0, '151628.001'), (1, '160794.096')]
+-[2023-09-19 11:55:02,322][73219] Updated weights for policy 1, policy_version 14280 (0.0013)
+-[2023-09-19 11:55:02,323][73145] Updated weights for policy 0, policy_version 14320 (0.0013)
+-[2023-09-19 11:55:07,043][72530] Fps is (10 sec: 4915.2, 60 sec: 5051.7, 300 sec: 5415.1). Total num frames: 14659584. Throughput: 0: 2513.9, 1: 2512.9. Samples: 12219370. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
+-[2023-09-19 11:55:07,044][72530] Avg episode reward: [(0, '148176.544'), (1, '161684.229')]
+-[2023-09-19 11:55:07,052][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000014296_7319552.pth...
+-[2023-09-19 11:55:07,053][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000014336_7340032.pth...
+-[2023-09-19 11:55:07,061][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000014152_7245824.pth
+-[2023-09-19 11:55:07,061][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000014192_7266304.pth
+-[2023-09-19 11:55:12,043][72530] Fps is (10 sec: 4915.8, 60 sec: 5051.7, 300 sec: 5387.3). Total num frames: 14684160. Throughput: 0: 2444.2, 1: 2444.4. Samples: 12245164. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0)
+-[2023-09-19 11:55:12,045][72530] Avg episode reward: [(0, '148176.544'), (1, '161684.229')]
+-[2023-09-19 11:55:17,043][72530] Fps is (10 sec: 4915.2, 60 sec: 4915.2, 300 sec: 5387.3). Total num frames: 14708736. Throughput: 0: 2444.5, 1: 2444.5. Samples: 12275438. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0)
+-[2023-09-19 11:55:17,045][72530] Avg episode reward: [(0, '148556.520'), (1, '161543.907')]
+-[2023-09-19 11:55:19,505][73219] Updated weights for policy 1, policy_version 14360 (0.0011)
+-[2023-09-19 11:55:19,506][73145] Updated weights for policy 0, policy_version 14400 (0.0014)
+-[2023-09-19 11:55:22,043][72530] Fps is (10 sec: 4915.2, 60 sec: 4915.2, 300 sec: 5387.3). Total num frames: 14733312. Throughput: 0: 2457.9, 1: 2457.9. Samples: 12291112. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0)
+-[2023-09-19 11:55:22,044][72530] Avg episode reward: [(0, '146305.866'), (1, '161543.272')]
+-[2023-09-19 11:55:22,052][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000014368_7356416.pth...
+-[2023-09-19 11:55:22,052][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000014408_7376896.pth...
+-[2023-09-19 11:55:22,061][73131] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000014224_7282688.pth
+-[2023-09-19 11:55:22,061][73130] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000014264_7303168.pth
+-[2023-09-19 11:55:22,280][72530] Keyboard interrupt detected in the event loop EvtLoop [Runner_EvtLoop, process=main process 72530], exiting...
+-[2023-09-19 11:55:22,281][72530] Runner profile tree view:
+-main_loop: 2141.4988
+-[2023-09-19 11:55:22,282][72530] Collected {1: 7356416, 0: 7376896}, FPS: 5741.9
+-[2023-09-19 11:55:22,281][73130] Stopping Batcher_0...
+-[2023-09-19 11:55:22,281][73131] Stopping Batcher_1...
+-[2023-09-19 11:55:22,282][73130] Loop batcher_evt_loop terminating...
+-[2023-09-19 11:55:22,282][73131] Loop batcher_evt_loop terminating...
+-[2023-09-19 11:55:22,282][73130] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000014408_7376896.pth...
+-[2023-09-19 11:55:22,283][73131] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000014368_7356416.pth...
+-[2023-09-19 11:55:22,285][73221] Stopping RolloutWorker_w1...
+-[2023-09-19 11:55:22,285][73221] Loop rollout_proc1_evt_loop terminating...
+-[2023-09-19 11:55:22,288][73220] Stopping RolloutWorker_w2...
+-[2023-09-19 11:55:22,288][73130] Stopping LearnerWorker_p0...
+-[2023-09-19 11:55:22,288][73220] Loop rollout_proc2_evt_loop terminating...
+-[2023-09-19 11:55:22,288][73130] Loop learner_proc0_evt_loop terminating...
+-[2023-09-19 11:55:22,288][73222] Stopping RolloutWorker_w6...
+-[2023-09-19 11:55:22,288][73131] Stopping LearnerWorker_p1...
+-[2023-09-19 11:55:22,289][73222] Loop rollout_proc6_evt_loop terminating...
+-[2023-09-19 11:55:22,289][73131] Loop learner_proc1_evt_loop terminating...
+-[2023-09-19 11:55:22,290][73218] Stopping RolloutWorker_w0...
+-[2023-09-19 11:55:22,290][73224] Stopping RolloutWorker_w4...
+-[2023-09-19 11:55:22,291][73218] Loop rollout_proc0_evt_loop terminating...
+-[2023-09-19 11:55:22,291][73223] Stopping RolloutWorker_w3...
+-[2023-09-19 11:55:22,291][73224] Loop rollout_proc4_evt_loop terminating...
+-[2023-09-19 11:55:22,291][73223] Loop rollout_proc3_evt_loop terminating...
+-[2023-09-19 11:55:22,292][73226] Stopping RolloutWorker_w7...
+-[2023-09-19 11:55:22,292][73226] Loop rollout_proc7_evt_loop terminating...
+-[2023-09-19 11:55:22,295][73229] Stopping RolloutWorker_w5...
+-[2023-09-19 11:55:22,295][73229] Loop rollout_proc5_evt_loop terminating...
+-[2023-09-19 11:55:22,296][73145] Weights refcount: 2 0
+-[2023-09-19 11:55:22,297][73145] Stopping InferenceWorker_p0-w0...
+-[2023-09-19 11:55:22,297][73145] Loop inference_proc0-0_evt_loop terminating...
+-[2023-09-19 11:55:22,301][73219] Weights refcount: 2 0
+-[2023-09-19 11:55:22,303][73219] Stopping InferenceWorker_p1-w0...
+-[2023-09-19 11:55:22,303][73219] Loop inference_proc1-0_evt_loop terminating...
++[2023-09-21 15:10:45,648][101116] Worker 0 uses CPU cores [0, 1, 2, 3]
++[2023-09-21 15:10:45,774][101118] Worker 1 uses CPU cores [4, 5, 6, 7]
++[2023-09-21 15:10:46,022][101035] Using optimizer <class 'torch.optim.adam.Adam'>
++[2023-09-21 15:10:46,023][101035] No checkpoints found
++[2023-09-21 15:10:46,023][101035] Did not load from checkpoint, starting from scratch!
++[2023-09-21 15:10:46,023][101035] Initialized policy 1 weights for model version 0
++[2023-09-21 15:10:46,025][101035] LearnerWorker_p1 finished initialization!
++[2023-09-21 15:10:46,025][101035] Using GPUs [0] for process 1 (actually maps to GPUs [1])
++[2023-09-21 15:10:46,158][101034] Using optimizer <class 'torch.optim.adam.Adam'>
++[2023-09-21 15:10:46,159][101034] No checkpoints found
++[2023-09-21 15:10:46,159][101034] Did not load from checkpoint, starting from scratch!
++[2023-09-21 15:10:46,159][101034] Initialized policy 0 weights for model version 0
++[2023-09-21 15:10:46,161][101034] LearnerWorker_p0 finished initialization!
++[2023-09-21 15:10:46,161][101034] Using GPUs [0] for process 0 (actually maps to GPUs [0])
++[2023-09-21 15:10:46,569][101117] RunningMeanStd input shape: (376,)
++[2023-09-21 15:10:46,570][101117] RunningMeanStd input shape: (1,)
++[2023-09-21 15:10:46,602][99566] Inference worker 1-0 is ready!
++[2023-09-21 15:10:46,707][101115] RunningMeanStd input shape: (376,)
++[2023-09-21 15:10:46,707][101115] RunningMeanStd input shape: (1,)
++[2023-09-21 15:10:46,739][99566] Inference worker 0-0 is ready!
++[2023-09-21 15:10:46,740][99566] All inference workers are ready! Signal rollout workers to start!
++[2023-09-21 15:10:46,835][101122] Decorrelating experience for 0 frames...
++[2023-09-21 15:10:46,836][101122] Decorrelating experience for 64 frames...
++[2023-09-21 15:10:46,836][101120] Decorrelating experience for 0 frames...
++[2023-09-21 15:10:46,837][101120] Decorrelating experience for 64 frames...
++[2023-09-21 15:10:46,838][101118] Decorrelating experience for 0 frames...
++[2023-09-21 15:10:46,838][101116] Decorrelating experience for 0 frames...
++[2023-09-21 15:10:46,839][101118] Decorrelating experience for 64 frames...
++[2023-09-21 15:10:46,839][101119] Decorrelating experience for 0 frames...
++[2023-09-21 15:10:46,839][101116] Decorrelating experience for 64 frames...
++[2023-09-21 15:10:46,840][101119] Decorrelating experience for 64 frames...
++[2023-09-21 15:10:46,840][101121] Decorrelating experience for 0 frames...
++[2023-09-21 15:10:46,841][101121] Decorrelating experience for 64 frames...
++[2023-09-21 15:10:46,843][101124] Decorrelating experience for 0 frames...
++[2023-09-21 15:10:46,844][101124] Decorrelating experience for 64 frames...
++[2023-09-21 15:10:46,851][101123] Decorrelating experience for 0 frames...
++[2023-09-21 15:10:46,852][101123] Decorrelating experience for 64 frames...
++[2023-09-21 15:10:46,887][101120] Decorrelating experience for 128 frames...
++[2023-09-21 15:10:46,887][101122] Decorrelating experience for 128 frames...
++[2023-09-21 15:10:46,888][101116] Decorrelating experience for 128 frames...
++[2023-09-21 15:10:46,892][101119] Decorrelating experience for 128 frames...
++[2023-09-21 15:10:46,893][101118] Decorrelating experience for 128 frames...
++[2023-09-21 15:10:46,893][101121] Decorrelating experience for 128 frames...
++[2023-09-21 15:10:46,897][101124] Decorrelating experience for 128 frames...
++[2023-09-21 15:10:46,903][101123] Decorrelating experience for 128 frames...
++[2023-09-21 15:10:46,985][101116] Decorrelating experience for 192 frames...
++[2023-09-21 15:10:46,985][101122] Decorrelating experience for 192 frames...
++[2023-09-21 15:10:46,985][101120] Decorrelating experience for 192 frames...
++[2023-09-21 15:10:46,989][101119] Decorrelating experience for 192 frames...
++[2023-09-21 15:10:46,990][101118] Decorrelating experience for 192 frames...
++[2023-09-21 15:10:46,995][101121] Decorrelating experience for 192 frames...
++[2023-09-21 15:10:46,998][101124] Decorrelating experience for 192 frames...
++[2023-09-21 15:10:47,003][101123] Decorrelating experience for 192 frames...
++[2023-09-21 15:10:47,149][101119] Decorrelating experience for 256 frames...
++[2023-09-21 15:10:47,153][101120] Decorrelating experience for 256 frames...
++[2023-09-21 15:10:47,154][101116] Decorrelating experience for 256 frames...
++[2023-09-21 15:10:47,156][101122] Decorrelating experience for 256 frames...
++[2023-09-21 15:10:47,157][101118] Decorrelating experience for 256 frames...
++[2023-09-21 15:10:47,163][101121] Decorrelating experience for 256 frames...
++[2023-09-21 15:10:47,164][101123] Decorrelating experience for 256 frames...
++[2023-09-21 15:10:47,170][101124] Decorrelating experience for 256 frames...
++[2023-09-21 15:10:47,345][101119] Decorrelating experience for 320 frames...
++[2023-09-21 15:10:47,348][101120] Decorrelating experience for 320 frames...
++[2023-09-21 15:10:47,349][101118] Decorrelating experience for 320 frames...
++[2023-09-21 15:10:47,359][101123] Decorrelating experience for 320 frames...
++[2023-09-21 15:10:47,363][101122] Decorrelating experience for 320 frames...
++[2023-09-21 15:10:47,370][101121] Decorrelating experience for 320 frames...
++[2023-09-21 15:10:47,372][101124] Decorrelating experience for 320 frames...
++[2023-09-21 15:10:47,377][101116] Decorrelating experience for 320 frames...
++[2023-09-21 15:10:47,595][101123] Decorrelating experience for 384 frames...
++[2023-09-21 15:10:47,596][101120] Decorrelating experience for 384 frames...
++[2023-09-21 15:10:47,600][101118] Decorrelating experience for 384 frames...
++[2023-09-21 15:10:47,603][101119] Decorrelating experience for 384 frames...
++[2023-09-21 15:10:47,609][101122] Decorrelating experience for 384 frames...
++[2023-09-21 15:10:47,611][101121] Decorrelating experience for 384 frames...
++[2023-09-21 15:10:47,632][101116] Decorrelating experience for 384 frames...
++[2023-09-21 15:10:47,633][101124] Decorrelating experience for 384 frames...
++[2023-09-21 15:10:47,892][101118] Decorrelating experience for 448 frames...
++[2023-09-21 15:10:47,903][101119] Decorrelating experience for 448 frames...
++[2023-09-21 15:10:47,910][101122] Decorrelating experience for 448 frames...
++[2023-09-21 15:10:47,915][101121] Decorrelating experience for 448 frames...
++[2023-09-21 15:10:47,915][101123] Decorrelating experience for 448 frames...
++[2023-09-21 15:10:47,917][101120] Decorrelating experience for 448 frames...
++[2023-09-21 15:10:47,930][101124] Decorrelating experience for 448 frames...
++[2023-09-21 15:10:47,947][101116] Decorrelating experience for 448 frames...
++[2023-09-21 15:10:49,496][99566] Fps is (10 sec: nan, 60 sec: nan, 300 sec: nan). Total num frames: 0. Throughput: 0: nan, 1: nan. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
++[2023-09-21 15:10:54,497][99566] Fps is (10 sec: 3276.5, 60 sec: 3276.5, 300 sec: 3276.5). Total num frames: 16384. Throughput: 0: 1638.3, 1: 1638.3. Samples: 16384. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0)
++[2023-09-21 15:10:54,861][101035] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000000024_12288.pth...
++[2023-09-21 15:10:54,871][101034] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000000024_12288.pth...
++[2023-09-21 15:10:59,497][99566] Fps is (10 sec: 5734.3, 60 sec: 5734.3, 300 sec: 5734.3). Total num frames: 57344. Throughput: 0: 2677.6, 1: 2619.8. Samples: 52974. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0)
++[2023-09-21 15:10:59,498][99566] Avg episode reward: [(0, '29111.123'), (1, '26500.965')]
++[2023-09-21 15:11:03,368][101115] Updated weights for policy 0, policy_version 80 (0.0014)
++[2023-09-21 15:11:03,369][101117] Updated weights for policy 1, policy_version 80 (0.0013)
++[2023-09-21 15:11:03,395][99566] Heartbeat connected on Batcher_0
++[2023-09-21 15:11:03,398][99566] Heartbeat connected on LearnerWorker_p0
++[2023-09-21 15:11:03,401][99566] Heartbeat connected on Batcher_1
++[2023-09-21 15:11:03,404][99566] Heartbeat connected on LearnerWorker_p1
++[2023-09-21 15:11:03,410][99566] Heartbeat connected on InferenceWorker_p0-w0
++[2023-09-21 15:11:03,415][99566] Heartbeat connected on InferenceWorker_p1-w0
++[2023-09-21 15:11:03,419][99566] Heartbeat connected on RolloutWorker_w0
++[2023-09-21 15:11:03,420][99566] Heartbeat connected on RolloutWorker_w1
++[2023-09-21 15:11:03,425][99566] Heartbeat connected on RolloutWorker_w2
++[2023-09-21 15:11:03,430][99566] Heartbeat connected on RolloutWorker_w5
++[2023-09-21 15:11:03,432][99566] Heartbeat connected on RolloutWorker_w3
++[2023-09-21 15:11:03,435][99566] Heartbeat connected on RolloutWorker_w4
++[2023-09-21 15:11:03,435][99566] Heartbeat connected on RolloutWorker_w6
++[2023-09-21 15:11:03,441][99566] Heartbeat connected on RolloutWorker_w7
++[2023-09-21 15:11:04,497][99566] Fps is (10 sec: 6553.8, 60 sec: 5461.3, 300 sec: 5461.3). Total num frames: 81920. Throughput: 0: 2445.3, 1: 2433.3. Samples: 73180. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
++[2023-09-21 15:11:04,498][99566] Avg episode reward: [(0, '32653.580'), (1, '29531.158')]
++[2023-09-21 15:11:09,497][99566] Fps is (10 sec: 5734.4, 60 sec: 5734.4, 300 sec: 5734.4). Total num frames: 114688. Throughput: 0: 2741.4, 1: 2711.0. Samples: 109048. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
++[2023-09-21 15:11:09,497][99566] Avg episode reward: [(0, '42202.736'), (1, '37345.618')]
++[2023-09-21 15:11:09,500][101034] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000000112_57344.pth...
++[2023-09-21 15:11:09,500][101035] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000000112_57344.pth...
++[2023-09-21 15:11:14,496][99566] Fps is (10 sec: 7372.8, 60 sec: 6225.9, 300 sec: 6225.9). Total num frames: 155648. Throughput: 0: 3059.7, 1: 3035.7. Samples: 152388. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0)
++[2023-09-21 15:11:14,498][99566] Avg episode reward: [(0, '44269.193'), (1, '39095.771')]
++[2023-09-21 15:11:15,281][101117] Updated weights for policy 1, policy_version 160 (0.0014)
++[2023-09-21 15:11:15,282][101115] Updated weights for policy 0, policy_version 160 (0.0014)
++[2023-09-21 15:11:19,496][99566] Fps is (10 sec: 7372.8, 60 sec: 6280.5, 300 sec: 6280.5). Total num frames: 188416. Throughput: 0: 2891.8, 1: 2871.1. Samples: 172888. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0)
++[2023-09-21 15:11:19,498][99566] Avg episode reward: [(0, '52608.069'), (1, '46035.948')]
++[2023-09-21 15:11:24,497][99566] Fps is (10 sec: 7372.7, 60 sec: 6553.6, 300 sec: 6553.6). Total num frames: 229376. Throughput: 0: 3103.4, 1: 3086.0. Samples: 216632. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
++[2023-09-21 15:11:24,498][99566] Avg episode reward: [(0, '52608.069'), (1, '49544.367')]
++[2023-09-21 15:11:24,502][101035] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000000224_114688.pth...
++[2023-09-21 15:11:24,502][101034] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000000224_114688.pth...
++[2023-09-21 15:11:24,508][101035] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000000024_12288.pth
++[2023-09-21 15:11:24,509][101035] Saving new best policy, reward=49544.367!
++[2023-09-21 15:11:24,510][101034] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000000024_12288.pth
++[2023-09-21 15:11:24,511][101034] Saving new best policy, reward=52608.069!
++[2023-09-21 15:11:26,547][101117] Updated weights for policy 1, policy_version 240 (0.0011)
++[2023-09-21 15:11:26,548][101115] Updated weights for policy 0, policy_version 240 (0.0012)
++[2023-09-21 15:11:29,496][99566] Fps is (10 sec: 7372.8, 60 sec: 6553.6, 300 sec: 6553.6). Total num frames: 262144. Throughput: 0: 3277.6, 1: 3275.7. Samples: 262134. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0)
++[2023-09-21 15:11:29,497][99566] Avg episode reward: [(0, '66016.832'), (1, '59449.959')]
++[2023-09-21 15:11:29,498][101034] Saving new best policy, reward=66016.832!
++[2023-09-21 15:11:29,498][101035] Saving new best policy, reward=59449.959!
++[2023-09-21 15:11:34,496][99566] Fps is (10 sec: 6963.4, 60 sec: 6644.6, 300 sec: 6644.6). Total num frames: 299008. Throughput: 0: 3152.0, 1: 3139.7. Samples: 283126. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
++[2023-09-21 15:11:34,497][99566] Avg episode reward: [(0, '68820.170'), (1, '64166.988')]
++[2023-09-21 15:11:34,497][101034] Saving new best policy, reward=68820.170!
++[2023-09-21 15:11:34,499][101035] Saving new best policy, reward=64166.988!
++[2023-09-21 15:11:37,925][101117] Updated weights for policy 1, policy_version 320 (0.0015)
++[2023-09-21 15:11:37,925][101115] Updated weights for policy 0, policy_version 320 (0.0013)
++[2023-09-21 15:11:39,497][99566] Fps is (10 sec: 7372.6, 60 sec: 6717.4, 300 sec: 6717.4). Total num frames: 335872. Throughput: 0: 3456.7, 1: 3448.0. Samples: 327094. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
++[2023-09-21 15:11:39,498][99566] Avg episode reward: [(0, '75159.121'), (1, '68598.547')]
++[2023-09-21 15:11:39,506][101035] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000000328_167936.pth...
++[2023-09-21 15:11:39,506][101034] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000000328_167936.pth...
++[2023-09-21 15:11:39,513][101035] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000000112_57344.pth
++[2023-09-21 15:11:39,513][101035] Saving new best policy, reward=68598.547!
++[2023-09-21 15:11:39,515][101034] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000000112_57344.pth
++[2023-09-21 15:11:39,516][101034] Saving new best policy, reward=75159.121!
++[2023-09-21 15:11:44,497][99566] Fps is (10 sec: 6963.0, 60 sec: 6702.5, 300 sec: 6702.5). Total num frames: 368640. Throughput: 0: 3484.0, 1: 3483.4. Samples: 366510. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
++[2023-09-21 15:11:44,498][99566] Avg episode reward: [(0, '77287.138'), (1, '73006.291')]
++[2023-09-21 15:11:44,499][101034] Saving new best policy, reward=77287.138!
++[2023-09-21 15:11:44,499][101035] Saving new best policy, reward=73006.291!
++[2023-09-21 15:11:49,496][99566] Fps is (10 sec: 6553.8, 60 sec: 6690.1, 300 sec: 6690.1). Total num frames: 401408. Throughput: 0: 3500.4, 1: 3490.9. Samples: 387786. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
++[2023-09-21 15:11:49,497][99566] Avg episode reward: [(0, '79728.904'), (1, '73989.310')]
++[2023-09-21 15:11:49,498][101034] Saving new best policy, reward=79728.904!
++[2023-09-21 15:11:49,498][101035] Saving new best policy, reward=73989.310!
++[2023-09-21 15:11:49,630][101117] Updated weights for policy 1, policy_version 400 (0.0014)
++[2023-09-21 15:11:49,630][101115] Updated weights for policy 0, policy_version 400 (0.0015)
++[2023-09-21 15:11:54,496][99566] Fps is (10 sec: 7372.8, 60 sec: 7099.8, 300 sec: 6805.7). Total num frames: 442368. Throughput: 0: 3564.5, 1: 3565.1. Samples: 429880. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
++[2023-09-21 15:11:54,497][99566] Avg episode reward: [(0, '83640.081'), (1, '77200.239')]
++[2023-09-21 15:11:54,506][101034] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000000432_221184.pth...
++[2023-09-21 15:11:54,506][101035] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000000432_221184.pth...
++[2023-09-21 15:11:54,512][101034] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000000224_114688.pth
++[2023-09-21 15:11:54,512][101035] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000000224_114688.pth
++[2023-09-21 15:11:54,513][101034] Saving new best policy, reward=83640.081!
++[2023-09-21 15:11:54,513][101035] Saving new best policy, reward=77200.239!
++[2023-09-21 15:11:59,497][99566] Fps is (10 sec: 6553.5, 60 sec: 6826.7, 300 sec: 6670.6). Total num frames: 466944. Throughput: 0: 3511.4, 1: 3516.1. Samples: 468628. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
++[2023-09-21 15:11:59,498][99566] Avg episode reward: [(0, '84922.994'), (1, '77768.201')]
++[2023-09-21 15:11:59,499][101034] Saving new best policy, reward=84922.994!
++[2023-09-21 15:11:59,499][101035] Saving new best policy, reward=77768.201!
++[2023-09-21 15:12:02,658][101117] Updated weights for policy 1, policy_version 480 (0.0016)
++[2023-09-21 15:12:02,658][101115] Updated weights for policy 0, policy_version 480 (0.0011)
++[2023-09-21 15:12:04,496][99566] Fps is (10 sec: 5734.4, 60 sec: 6963.2, 300 sec: 6662.8). Total num frames: 499712. Throughput: 0: 3466.4, 1: 3468.6. Samples: 484962. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
++[2023-09-21 15:12:04,497][99566] Avg episode reward: [(0, '88681.435'), (1, '80463.062')]
++[2023-09-21 15:12:04,498][101034] Saving new best policy, reward=88681.435!
++[2023-09-21 15:12:04,498][101035] Saving new best policy, reward=80463.062!
++[2023-09-21 15:12:09,497][99566] Fps is (10 sec: 6553.6, 60 sec: 6963.2, 300 sec: 6656.0). Total num frames: 532480. Throughput: 0: 3427.1, 1: 3427.7. Samples: 525100. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
++[2023-09-21 15:12:09,498][99566] Avg episode reward: [(0, '89644.782'), (1, '81336.452')]
++[2023-09-21 15:12:09,508][101035] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000000520_266240.pth...
++[2023-09-21 15:12:09,509][101034] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000000520_266240.pth...
++[2023-09-21 15:12:09,515][101035] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000000328_167936.pth
++[2023-09-21 15:12:09,516][101035] Saving new best policy, reward=81336.452!
++[2023-09-21 15:12:09,517][101034] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000000328_167936.pth
++[2023-09-21 15:12:09,517][101034] Saving new best policy, reward=89644.782!
++[2023-09-21 15:12:14,497][99566] Fps is (10 sec: 6553.5, 60 sec: 6826.7, 300 sec: 6650.0). Total num frames: 565248. Throughput: 0: 3353.4, 1: 3345.7. Samples: 563594. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0)
++[2023-09-21 15:12:14,498][99566] Avg episode reward: [(0, '93904.727'), (1, '84817.215')]
++[2023-09-21 15:12:14,499][101034] Saving new best policy, reward=93904.727!
++[2023-09-21 15:12:14,499][101035] Saving new best policy, reward=84817.215!
++[2023-09-21 15:12:15,959][101117] Updated weights for policy 1, policy_version 560 (0.0014)
++[2023-09-21 15:12:15,960][101115] Updated weights for policy 0, policy_version 560 (0.0012)
++[2023-09-21 15:12:19,497][99566] Fps is (10 sec: 6553.6, 60 sec: 6826.7, 300 sec: 6644.6). Total num frames: 598016. Throughput: 0: 3291.8, 1: 3291.1. Samples: 579360. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
++[2023-09-21 15:12:19,498][99566] Avg episode reward: [(0, '95010.164'), (1, '85718.694')]
++[2023-09-21 15:12:19,499][101034] Saving new best policy, reward=95010.164!
++[2023-09-21 15:12:19,499][101035] Saving new best policy, reward=85718.694!
++[2023-09-21 15:12:24,497][99566] Fps is (10 sec: 6553.6, 60 sec: 6690.1, 300 sec: 6639.8). Total num frames: 630784. Throughput: 0: 3273.7, 1: 3269.4. Samples: 621534. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
++[2023-09-21 15:12:24,498][99566] Avg episode reward: [(0, '98412.703'), (1, '89341.648')]
++[2023-09-21 15:12:24,508][101035] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000000616_315392.pth...
++[2023-09-21 15:12:24,508][101034] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000000616_315392.pth...
++[2023-09-21 15:12:24,515][101034] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000000432_221184.pth
++[2023-09-21 15:12:24,516][101035] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000000432_221184.pth
++[2023-09-21 15:12:24,516][101034] Saving new best policy, reward=98412.703!
++[2023-09-21 15:12:24,517][101035] Saving new best policy, reward=89341.648!
++[2023-09-21 15:12:27,494][101115] Updated weights for policy 0, policy_version 640 (0.0013)
++[2023-09-21 15:12:27,495][101117] Updated weights for policy 1, policy_version 640 (0.0015)
++[2023-09-21 15:12:29,496][99566] Fps is (10 sec: 6553.7, 60 sec: 6690.1, 300 sec: 6635.5). Total num frames: 663552. Throughput: 0: 3307.6, 1: 3308.7. Samples: 664240. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
++[2023-09-21 15:12:29,497][99566] Avg episode reward: [(0, '100510.374'), (1, '91250.829')]
++[2023-09-21 15:12:29,498][101034] Saving new best policy, reward=100510.374!
++[2023-09-21 15:12:29,498][101035] Saving new best policy, reward=91250.829!
++[2023-09-21 15:12:34,496][99566] Fps is (10 sec: 7372.9, 60 sec: 6758.4, 300 sec: 6709.6). Total num frames: 704512. Throughput: 0: 3325.3, 1: 3326.3. Samples: 687108. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0)
++[2023-09-21 15:12:34,498][99566] Avg episode reward: [(0, '106969.058'), (1, '95836.961')]
++[2023-09-21 15:12:34,499][101034] Saving new best policy, reward=106969.058!
++[2023-09-21 15:12:34,499][101035] Saving new best policy, reward=95836.961!
++[2023-09-21 15:12:38,780][101115] Updated weights for policy 0, policy_version 720 (0.0012)
++[2023-09-21 15:12:38,780][101117] Updated weights for policy 1, policy_version 720 (0.0015)
++[2023-09-21 15:12:39,497][99566] Fps is (10 sec: 7372.7, 60 sec: 6690.1, 300 sec: 6702.5). Total num frames: 737280. Throughput: 0: 3329.2, 1: 3331.7. Samples: 729624. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0)
++[2023-09-21 15:12:39,498][99566] Avg episode reward: [(0, '106969.058'), (1, '97182.862')]
++[2023-09-21 15:12:39,508][101034] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000000720_368640.pth...
++[2023-09-21 15:12:39,508][101035] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000000720_368640.pth...
++[2023-09-21 15:12:39,517][101034] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000000520_266240.pth
++[2023-09-21 15:12:39,517][101035] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000000520_266240.pth
++[2023-09-21 15:12:39,517][101035] Saving new best policy, reward=97182.862!
++[2023-09-21 15:12:44,496][99566] Fps is (10 sec: 6553.7, 60 sec: 6690.1, 300 sec: 6696.1). Total num frames: 770048. Throughput: 0: 3327.6, 1: 3329.0. Samples: 768176. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0)
++[2023-09-21 15:12:44,497][99566] Avg episode reward: [(0, '113117.062'), (1, '101505.450')]
++[2023-09-21 15:12:44,498][101034] Saving new best policy, reward=113117.062!
++[2023-09-21 15:12:44,498][101035] Saving new best policy, reward=101505.450!
++[2023-09-21 15:12:49,496][99566] Fps is (10 sec: 6553.7, 60 sec: 6690.1, 300 sec: 6690.1). Total num frames: 802816. Throughput: 0: 3349.2, 1: 3355.5. Samples: 786672. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0)
++[2023-09-21 15:12:49,497][99566] Avg episode reward: [(0, '113117.062'), (1, '101932.079')]
++[2023-09-21 15:12:49,499][101035] Saving new best policy, reward=101932.079!
++[2023-09-21 15:12:51,683][101115] Updated weights for policy 0, policy_version 800 (0.0014)
++[2023-09-21 15:12:51,683][101117] Updated weights for policy 1, policy_version 800 (0.0013)
++[2023-09-21 15:12:54,496][99566] Fps is (10 sec: 6553.6, 60 sec: 6553.6, 300 sec: 6684.7). Total num frames: 835584. Throughput: 0: 3348.4, 1: 3351.9. Samples: 826612. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0)
++[2023-09-21 15:12:54,497][99566] Avg episode reward: [(0, '116085.972'), (1, '103659.764')]
++[2023-09-21 15:12:54,505][101034] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000000816_417792.pth...
++[2023-09-21 15:12:54,505][101035] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000000816_417792.pth...
++[2023-09-21 15:12:54,509][101034] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000000616_315392.pth
++[2023-09-21 15:12:54,509][101035] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000000616_315392.pth
++[2023-09-21 15:12:54,509][101034] Saving new best policy, reward=116085.972!
++[2023-09-21 15:12:54,509][101035] Saving new best policy, reward=103659.764!
++[2023-09-21 15:12:59,496][99566] Fps is (10 sec: 6553.6, 60 sec: 6690.1, 300 sec: 6679.6). Total num frames: 868352. Throughput: 0: 3349.9, 1: 3347.9. Samples: 864992. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0)
++[2023-09-21 15:12:59,497][99566] Avg episode reward: [(0, '116085.972'), (1, '104473.905')]
++[2023-09-21 15:12:59,498][101035] Saving new best policy, reward=104473.905!
++[2023-09-21 15:13:04,444][101115] Updated weights for policy 0, policy_version 880 (0.0016)
++[2023-09-21 15:13:04,444][101117] Updated weights for policy 1, policy_version 880 (0.0015)
++[2023-09-21 15:13:04,496][99566] Fps is (10 sec: 6553.6, 60 sec: 6690.1, 300 sec: 6675.0). Total num frames: 901120. Throughput: 0: 3359.1, 1: 3359.9. Samples: 881714. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0)
++[2023-09-21 15:13:04,497][99566] Avg episode reward: [(0, '120958.463'), (1, '109086.335')]
++[2023-09-21 15:13:04,498][101034] Saving new best policy, reward=120958.463!
++[2023-09-21 15:13:04,498][101035] Saving new best policy, reward=109086.335!
++[2023-09-21 15:13:09,497][99566] Fps is (10 sec: 6553.5, 60 sec: 6690.1, 300 sec: 6670.6). Total num frames: 933888. Throughput: 0: 3373.1, 1: 3378.0. Samples: 925336. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
++[2023-09-21 15:13:09,497][99566] Avg episode reward: [(0, '121585.003'), (1, '109071.902')]
++[2023-09-21 15:13:09,507][101034] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000000912_466944.pth...
++[2023-09-21 15:13:09,507][101035] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000000912_466944.pth...
++[2023-09-21 15:13:09,516][101035] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000000720_368640.pth
++[2023-09-21 15:13:09,516][101034] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000000720_368640.pth
++[2023-09-21 15:13:09,517][101034] Saving new best policy, reward=121585.003!
++[2023-09-21 15:13:14,496][99566] Fps is (10 sec: 6553.6, 60 sec: 6690.1, 300 sec: 6666.6). Total num frames: 966656. Throughput: 0: 3353.0, 1: 3356.2. Samples: 966154. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
++[2023-09-21 15:13:14,497][99566] Avg episode reward: [(0, '122500.165'), (1, '112494.272')]
++[2023-09-21 15:13:14,498][101034] Saving new best policy, reward=122500.165!
++[2023-09-21 15:13:14,498][101035] Saving new best policy, reward=112494.272!
++[2023-09-21 15:13:16,904][101117] Updated weights for policy 1, policy_version 960 (0.0014)
++[2023-09-21 15:13:16,904][101115] Updated weights for policy 0, policy_version 960 (0.0012)
++[2023-09-21 15:13:19,497][99566] Fps is (10 sec: 5734.4, 60 sec: 6553.6, 300 sec: 6608.2). Total num frames: 991232. Throughput: 0: 3280.2, 1: 3286.4. Samples: 982602. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
++[2023-09-21 15:13:19,497][99566] Avg episode reward: [(0, '124457.495'), (1, '113067.463')]
++[2023-09-21 15:13:19,499][101034] Saving new best policy, reward=124457.495!
++[2023-09-21 15:13:19,499][101035] Saving new best policy, reward=113067.463!
++[2023-09-21 15:13:24,497][99566] Fps is (10 sec: 5734.3, 60 sec: 6553.6, 300 sec: 6606.4). Total num frames: 1024000. Throughput: 0: 3215.8, 1: 3213.7. Samples: 1018952. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
++[2023-09-21 15:13:24,498][99566] Avg episode reward: [(0, '128172.103'), (1, '116190.090')]
++[2023-09-21 15:13:24,506][101034] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000001000_512000.pth...
++[2023-09-21 15:13:24,506][101035] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000001000_512000.pth...
++[2023-09-21 15:13:24,513][101035] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000000816_417792.pth
++[2023-09-21 15:13:24,513][101034] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000000816_417792.pth
++[2023-09-21 15:13:24,513][101035] Saving new best policy, reward=116190.090!
++[2023-09-21 15:13:24,514][101034] Saving new best policy, reward=128172.103!
++[2023-09-21 15:13:29,496][99566] Fps is (10 sec: 6553.6, 60 sec: 6553.6, 300 sec: 6604.8). Total num frames: 1056768. Throughput: 0: 3251.9, 1: 3247.1. Samples: 1060632. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
++[2023-09-21 15:13:29,498][99566] Avg episode reward: [(0, '129655.387'), (1, '116680.591')]
++[2023-09-21 15:13:29,499][101034] Saving new best policy, reward=129655.387!
++[2023-09-21 15:13:29,499][101035] Saving new best policy, reward=116680.591!
++[2023-09-21 15:13:29,751][101117] Updated weights for policy 1, policy_version 1040 (0.0013)
++[2023-09-21 15:13:29,751][101115] Updated weights for policy 0, policy_version 1040 (0.0013)
++[2023-09-21 15:13:34,497][99566] Fps is (10 sec: 6553.6, 60 sec: 6417.1, 300 sec: 6603.2). Total num frames: 1089536. Throughput: 0: 3241.6, 1: 3235.9. Samples: 1078160. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
++[2023-09-21 15:13:34,498][99566] Avg episode reward: [(0, '131544.446'), (1, '116603.723')]
++[2023-09-21 15:13:34,499][101034] Saving new best policy, reward=131544.446!
++[2023-09-21 15:13:39,497][99566] Fps is (10 sec: 6553.5, 60 sec: 6417.1, 300 sec: 6601.8). Total num frames: 1122304. Throughput: 0: 3209.9, 1: 3206.6. Samples: 1115360. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0)
++[2023-09-21 15:13:39,498][99566] Avg episode reward: [(0, '132903.044'), (1, '116397.835')]
++[2023-09-21 15:13:39,508][101035] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000001096_561152.pth...
++[2023-09-21 15:13:39,508][101034] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000001096_561152.pth...
++[2023-09-21 15:13:39,514][101035] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000000912_466944.pth
++[2023-09-21 15:13:39,516][101034] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000000912_466944.pth
++[2023-09-21 15:13:39,517][101034] Saving new best policy, reward=132903.044!
++[2023-09-21 15:13:42,911][101115] Updated weights for policy 0, policy_version 1120 (0.0014)
++[2023-09-21 15:13:42,911][101117] Updated weights for policy 1, policy_version 1120 (0.0013)
++[2023-09-21 15:13:44,497][99566] Fps is (10 sec: 6553.6, 60 sec: 6417.1, 300 sec: 6600.4). Total num frames: 1155072. Throughput: 0: 3195.6, 1: 3195.7. Samples: 1152604. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
++[2023-09-21 15:13:44,498][99566] Avg episode reward: [(0, '137104.414'), (1, '119496.691')]
++[2023-09-21 15:13:44,499][101034] Saving new best policy, reward=137104.414!
++[2023-09-21 15:13:44,499][101035] Saving new best policy, reward=119496.691!
++[2023-09-21 15:13:49,496][99566] Fps is (10 sec: 5734.5, 60 sec: 6280.5, 300 sec: 6553.6). Total num frames: 1179648. Throughput: 0: 3200.2, 1: 3200.0. Samples: 1169724. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
++[2023-09-21 15:13:49,497][99566] Avg episode reward: [(0, '137104.414'), (1, '121701.677')]
++[2023-09-21 15:13:49,526][101035] Saving new best policy, reward=121701.677!
++[2023-09-21 15:13:54,497][99566] Fps is (10 sec: 6553.6, 60 sec: 6417.0, 300 sec: 6597.9). Total num frames: 1220608. Throughput: 0: 3163.7, 1: 3159.2. Samples: 1209864. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
++[2023-09-21 15:13:54,498][99566] Avg episode reward: [(0, '142552.888'), (1, '126028.832')]
++[2023-09-21 15:13:54,508][101034] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000001192_610304.pth...
++[2023-09-21 15:13:54,508][101035] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000001192_610304.pth...
++[2023-09-21 15:13:54,515][101035] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000001000_512000.pth
++[2023-09-21 15:13:54,515][101035] Saving new best policy, reward=126028.832!
++[2023-09-21 15:13:54,516][101034] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000001000_512000.pth
++[2023-09-21 15:13:54,516][101034] Saving new best policy, reward=142552.888!
++[2023-09-21 15:13:55,395][101117] Updated weights for policy 1, policy_version 1200 (0.0013)
++[2023-09-21 15:13:55,395][101115] Updated weights for policy 0, policy_version 1200 (0.0014)
++[2023-09-21 15:13:59,496][99566] Fps is (10 sec: 7372.9, 60 sec: 6417.1, 300 sec: 6596.7). Total num frames: 1253376. Throughput: 0: 3178.4, 1: 3175.2. Samples: 1252066. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
++[2023-09-21 15:13:59,497][99566] Avg episode reward: [(0, '143172.574'), (1, '126257.348')]
++[2023-09-21 15:13:59,498][101034] Saving new best policy, reward=143172.574!
++[2023-09-21 15:13:59,498][101035] Saving new best policy, reward=126257.348!
++[2023-09-21 15:14:04,496][99566] Fps is (10 sec: 6553.7, 60 sec: 6417.1, 300 sec: 6595.6). Total num frames: 1286144. Throughput: 0: 3190.2, 1: 3193.8. Samples: 1269880. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
++[2023-09-21 15:14:04,497][99566] Avg episode reward: [(0, '143312.733'), (1, '133847.080')]
++[2023-09-21 15:14:04,498][101035] Saving new best policy, reward=133847.080!
++[2023-09-21 15:14:04,498][101034] Saving new best policy, reward=143312.733!
++[2023-09-21 15:14:07,603][101117] Updated weights for policy 1, policy_version 1280 (0.0015)
++[2023-09-21 15:14:07,604][101115] Updated weights for policy 0, policy_version 1280 (0.0013)
++[2023-09-21 15:14:09,496][99566] Fps is (10 sec: 6553.6, 60 sec: 6417.1, 300 sec: 6594.6). Total num frames: 1318912. Throughput: 0: 3247.3, 1: 3248.9. Samples: 1311276. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0)
++[2023-09-21 15:14:09,497][99566] Avg episode reward: [(0, '142024.998'), (1, '135803.021')]
++[2023-09-21 15:14:09,506][101034] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000001288_659456.pth...
++[2023-09-21 15:14:09,506][101035] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000001288_659456.pth...
++[2023-09-21 15:14:09,514][101034] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000001096_561152.pth
++[2023-09-21 15:14:09,514][101035] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000001096_561152.pth
++[2023-09-21 15:14:09,514][101035] Saving new best policy, reward=135803.021!
++[2023-09-21 15:14:14,496][99566] Fps is (10 sec: 6553.6, 60 sec: 6417.1, 300 sec: 6593.6). Total num frames: 1351680. Throughput: 0: 3252.1, 1: 3252.0. Samples: 1353318. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0)
++[2023-09-21 15:14:14,497][99566] Avg episode reward: [(0, '137567.192'), (1, '137580.324')]
++[2023-09-21 15:14:14,498][101035] Saving new best policy, reward=137580.324!
++[2023-09-21 15:14:19,496][99566] Fps is (10 sec: 6553.7, 60 sec: 6553.6, 300 sec: 6592.6). Total num frames: 1384448. Throughput: 0: 3300.0, 1: 3298.9. Samples: 1375110. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
++[2023-09-21 15:14:19,497][99566] Avg episode reward: [(0, '135167.354'), (1, '138853.897')]
++[2023-09-21 15:14:19,498][101035] Saving new best policy, reward=138853.897!
++[2023-09-21 15:14:19,579][101115] Updated weights for policy 0, policy_version 1360 (0.0013)
++[2023-09-21 15:14:19,580][101117] Updated weights for policy 1, policy_version 1360 (0.0011)
++[2023-09-21 15:14:24,497][99566] Fps is (10 sec: 5734.3, 60 sec: 6417.1, 300 sec: 6553.6). Total num frames: 1409024. Throughput: 0: 3251.1, 1: 3259.6. Samples: 1408344. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0)
++[2023-09-21 15:14:24,497][99566] Avg episode reward: [(0, '133135.888'), (1, '140760.635')]
++[2023-09-21 15:14:24,508][101035] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000001376_704512.pth...
++[2023-09-21 15:14:24,508][101034] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000001376_704512.pth...
++[2023-09-21 15:14:24,519][101034] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000001192_610304.pth
++[2023-09-21 15:14:24,519][101035] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000001192_610304.pth
++[2023-09-21 15:14:24,520][101035] Saving new best policy, reward=140760.635!
++[2023-09-21 15:14:29,497][99566] Fps is (10 sec: 5734.3, 60 sec: 6417.1, 300 sec: 6553.6). Total num frames: 1441792. Throughput: 0: 3224.6, 1: 3224.8. Samples: 1442826. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0)
++[2023-09-21 15:14:29,498][99566] Avg episode reward: [(0, '133811.659'), (1, '141653.024')]
++[2023-09-21 15:14:29,499][101035] Saving new best policy, reward=141653.024!
++[2023-09-21 15:14:33,167][101115] Updated weights for policy 0, policy_version 1440 (0.0014)
++[2023-09-21 15:14:33,167][101117] Updated weights for policy 1, policy_version 1440 (0.0011)
++[2023-09-21 15:14:34,496][99566] Fps is (10 sec: 7372.8, 60 sec: 6553.6, 300 sec: 6590.0). Total num frames: 1482752. Throughput: 0: 3281.4, 1: 3281.6. Samples: 1465058. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
++[2023-09-21 15:14:34,498][99566] Avg episode reward: [(0, '137138.699'), (1, '143246.225')]
++[2023-09-21 15:14:34,499][101035] Saving new best policy, reward=143246.225!
++[2023-09-21 15:14:39,496][99566] Fps is (10 sec: 7372.9, 60 sec: 6553.6, 300 sec: 6589.2). Total num frames: 1515520. Throughput: 0: 3298.9, 1: 3303.3. Samples: 1506962. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
++[2023-09-21 15:14:39,497][99566] Avg episode reward: [(0, '138323.470'), (1, '146247.815')]
++[2023-09-21 15:14:39,505][101035] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000001480_757760.pth...
++[2023-09-21 15:14:39,505][101034] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000001480_757760.pth...
++[2023-09-21 15:14:39,514][101035] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000001288_659456.pth
++[2023-09-21 15:14:39,515][101035] Saving new best policy, reward=146247.815!
++[2023-09-21 15:14:39,515][101034] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000001288_659456.pth
++[2023-09-21 15:14:44,496][99566] Fps is (10 sec: 6553.7, 60 sec: 6553.6, 300 sec: 6588.5). Total num frames: 1548288. Throughput: 0: 3242.7, 1: 3242.9. Samples: 1543918. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
++[2023-09-21 15:14:44,497][99566] Avg episode reward: [(0, '146316.476'), (1, '147786.818')]
++[2023-09-21 15:14:44,498][101034] Saving new best policy, reward=146316.476!
++[2023-09-21 15:14:44,498][101035] Saving new best policy, reward=147786.818!
++[2023-09-21 15:14:46,115][101115] Updated weights for policy 0, policy_version 1520 (0.0014)
++[2023-09-21 15:14:46,115][101117] Updated weights for policy 1, policy_version 1520 (0.0015)
++[2023-09-21 15:14:49,496][99566] Fps is (10 sec: 5734.4, 60 sec: 6553.6, 300 sec: 6553.6). Total num frames: 1572864. Throughput: 0: 3228.2, 1: 3221.9. Samples: 1560134. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
++[2023-09-21 15:14:49,497][99566] Avg episode reward: [(0, '148683.548'), (1, '148519.388')]
++[2023-09-21 15:14:49,498][101034] Saving new best policy, reward=148683.548!
++[2023-09-21 15:14:49,498][101035] Saving new best policy, reward=148519.388!
++[2023-09-21 15:14:54,496][99566] Fps is (10 sec: 5734.4, 60 sec: 6417.1, 300 sec: 6553.6). Total num frames: 1605632. Throughput: 0: 3169.4, 1: 3167.6. Samples: 1596444. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
++[2023-09-21 15:14:54,497][99566] Avg episode reward: [(0, '154239.879'), (1, '148233.580')]
++[2023-09-21 15:14:54,506][101035] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000001568_802816.pth...
++[2023-09-21 15:14:54,506][101034] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000001568_802816.pth...
++[2023-09-21 15:14:54,512][101035] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000001376_704512.pth
++[2023-09-21 15:14:54,514][101034] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000001376_704512.pth
++[2023-09-21 15:14:54,514][101034] Saving new best policy, reward=154239.879!
++[2023-09-21 15:14:59,496][99566] Fps is (10 sec: 5734.3, 60 sec: 6280.5, 300 sec: 6520.8). Total num frames: 1630208. Throughput: 0: 3099.2, 1: 3100.9. Samples: 1632322. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
++[2023-09-21 15:14:59,498][99566] Avg episode reward: [(0, '154239.879'), (1, '148584.617')]
++[2023-09-21 15:14:59,499][101035] Saving new best policy, reward=148584.617!
++[2023-09-21 15:14:59,981][101117] Updated weights for policy 1, policy_version 1600 (0.0013)
++[2023-09-21 15:14:59,981][101115] Updated weights for policy 0, policy_version 1600 (0.0013)
++[2023-09-21 15:15:04,496][99566] Fps is (10 sec: 5734.4, 60 sec: 6280.5, 300 sec: 6521.5). Total num frames: 1662976. Throughput: 0: 3053.0, 1: 3054.0. Samples: 1649926. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
++[2023-09-21 15:15:04,498][99566] Avg episode reward: [(0, '155604.981'), (1, '151719.185')]
++[2023-09-21 15:15:04,499][101034] Saving new best policy, reward=155604.981!
++[2023-09-21 15:15:04,499][101035] Saving new best policy, reward=151719.185!
++[2023-09-21 15:15:09,497][99566] Fps is (10 sec: 6553.5, 60 sec: 6280.5, 300 sec: 6522.1). Total num frames: 1695744. Throughput: 0: 3104.8, 1: 3104.4. Samples: 1687760. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
++[2023-09-21 15:15:09,498][99566] Avg episode reward: [(0, '155604.981'), (1, '151719.185')]
++[2023-09-21 15:15:09,508][101034] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000001656_847872.pth...
++[2023-09-21 15:15:09,508][101035] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000001656_847872.pth...
++[2023-09-21 15:15:09,514][101034] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000001480_757760.pth
++[2023-09-21 15:15:09,517][101035] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000001480_757760.pth
++[2023-09-21 15:15:12,938][101115] Updated weights for policy 0, policy_version 1680 (0.0015)
++[2023-09-21 15:15:12,938][101117] Updated weights for policy 1, policy_version 1680 (0.0013)
++[2023-09-21 15:15:14,496][99566] Fps is (10 sec: 6553.7, 60 sec: 6280.5, 300 sec: 6522.7). Total num frames: 1728512. Throughput: 0: 3141.0, 1: 3140.8. Samples: 1725508. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0)
++[2023-09-21 15:15:14,497][99566] Avg episode reward: [(0, '155183.801'), (1, '155086.429')]
++[2023-09-21 15:15:14,498][101035] Saving new best policy, reward=155086.429!
++[2023-09-21 15:15:19,497][99566] Fps is (10 sec: 5734.4, 60 sec: 6144.0, 300 sec: 6492.9). Total num frames: 1753088. Throughput: 0: 3084.1, 1: 3084.4. Samples: 1742640. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0)
++[2023-09-21 15:15:19,498][99566] Avg episode reward: [(0, '155183.801'), (1, '155086.429')]
++[2023-09-21 15:15:24,497][99566] Fps is (10 sec: 5734.3, 60 sec: 6280.5, 300 sec: 6494.0). Total num frames: 1785856. Throughput: 0: 3047.1, 1: 3042.9. Samples: 1781016. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
++[2023-09-21 15:15:24,497][99566] Avg episode reward: [(0, '156547.028'), (1, '156937.777')]
++[2023-09-21 15:15:24,507][101034] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000001744_892928.pth...
++[2023-09-21 15:15:24,507][101035] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000001744_892928.pth...
++[2023-09-21 15:15:24,514][101034] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000001568_802816.pth
++[2023-09-21 15:15:24,514][101035] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000001568_802816.pth
++[2023-09-21 15:15:24,515][101035] Saving new best policy, reward=156937.777!
++[2023-09-21 15:15:24,515][101034] Saving new best policy, reward=156547.028!
++[2023-09-21 15:15:25,925][101115] Updated weights for policy 0, policy_version 1760 (0.0016)
++[2023-09-21 15:15:25,926][101117] Updated weights for policy 1, policy_version 1760 (0.0016)
++[2023-09-21 15:15:29,496][99566] Fps is (10 sec: 6553.7, 60 sec: 6280.6, 300 sec: 6495.1). Total num frames: 1818624. Throughput: 0: 3045.6, 1: 3055.0. Samples: 1818448. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0)
++[2023-09-21 15:15:29,497][99566] Avg episode reward: [(0, '156547.028'), (1, '156937.777')]
++[2023-09-21 15:15:34,496][99566] Fps is (10 sec: 6553.7, 60 sec: 6144.0, 300 sec: 6496.1). Total num frames: 1851392. Throughput: 0: 3056.4, 1: 3058.8. Samples: 1835316. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
++[2023-09-21 15:15:34,497][99566] Avg episode reward: [(0, '157397.752'), (1, '159312.801')]
++[2023-09-21 15:15:34,498][101034] Saving new best policy, reward=157397.752!
++[2023-09-21 15:15:34,498][101035] Saving new best policy, reward=159312.801!
++[2023-09-21 15:15:39,496][99566] Fps is (10 sec: 5734.4, 60 sec: 6007.5, 300 sec: 6468.9). Total num frames: 1875968. Throughput: 0: 3089.1, 1: 3090.0. Samples: 1874502. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0)
++[2023-09-21 15:15:39,497][99566] Avg episode reward: [(0, '156903.730'), (1, '159312.801')]
++[2023-09-21 15:15:39,554][101035] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000001840_942080.pth...
++[2023-09-21 15:15:39,555][101034] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000001840_942080.pth...
++[2023-09-21 15:15:39,558][101035] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000001656_847872.pth
++[2023-09-21 15:15:39,559][101034] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000001656_847872.pth
++[2023-09-21 15:15:39,559][101117] Updated weights for policy 1, policy_version 1840 (0.0011)
++[2023-09-21 15:15:39,560][101115] Updated weights for policy 0, policy_version 1840 (0.0013)
++[2023-09-21 15:15:44,496][99566] Fps is (10 sec: 6553.5, 60 sec: 6144.0, 300 sec: 6498.1). Total num frames: 1916928. Throughput: 0: 3111.8, 1: 3110.3. Samples: 1912318. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
++[2023-09-21 15:15:44,498][99566] Avg episode reward: [(0, '157395.614'), (1, '159854.521')]
++[2023-09-21 15:15:44,499][101035] Saving new best policy, reward=159854.521!
++[2023-09-21 15:15:49,496][99566] Fps is (10 sec: 7372.8, 60 sec: 6280.5, 300 sec: 6553.6). Total num frames: 1949696. Throughput: 0: 3142.5, 1: 3145.9. Samples: 1932904. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0)
++[2023-09-21 15:15:49,497][99566] Avg episode reward: [(0, '157502.563'), (1, '159854.521')]
++[2023-09-21 15:15:49,498][101034] Saving new best policy, reward=157502.563!
++[2023-09-21 15:15:51,986][101115] Updated weights for policy 0, policy_version 1920 (0.0012)
++[2023-09-21 15:15:51,986][101117] Updated weights for policy 1, policy_version 1920 (0.0012)
++[2023-09-21 15:15:54,496][99566] Fps is (10 sec: 5734.5, 60 sec: 6144.0, 300 sec: 6498.1). Total num frames: 1974272. Throughput: 0: 3146.4, 1: 3140.3. Samples: 1970662. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
++[2023-09-21 15:15:54,497][99566] Avg episode reward: [(0, '154117.366'), (1, '160110.948')]
++[2023-09-21 15:15:54,503][101035] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000001928_987136.pth...
++[2023-09-21 15:15:54,503][101034] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000001928_987136.pth...
++[2023-09-21 15:15:54,507][101035] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000001744_892928.pth
++[2023-09-21 15:15:54,507][101035] Saving new best policy, reward=160110.948!
++[2023-09-21 15:15:54,512][101034] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000001744_892928.pth
++[2023-09-21 15:15:59,497][99566] Fps is (10 sec: 6553.5, 60 sec: 6417.1, 300 sec: 6553.6). Total num frames: 2015232. Throughput: 0: 3161.0, 1: 3160.7. Samples: 2009984. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
++[2023-09-21 15:15:59,498][99566] Avg episode reward: [(0, '152354.094'), (1, '160110.948')]
++[2023-09-21 15:16:04,496][99566] Fps is (10 sec: 6553.6, 60 sec: 6280.5, 300 sec: 6525.8). Total num frames: 2039808. Throughput: 0: 3201.8, 1: 3202.4. Samples: 2030826. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
++[2023-09-21 15:16:04,497][99566] Avg episode reward: [(0, '145305.518'), (1, '161252.171')]
++[2023-09-21 15:16:04,498][101035] Saving new best policy, reward=161252.171!
++[2023-09-21 15:16:04,810][101117] Updated weights for policy 1, policy_version 2000 (0.0015)
++[2023-09-21 15:16:04,810][101115] Updated weights for policy 0, policy_version 2000 (0.0012)
++[2023-09-21 15:16:09,497][99566] Fps is (10 sec: 5734.4, 60 sec: 6280.5, 300 sec: 6498.1). Total num frames: 2072576. Throughput: 0: 3152.8, 1: 3155.5. Samples: 2064886. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
++[2023-09-21 15:16:09,498][99566] Avg episode reward: [(0, '144668.785'), (1, '161252.171')]
++[2023-09-21 15:16:09,506][101035] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000002024_1036288.pth...
++[2023-09-21 15:16:09,506][101034] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000002024_1036288.pth...
++[2023-09-21 15:16:09,511][101035] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000001840_942080.pth
++[2023-09-21 15:16:09,513][101034] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000001840_942080.pth
++[2023-09-21 15:16:14,497][99566] Fps is (10 sec: 5734.3, 60 sec: 6144.0, 300 sec: 6470.3). Total num frames: 2097152. Throughput: 0: 3118.9, 1: 3111.8. Samples: 2098830. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0)
++[2023-09-21 15:16:14,498][99566] Avg episode reward: [(0, '143485.830'), (1, '162275.771')]
++[2023-09-21 15:16:14,500][101035] Saving new best policy, reward=162275.771!
++[2023-09-21 15:16:18,984][101115] Updated weights for policy 0, policy_version 2080 (0.0014)
++[2023-09-21 15:16:18,985][101117] Updated weights for policy 1, policy_version 2080 (0.0014)
++[2023-09-21 15:16:19,497][99566] Fps is (10 sec: 5734.4, 60 sec: 6280.5, 300 sec: 6442.5). Total num frames: 2129920. Throughput: 0: 3111.4, 1: 3107.0. Samples: 2115142. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
++[2023-09-21 15:16:19,498][99566] Avg episode reward: [(0, '141474.267'), (1, '162345.285')]
++[2023-09-21 15:16:19,499][101035] Saving new best policy, reward=162345.285!
++[2023-09-21 15:16:24,497][99566] Fps is (10 sec: 6553.6, 60 sec: 6280.5, 300 sec: 6442.5). Total num frames: 2162688. Throughput: 0: 3106.0, 1: 3115.1. Samples: 2154452. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
++[2023-09-21 15:16:24,498][99566] Avg episode reward: [(0, '140839.183'), (1, '163464.763')]
++[2023-09-21 15:16:24,507][101034] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000002112_1081344.pth...
++[2023-09-21 15:16:24,507][101035] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000002112_1081344.pth...
++[2023-09-21 15:16:24,516][101035] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000001928_987136.pth
++[2023-09-21 15:16:24,516][101034] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000001928_987136.pth
++[2023-09-21 15:16:24,517][101035] Saving new best policy, reward=163464.763!
++[2023-09-21 15:16:29,496][99566] Fps is (10 sec: 6553.7, 60 sec: 6280.5, 300 sec: 6428.6). Total num frames: 2195456. Throughput: 0: 3110.6, 1: 3111.2. Samples: 2192296. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0)
++[2023-09-21 15:16:29,497][99566] Avg episode reward: [(0, '141474.326'), (1, '163612.163')]
++[2023-09-21 15:16:29,498][101035] Saving new best policy, reward=163612.163!
++[2023-09-21 15:16:32,534][101115] Updated weights for policy 0, policy_version 2160 (0.0013)
++[2023-09-21 15:16:32,534][101117] Updated weights for policy 1, policy_version 2160 (0.0015)
++[2023-09-21 15:16:34,496][99566] Fps is (10 sec: 5734.5, 60 sec: 6144.0, 300 sec: 6387.0). Total num frames: 2220032. Throughput: 0: 3060.2, 1: 3058.9. Samples: 2208266. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
++[2023-09-21 15:16:34,497][99566] Avg episode reward: [(0, '143510.663'), (1, '161964.692')]
++[2023-09-21 15:16:39,497][99566] Fps is (10 sec: 5734.3, 60 sec: 6280.5, 300 sec: 6387.0). Total num frames: 2252800. Throughput: 0: 3029.4, 1: 3028.4. Samples: 2243264. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
++[2023-09-21 15:16:39,498][99566] Avg episode reward: [(0, '144449.158'), (1, '159709.222')]
++[2023-09-21 15:16:39,507][101034] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000002200_1126400.pth...
++[2023-09-21 15:16:39,507][101035] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000002200_1126400.pth...
++[2023-09-21 15:16:39,513][101034] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000002024_1036288.pth
++[2023-09-21 15:16:39,514][101035] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000002024_1036288.pth
++[2023-09-21 15:16:44,496][99566] Fps is (10 sec: 5734.4, 60 sec: 6007.5, 300 sec: 6359.2). Total num frames: 2277376. Throughput: 0: 2993.8, 1: 2994.1. Samples: 2279440. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
++[2023-09-21 15:16:44,497][99566] Avg episode reward: [(0, '144500.336'), (1, '159960.034')]
++[2023-09-21 15:16:46,205][101117] Updated weights for policy 1, policy_version 2240 (0.0015)
++[2023-09-21 15:16:46,206][101115] Updated weights for policy 0, policy_version 2240 (0.0013)
++[2023-09-21 15:16:49,496][99566] Fps is (10 sec: 5734.5, 60 sec: 6007.5, 300 sec: 6331.4). Total num frames: 2310144. Throughput: 0: 2960.0, 1: 2959.9. Samples: 2297222. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
++[2023-09-21 15:16:49,497][99566] Avg episode reward: [(0, '148419.870'), (1, '157559.143')]
++[2023-09-21 15:16:54,497][99566] Fps is (10 sec: 6553.4, 60 sec: 6144.0, 300 sec: 6359.2). Total num frames: 2342912. Throughput: 0: 2975.2, 1: 2973.6. Samples: 2332580. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
++[2023-09-21 15:16:54,498][99566] Avg episode reward: [(0, '148104.147'), (1, '157533.887')]
++[2023-09-21 15:16:54,507][101034] Saving ./train_dir/Standup/checkpoint_p0/checkpoint_000002288_1171456.pth...
++[2023-09-21 15:16:54,507][101035] Saving ./train_dir/Standup/checkpoint_p1/checkpoint_000002288_1171456.pth...
++[2023-09-21 15:16:54,512][101034] Removing ./train_dir/Standup/checkpoint_p0/checkpoint_000002112_1081344.pth
++[2023-09-21 15:16:54,513][101035] Removing ./train_dir/Standup/checkpoint_p1/checkpoint_000002112_1081344.pth
++[2023-09-21 15:16:59,496][99566] Fps is (10 sec: 5734.5, 60 sec: 5871.0, 300 sec: 6331.4). Total num frames: 2367488. Throughput: 0: 3009.8, 1: 3008.9. Samples: 2369672. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0)
++[2023-09-21 15:16:59,497][99566] Avg episode reward: [(0, '149878.068'), (1, '156400.338')]
++[2023-09-21 15:16:59,928][101115] Updated weights for policy 0, policy_vers
\ No newline at end of file
diff --git a/replay.mp4 b/replay.mp4
new file mode 100644
index 0000000000000000000000000000000000000000..b0a66e2aadcd2be861d04124de525b3baf7d77bf
Binary files /dev/null and b/replay.mp4 differ
diff --git a/sf_log.txt b/sf_log.txt
new file mode 100644
index 0000000000000000000000000000000000000000..ff7a040c76798adbc50b2f7e8b94f657039af982
--- /dev/null
+++ b/sf_log.txt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2a7b828f86d7d5e2833f485f9d118bc762e568516293a81d176a39b0cd047f4
+size 42224329