Huggy

Huggy.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b92309003666901febd79a3ee11fc28af357e454f96b38edaefc073ceb3ca20
-size 2270373
+oid sha256:44d133ce7c4f9f017a38c5302950f3a14f0c682e4e85bb86b95f3b2d2044f504
+size 2273983

Huggy/Huggy-1199991.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5768dea29d3b84817158429d315fb0cddcff1f800fdbae4a06bb3752b117729
+size 2273983

Huggy/Huggy-1199991.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a418157b2e5c5954787ce1761669c35d8b0509c05cc281ac25106ad2d2a2e632
+size 13509028

Huggy/Huggy-1399993.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8693dc08d59fc769fa25053495b8dd3f5681f6d3c19bae1450a3bce9feaea6bd
+size 2273983

Huggy/Huggy-1399993.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31da4a6577c5e5b4b5cd8243f01f85ebd4003e2268fa38b91fc3ebdb30a74ed1
+size 13509028

Huggy/Huggy-1599947.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1181c93bc7313fc05219df54b85510eb2201be736558d6d15fa3c02960b1ff25
+size 2273983

Huggy/Huggy-1599947.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f417bde7e613677d798fcd09f307cb9f94d0ada16debbb31a5a3980ee54957c
+size 13509028

Huggy/Huggy-1799952.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9975c62ba1fd424fa92ce3a3e79e98363c3f3e0b051da5f39d88797a2a67c78e
+size 2273983

Huggy/Huggy-1799952.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4b0e0f7e6912eeb3d03cb5bcbacd1f76e5ac2861b6167eda893fb0c4fd7e907
+size 13509028

Huggy/Huggy-199642.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3316d26a703c540de84581a7d6b98f3052d501cacb3c22592f4903cf24e4ca25
+size 2273983

Huggy/Huggy-199642.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3534bb96536d6616fcfbcd27aaa8496e34e6359bf2c03b933791400bdad28a3d
+size 13508945

Huggy/Huggy-1999979.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50740e75a60166a8f63325cb78137cd29ce3adbbe444f02a4c050c17473a876d
+size 2273983

Huggy/Huggy-1999979.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55e9214787f8e68cd8b1c4ec88b95858db9e7a2c0fae7bc5e8a9d39edce573ac
+size 13509028

Huggy/Huggy-2000044.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44d133ce7c4f9f017a38c5302950f3a14f0c682e4e85bb86b95f3b2d2044f504
+size 2273983

Huggy/Huggy-2000044.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a1fd8c07ea96154c92adbc9b22cfb5828a97ff72a6ea5b5570e32291fc36516
+size 13509028

Huggy/Huggy-399995.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f8d6e7dc9630259bdc14893945598ff71abd7561fa79b8d305282890f82f239
+size 2273983

Huggy/Huggy-399995.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:448a23eddcb4a9858f1b6833624d64fa286aa11ae41b849165af0ac84d2e621b
+size 13508945

Huggy/Huggy-599953.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5152242934991ea4ddee10976eb8d240e7dba844c96835fba83fc3576b08e894
+size 2273983

Huggy/Huggy-599953.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5bc8cfb8bbe6696456e299df22a8c6f8a11ac9fcaa66d17c29e5062d81c00be4
+size 13508945

Huggy/Huggy-799938.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5231ced0b9246ed3b7b5df70836006a61f741e04ccc69e09f451f8acbbbf6f0
+size 2273983

Huggy/Huggy-799938.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dcad4664ae88a6fbbd22a42aa735db0de6dabfacff2e95793fab33c369ed3584
+size 13508945

Huggy/Huggy-999969.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:289eda62ecf90d8b95d5792ffe326ad9365cf9d5a590d9652ca12732983f5b11
+size 2273983

Huggy/Huggy-999969.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6f7a8baa25ee0195f3044af959e8442c57e5e02e757ac435fa7e4d48714c8ae
+size 13508945

Huggy/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c9021d2a2cbab60aa966dbaab73eb57481610fb41f0efb0633c4e334aff40be
-size 13505250
+oid sha256:654ef81d97c0282175a2426e4fe22c55fef3b66dc5b598a539b6c8101e2632ab
+size 13508779

Huggy/events.out.tfevents.1696951108.8742e47e82d7.5733.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57395899053b0df18a8fa210a7f0f5531962349890b4d2b90901c3d8557d189a
+size 246433

README.md

@@ -1,31 +1,35 @@
-
 ---
-      tags:
-      - unity-ml-agents
-      - ml-agents
-      - deep-reinforcement-learning
-      - reinforcement-learning
-      - ML-Agents-Huggy
-      library_name: ml-agents
+library_name: ml-agents
+tags:
+- Huggy
+- deep-reinforcement-learning
+- reinforcement-learning
+- ML-Agents-Huggy
 ---
-    
+
   # **ppo** Agent playing **Huggy**
-  This is a trained model of a **ppo** agent playing **Huggy** using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
-  
+  This is a trained model of a **ppo** agent playing **Huggy**
+  using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
+
   ## Usage (with ML-Agents)
-  The Documentation: https://github.com/huggingface/ml-agents#get-started
-  We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
+  The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/
 
+  We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
+  - A *short tutorial* where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your
+  browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction
+  - A *longer tutorial* to understand how works ML-Agents:
+  https://huggingface.co/learn/deep-rl-course/unit5/introduction
 
   ### Resume the training
-  ```
+  ```bash
   mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume
   ```
+
   ### Watch your Agent play
-  You can watch your agent **playing directly in your browser:**.
-  
-  1. Go to https://huggingface.co/spaces/unity/ML-Agents-Huggy
-  2. Step 1: Write your model_id: micheljperez/ppo-Huggy
+  You can watch your agent **playing directly in your browser**
+
+  1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity
+  2. Step 1: Find your model_id: micheljperez/ppo-Huggy
   3. Step 2: Select your *.nn /*.onnx file
   4. Click on Watch the agent play 👀
   

config.json

@@ -1 +1 @@
-{"default_settings": null, "behaviors": {"Huggy": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 2048, "buffer_size": 20480, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "network_settings": {"normalize": true, "hidden_units": 512, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.995, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 15, "checkpoint_interval": 200000, "max_steps": 2000000, "time_horizon": 1000, "summary_freq": 50000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./trained-envs-executables/linux/Huggy/Huggy", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true}, "environment_parameters": null, "checkpoint_settings": {"run_id": "Huggy", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
+{"default_settings": null, "behaviors": {"Huggy": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 2048, "buffer_size": 20480, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 200000, "network_settings": {"normalize": true, "hidden_units": 512, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.995, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 15, "even_checkpoints": false, "max_steps": 2000000, "time_horizon": 1000, "summary_freq": 50000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./trained-envs-executables/linux/Huggy/Huggy", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true}, "environment_parameters": null, "checkpoint_settings": {"run_id": "Huggy", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -10,9 +10,11 @@ behaviors:
       epsilon: 0.2
       lambd: 0.95
       num_epoch: 3
+      shared_critic: false
       learning_rate_schedule: linear
       beta_schedule: linear
       epsilon_schedule: linear
+    checkpoint_interval: 200000
     network_settings:
       normalize: true
       hidden_units: 512
@@ -35,7 +37,7 @@ behaviors:
           deterministic: false
     init_path: null
     keep_checkpoints: 15
-    checkpoint_interval: 200000
+    even_checkpoints: false
     max_steps: 2000000
     time_horizon: 1000
     summary_freq: 50000
@@ -48,6 +50,7 @@ env_settings:
   base_port: 5005
   num_envs: 1
   num_areas: 1
+  timeout_wait: 60
   seed: -1
   max_lifetime_restarts: 10
   restarts_rate_limit_n: 1

run_logs/Player-0.log

@@ -13,28 +13,28 @@ NullGfxDevice:
     Version:  NULL 1.0 [1.0]
     Renderer: Null Device
     Vendor:   Unity Technologies
-ALSA lib confmisc.c:767:(parse_card) cannot find card '0'
-ALSA lib conf.c:4732:(_snd_config_evaluate) function snd_func_card_driver returned error: No such file or directory
-ALSA lib confmisc.c:392:(snd_func_concat) error evaluating strings
-ALSA lib conf.c:4732:(_snd_config_evaluate) function snd_func_concat returned error: No such file or directory
-ALSA lib confmisc.c:1246:(snd_func_refer) error evaluating name
-ALSA lib conf.c:4732:(_snd_config_evaluate) function snd_func_refer returned error: No such file or directory
-ALSA lib conf.c:5220:(snd_config_expand) Evaluate error: No such file or directory
-ALSA lib pcm.c:2642:(snd_pcm_open_noupdate) Unknown PCM default
+ALSA lib confmisc.c:855:(parse_card) cannot find card '0'
+ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_card_inum returned error: No such file or directory
+ALSA lib confmisc.c:422:(snd_func_concat) error evaluating strings
+ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_concat returned error: No such file or directory
+ALSA lib confmisc.c:1334:(snd_func_refer) error evaluating name
+ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_refer returned error: No such file or directory
+ALSA lib conf.c:5701:(snd_config_expand) Evaluate error: No such file or directory
+ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM default
 FMOD failed to initialize the output device.: "Error initializing output device. " (60)
 Forced to initialize FMOD to to the device driver's system output rate 48000, this may impact performance and/or give inconsistent experiences compared to selected sample rate 48000
-ALSA lib confmisc.c:767:(parse_card) cannot find card '0'
-ALSA lib conf.c:4732:(_snd_config_evaluate) function snd_func_card_driver returned error: No such file or directory
-ALSA lib confmisc.c:392:(snd_func_concat) error evaluating strings
-ALSA lib conf.c:4732:(_snd_config_evaluate) function snd_func_concat returned error: No such file or directory
-ALSA lib confmisc.c:1246:(snd_func_refer) error evaluating name
-ALSA lib conf.c:4732:(_snd_config_evaluate) function snd_func_refer returned error: No such file or directory
-ALSA lib conf.c:5220:(snd_config_expand) Evaluate error: No such file or directory
-ALSA lib pcm.c:2642:(snd_pcm_open_noupdate) Unknown PCM default
+ALSA lib confmisc.c:855:(parse_card) cannot find card '0'
+ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_card_inum returned error: No such file or directory
+ALSA lib confmisc.c:422:(snd_func_concat) error evaluating strings
+ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_concat returned error: No such file or directory
+ALSA lib confmisc.c:1334:(snd_func_refer) error evaluating name
+ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_refer returned error: No such file or directory
+ALSA lib conf.c:5701:(snd_config_expand) Evaluate error: No such file or directory
+ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM default
 FMOD failed to initialize the output device.: "Error initializing output device. " (60)
 FMOD initialized on nosound output
 Begin MonoManager ReloadAssembly
-- Completed reload, in  0.090 seconds
+- Completed reload, in  0.087 seconds
 ERROR: Shader Hidden/Universal Render Pipeline/Blit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 ERROR: Shader Hidden/Universal Render Pipeline/CopyDepth shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 ERROR: Shader Hidden/Universal Render Pipeline/ScreenSpaceShadows shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
@@ -78,14 +78,14 @@ ERROR: Shader Universal Render Pipeline/Lit shader is not supported on this GPU
 WARNING: Shader Unsupported: 'Universal Render Pipeline/Lit' - All subshaders removed
 WARNING: Shader Did you use #pragma only_renderers and omit this platform?
 WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
-UnloadTime: 0.798761 ms
+UnloadTime: 0.697067 ms
 requesting resize 84 x 84
 Setting up 1 worker threads for Enlighten.
 Memory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [4.0 KB-8.0 KB]: 26752 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [4.0 KB-8.0 KB]: 26753 frames, [2.0 MB-4.0 MB]: 1 frames
       Initial Block Size 4.0 MB
       Current Block Size 4.0 MB
       Peak Allocated Bytes 3.6 MB
@@ -93,7 +93,7 @@ Memory Statistics:
     [ALLOC_TEMP_Loading.AsyncRead]
       Initial Block Size 64.0 KB
       Current Block Size 64.0 KB
-      Peak Allocated Bytes 192 B
+      Peak Allocated Bytes 144 B
       Overflow Count 0
     [ALLOC_TEMP_Loading.PreloadManager]
       Initial Block Size 256.0 KB
@@ -201,22 +201,22 @@ Memory Statistics:
       Peak Allocated Bytes 0 B
       Overflow Count 0
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 108
+  Peak main deferred allocation count 313
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
       Peak Allocated bytes 1.4 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 26753 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 26754 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 23.7 MB
+      Peak Allocated memory 24.2 MB
       Peak Large allocation bytes 16.0 MB
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [2.0 MB-4.0 MB]: 26753 frames
+      Peak usage frame count: [1.0 MB-2.0 MB]: 26753 frames, [2.0 MB-4.0 MB]: 1 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 2.7 MB
+      Peak Allocated memory 2.3 MB
       Peak Large allocation bytes 0 B
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -245,13 +245,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.4 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 26752 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 26753 frames, [64.0 KB-128.0 KB]: 1 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 65.6 KB
       Peak Large allocation bytes 0 B
     [ALLOC_GFX_THREAD]
-      Peak usage frame count: [64.0 KB-128.0 KB]: 26753 frames
+      Peak usage frame count: [64.0 KB-128.0 KB]: 26754 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 81.8 KB
@@ -263,13 +263,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.4 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [1.0 MB-2.0 MB]: 26752 frames, [16.0 MB-32.0 MB]: 1 frames
+      Peak usage frame count: [1.0 MB-2.0 MB]: 26753 frames, [16.0 MB-32.0 MB]: 1 frames
       Requested Block Size 4.0 MB
       Peak Block count 2
       Peak Allocated memory 30.6 MB
       Peak Large allocation bytes 24.9 MB
     [ALLOC_CACHEOBJECTS_THREAD]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 26752 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 26753 frames, [2.0 MB-4.0 MB]: 1 frames
       Requested Block Size 4.0 MB
       Peak Block count 1
       Peak Allocated memory 2.6 MB
@@ -281,13 +281,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.4 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 26753 frames
+      Peak usage frame count: [0-1.0 KB]: 26754 frames
       Requested Block Size 2.0 MB
       Peak Block count 1
       Peak Allocated memory 1.0 KB
       Peak Large allocation bytes 0 B
     [ALLOC_TYPETREE_THREAD]
-      Peak usage frame count: [4.0 KB-8.0 KB]: 26753 frames
+      Peak usage frame count: [4.0 KB-8.0 KB]: 26754 frames
       Requested Block Size 2.0 MB
       Peak Block count 1
       Peak Allocated memory 7.3 KB

run_logs/timers.json

@@ -2,135 +2,135 @@
     "name": "root",
     "gauges": {
         "Huggy.Policy.Entropy.mean": {
-            "value": 1.4014652967453003,
-            "min": 1.4014652967453003,
-            "max": 1.427881121635437,
+            "value": 1.403228998184204,
+            "min": 1.403228998184204,
+            "max": 1.4289727210998535,
             "count": 40
         },
         "Huggy.Policy.Entropy.sum": {
-            "value": 70493.703125,
-            "min": 69124.515625,
-            "max": 77285.28125,
+            "value": 70002.8828125,
+            "min": 69019.6796875,
+            "max": 77445.3203125,
             "count": 40
         },
         "Huggy.Environment.EpisodeLength.mean": {
-            "value": 76.02153846153846,
-            "min": 71.00287769784173,
-            "max": 412.26446280991735,
+            "value": 69.04341736694678,
+            "min": 69.04341736694678,
+            "max": 391.3828125,
             "count": 40
         },
         "Huggy.Environment.EpisodeLength.sum": {
-            "value": 49414.0,
-            "min": 49283.0,
-            "max": 50157.0,
+            "value": 49297.0,
+            "min": 48641.0,
+            "max": 50097.0,
             "count": 40
         },
         "Huggy.Step.mean": {
-            "value": 1999982.0,
-            "min": 49663.0,
-            "max": 1999982.0,
+            "value": 1999979.0,
+            "min": 49617.0,
+            "max": 1999979.0,
             "count": 40
         },
         "Huggy.Step.sum": {
-            "value": 1999982.0,
-            "min": 49663.0,
-            "max": 1999982.0,
+            "value": 1999979.0,
+            "min": 49617.0,
+            "max": 1999979.0,
             "count": 40
         },
         "Huggy.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 2.491381883621216,
-            "min": 0.05321761593222618,
-            "max": 2.535512924194336,
+            "value": 2.529850721359253,
+            "min": 0.09101362526416779,
+            "max": 2.562394857406616,
             "count": 40
         },
         "Huggy.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 1619.398193359375,
-            "min": 6.386114120483398,
-            "max": 1732.599365234375,
+            "value": 1806.3133544921875,
+            "min": 11.558730125427246,
+            "max": 1806.3133544921875,
             "count": 40
         },
         "Huggy.Environment.CumulativeReward.mean": {
-            "value": 3.859221896850146,
-            "min": 2.0314500451087953,
-            "max": 4.025593738311277,
+            "value": 3.9115888817804536,
+            "min": 1.9256142039937296,
+            "max": 4.080791214987032,
             "count": 40
         },
         "Huggy.Environment.CumulativeReward.sum": {
-            "value": 2508.4942329525948,
-            "min": 243.77400541305542,
-            "max": 2689.615422785282,
+            "value": 2792.8744615912437,
+            "min": 244.55300390720367,
+            "max": 2823.9075207710266,
             "count": 40
         },
         "Huggy.Policy.ExtrinsicReward.mean": {
-            "value": 3.859221896850146,
-            "min": 2.0314500451087953,
-            "max": 4.025593738311277,
+            "value": 3.9115888817804536,
+            "min": 1.9256142039937296,
+            "max": 4.080791214987032,
             "count": 40
         },
         "Huggy.Policy.ExtrinsicReward.sum": {
-            "value": 2508.4942329525948,
-            "min": 243.77400541305542,
-            "max": 2689.615422785282,
+            "value": 2792.8744615912437,
+            "min": 244.55300390720367,
+            "max": 2823.9075207710266,
             "count": 40
         },
         "Huggy.Losses.PolicyLoss.mean": {
-            "value": 0.015274040847240636,
-            "min": 0.014337154147647703,
-            "max": 0.022562845268597205,
+            "value": 0.017578730093858515,
+            "min": 0.013388852636368635,
+            "max": 0.020930114932222445,
             "count": 40
         },
         "Huggy.Losses.PolicyLoss.sum": {
-            "value": 0.04582212254172191,
-            "min": 0.030435713407496224,
-            "max": 0.05985438954157871,
+            "value": 0.05273619028157554,
+            "min": 0.02677770527273727,
+            "max": 0.059735836560139435,
             "count": 40
         },
         "Huggy.Losses.ValueLoss.mean": {
-            "value": 0.05871611125767231,
-            "min": 0.02263389518484473,
-            "max": 0.06464658478895824,
+            "value": 0.0627057037419743,
+            "min": 0.023507859713087477,
+            "max": 0.0627057037419743,
             "count": 40
         },
         "Huggy.Losses.ValueLoss.sum": {
-            "value": 0.17614833377301692,
-            "min": 0.04526779036968946,
-            "max": 0.17614833377301692,
+            "value": 0.1881171112259229,
+            "min": 0.047015719426174954,
+            "max": 0.1881171112259229,
             "count": 40
         },
         "Huggy.Policy.LearningRate.mean": {
-            "value": 3.9006486998166695e-06,
-            "min": 3.9006486998166695e-06,
-            "max": 0.00029530425156524994,
+            "value": 3.958048680683332e-06,
+            "min": 3.958048680683332e-06,
+            "max": 0.000295338826553725,
             "count": 40
         },
         "Huggy.Policy.LearningRate.sum": {
-            "value": 1.1701946099450008e-05,
-            "min": 1.1701946099450008e-05,
-            "max": 0.0008438560687146499,
+            "value": 1.1874146042049995e-05,
+            "min": 1.1874146042049995e-05,
+            "max": 0.0008438790187069998,
             "count": 40
         },
         "Huggy.Policy.Epsilon.mean": {
-            "value": 0.10130018333333335,
-            "min": 0.10130018333333335,
-            "max": 0.19843475000000005,
+            "value": 0.10131931666666667,
+            "min": 0.10131931666666667,
+            "max": 0.19844627499999995,
             "count": 40
         },
         "Huggy.Policy.Epsilon.sum": {
-            "value": 0.30390055000000005,
-            "min": 0.20773025,
-            "max": 0.5812853500000001,
+            "value": 0.30395795000000003,
+            "min": 0.20777125000000002,
+            "max": 0.581293,
             "count": 40
         },
         "Huggy.Policy.Beta.mean": {
-            "value": 7.487914833333338e-05,
-            "min": 7.487914833333338e-05,
-            "max": 0.004921894025,
+            "value": 7.583390166666665e-05,
+            "min": 7.583390166666665e-05,
+            "max": 0.0049224691224999985,
             "count": 40
         },
         "Huggy.Policy.Beta.sum": {
-            "value": 0.00022463744500000014,
-            "min": 0.00022463744500000014,
-            "max": 0.014066138965000002,
+            "value": 0.00022750170499999996,
+            "min": 0.00022750170499999996,
+            "max": 0.014066520700000001,
             "count": 40
         },
         "Huggy.IsTraining.mean": {
@@ -148,74 +148,67 @@
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1677608027",
-        "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]",
+        "start_time_seconds": "1696951107",
+        "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [GCC 11.4.0]",
         "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy --no-graphics",
-        "mlagents_version": "0.29.0.dev0",
-        "mlagents_envs_version": "0.29.0.dev0",
+        "mlagents_version": "1.1.0.dev0",
+        "mlagents_envs_version": "1.1.0.dev0",
         "communication_protocol_version": "1.5.0",
-        "pytorch_version": "1.8.1+cu102",
-        "numpy_version": "1.22.4",
-        "end_time_seconds": "1677610434"
+        "pytorch_version": "2.0.1+cu118",
+        "numpy_version": "1.21.2",
+        "end_time_seconds": "1696953531"
     },
-    "total": 2406.9226794270003,
+    "total": 2423.802595407,
     "count": 1,
-    "self": 0.4445138000000952,
+    "self": 0.43636329399987517,
     "children": {
         "run_training.setup": {
-            "total": 0.12011708199997884,
+            "total": 0.04781813099998544,
             "count": 1,
-            "self": 0.12011708199997884
+            "self": 0.04781813099998544
         },
         "TrainerController.start_learning": {
-            "total": 2406.358048545,
+            "total": 2423.318413982,
             "count": 1,
-            "self": 4.258204464015307,
+            "self": 4.413656039996113,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 10.087536569999997,
+                    "total": 8.021537040000112,
                     "count": 1,
-                    "self": 10.087536569999997
+                    "self": 8.021537040000112
                 },
                 "TrainerController.advance": {
-                    "total": 2391.8980703499847,
-                    "count": 233484,
-                    "self": 4.460104079784287,
+                    "total": 2410.784739200004,
+                    "count": 233890,
+                    "self": 4.560497000141822,
                     "children": {
                         "env_step": {
-                            "total": 1858.03990899415,
-                            "count": 233484,
-                            "self": 1560.4666971691663,
+                            "total": 1846.5977701539052,
+                            "count": 233890,
+                            "self": 1531.5861030200733,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 294.76814985495935,
-                                    "count": 233484,
-                                    "self": 16.276135231838225,
+                                    "total": 312.20134225886727,
+                                    "count": 233890,
+                                    "self": 16.499976662820472,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 278.4920146231211,
-                                            "count": 222942,
-                                            "self": 70.52789814602488,
-                                            "children": {
-                                                "TorchPolicy.sample_actions": {
-                                                    "total": 207.96411647709624,
-                                                    "count": 222942,
-                                                    "self": 207.96411647709624
-                                                }
-                                            }
+                                            "total": 295.7013655960468,
+                                            "count": 222945,
+                                            "self": 295.7013655960468
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 2.805061970024326,
-                                    "count": 233484,
+                                    "total": 2.8103248749646355,
+                                    "count": 233890,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 2397.999344846901,
-                                            "count": 233484,
+                                            "total": 2415.992196399164,
+                                            "count": 233890,
                                             "is_parallel": true,
-                                            "self": 1129.1211434049176,
+                                            "self": 1171.2062316571828,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -224,48 +217,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.0009612540000034642,
+                                                            "total": 0.000846455000100832,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0003112280001005274,
+                                                            "self": 0.00024190499993892445,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0006500259999029367,
+                                                                    "total": 0.0006045500001619075,
                                                                     "count": 2,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0006500259999029367
+                                                                    "self": 0.0006045500001619075
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.028854474999889135,
+                                                            "total": 0.02694922000000588,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.000299982999877102,
+                                                            "self": 0.0002893549999498646,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.00021390400002019305,
+                                                                    "total": 0.00023497400002270297,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00021390400002019305
+                                                                    "self": 0.00023497400002270297
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.027621409999937896,
+                                                                    "total": 0.025645232999977452,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.027621409999937896
+                                                                    "self": 0.025645232999977452
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0007191780000539438,
+                                                                    "total": 0.0007796580000558606,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0002631540000948007,
+                                                                    "self": 0.00023580899983244308,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0004560239999591431,
+                                                                            "total": 0.0005438490002234175,
                                                                             "count": 2,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0004560239999591431
+                                                                            "self": 0.0005438490002234175
                                                                         }
                                                                     }
                                                                 }
@@ -274,34 +267,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 1268.8782014419833,
-                                                    "count": 233483,
+                                                    "total": 1244.7859647419814,
+                                                    "count": 233889,
                                                     "is_parallel": true,
-                                                    "self": 39.23732533685984,
+                                                    "self": 40.70974441420867,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 80.49768388703205,
-                                                            "count": 233483,
+                                                            "total": 82.11496812792711,
+                                                            "count": 233889,
                                                             "is_parallel": true,
-                                                            "self": 80.49768388703205
+                                                            "self": 82.11496812792711
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 1056.9094856630145,
-                                                            "count": 233483,
+                                                            "total": 1022.8206100708637,
+                                                            "count": 233889,
                                                             "is_parallel": true,
-                                                            "self": 1056.9094856630145
+                                                            "self": 1022.8206100708637
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 92.23370655507688,
-                                                            "count": 233483,
+                                                            "total": 99.14064212898188,
+                                                            "count": 233889,
                                                             "is_parallel": true,
-                                                            "self": 37.41109621402484,
+                                                            "self": 35.78881004893856,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 54.82261034105204,
-                                                                    "count": 466966,
+                                                                    "total": 63.35183208004332,
+                                                                    "count": 467778,
                                                                     "is_parallel": true,
-                                                                    "self": 54.82261034105204
+                                                                    "self": 63.35183208004332
                                                                 }
                                                             }
                                                         }
@@ -314,31 +307,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 529.3980572760504,
-                            "count": 233484,
-                            "self": 6.3370501321692245,
+                            "total": 559.6264720459569,
+                            "count": 233890,
+                            "self": 6.173125561966344,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 167.7143627108842,
-                                    "count": 233484,
-                                    "self": 166.50670340888382,
+                                    "total": 152.44454011298876,
+                                    "count": 233890,
+                                    "self": 151.1038633239889,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 1.2076593020003656,
+                                            "total": 1.3406767889998719,
                                             "count": 10,
-                                            "self": 1.2076593020003656
+                                            "self": 1.3406767889998719
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 355.346644432997,
+                                    "total": 401.0088063710018,
                                     "count": 97,
-                                    "self": 297.7006297049936,
+                                    "self": 339.93564413300624,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 57.646014728003365,
+                                            "total": 61.073162237995575,
                                             "count": 2910,
-                                            "self": 57.646014728003365
+                                            "self": 61.073162237995575
                                         }
                                     }
                                 }
@@ -347,19 +340,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 8.340002750628628e-07,
+                    "total": 9.7599968285067e-07,
                     "count": 1,
-                    "self": 8.340002750628628e-07
+                    "self": 9.7599968285067e-07
                 },
                 "TrainerController._save_models": {
-                    "total": 0.11423632700007147,
+                    "total": 0.09848072600016167,
                     "count": 1,
-                    "self": 0.002008240000122896,
+                    "self": 0.001958457000000635,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.11222808699994857,
+                            "total": 0.09652226900016103,
                             "count": 1,
-                            "self": 0.11222808699994857
+                            "self": 0.09652226900016103
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,118 +2,118 @@
     "Huggy": {
         "checkpoints": [
             {
-                "steps": 199839,
-                "file_path": "results/Huggy/Huggy/Huggy-199839.onnx",
-                "reward": 3.267228267648641,
-                "creation_time": 1677608273.439319,
+                "steps": 199642,
+                "file_path": "results/Huggy/Huggy/Huggy-199642.onnx",
+                "reward": 3.3408852869814094,
+                "creation_time": 1696951351.066657,
                 "auxillary_file_paths": [
-                    "results/Huggy/Huggy/Huggy-199839.pt"
+                    "results/Huggy/Huggy/Huggy-199642.pt"
                 ]
             },
             {
-                "steps": 399856,
-                "file_path": "results/Huggy/Huggy/Huggy-399856.onnx",
-                "reward": 4.03699004650116,
-                "creation_time": 1677608514.0762005,
+                "steps": 399995,
+                "file_path": "results/Huggy/Huggy/Huggy-399995.onnx",
+                "reward": 3.8581132473129975,
+                "creation_time": 1696951588.3978288,
                 "auxillary_file_paths": [
-                    "results/Huggy/Huggy/Huggy-399856.pt"
+                    "results/Huggy/Huggy/Huggy-399995.pt"
                 ]
             },
             {
-                "steps": 599866,
-                "file_path": "results/Huggy/Huggy/Huggy-599866.onnx",
-                "reward": 3.9803427024321123,
-                "creation_time": 1677608755.036398,
+                "steps": 599953,
+                "file_path": "results/Huggy/Huggy/Huggy-599953.onnx",
+                "reward": 3.8165545654296875,
+                "creation_time": 1696951829.5304844,
                 "auxillary_file_paths": [
-                    "results/Huggy/Huggy/Huggy-599866.pt"
+                    "results/Huggy/Huggy/Huggy-599953.pt"
                 ]
             },
             {
-                "steps": 799958,
-                "file_path": "results/Huggy/Huggy/Huggy-799958.onnx",
-                "reward": 3.97494601169411,
-                "creation_time": 1677608993.1662903,
+                "steps": 799938,
+                "file_path": "results/Huggy/Huggy/Huggy-799938.onnx",
+                "reward": 3.9907866439548147,
+                "creation_time": 1696952068.3049042,
                 "auxillary_file_paths": [
-                    "results/Huggy/Huggy/Huggy-799958.pt"
+                    "results/Huggy/Huggy/Huggy-799938.pt"
                 ]
             },
             {
-                "steps": 999993,
-                "file_path": "results/Huggy/Huggy/Huggy-999993.onnx",
-                "reward": 4.005736847718556,
-                "creation_time": 1677609233.2743168,
+                "steps": 999969,
+                "file_path": "results/Huggy/Huggy/Huggy-999969.onnx",
+                "reward": 3.9267869674798215,
+                "creation_time": 1696952309.4688065,
                 "auxillary_file_paths": [
-                    "results/Huggy/Huggy/Huggy-999993.pt"
+                    "results/Huggy/Huggy/Huggy-999969.pt"
                 ]
             },
             {
-                "steps": 1199965,
-                "file_path": "results/Huggy/Huggy/Huggy-1199965.onnx",
-                "reward": 3.940881059613339,
-                "creation_time": 1677609475.2061155,
+                "steps": 1199991,
+                "file_path": "results/Huggy/Huggy/Huggy-1199991.onnx",
+                "reward": 4.183989282264266,
+                "creation_time": 1696952553.7304053,
                 "auxillary_file_paths": [
-                    "results/Huggy/Huggy/Huggy-1199965.pt"
+                    "results/Huggy/Huggy/Huggy-1199991.pt"
                 ]
             },
             {
-                "steps": 1399969,
-                "file_path": "results/Huggy/Huggy/Huggy-1399969.onnx",
-                "reward": 3.925844192504883,
-                "creation_time": 1677609715.3567898,
+                "steps": 1399993,
+                "file_path": "results/Huggy/Huggy/Huggy-1399993.onnx",
+                "reward": 3.392833543320497,
+                "creation_time": 1696952800.2592373,
                 "auxillary_file_paths": [
-                    "results/Huggy/Huggy/Huggy-1399969.pt"
+                    "results/Huggy/Huggy/Huggy-1399993.pt"
                 ]
             },
             {
-                "steps": 1599902,
-                "file_path": "results/Huggy/Huggy/Huggy-1599902.onnx",
-                "reward": 3.940251687027159,
-                "creation_time": 1677609952.1858134,
+                "steps": 1599947,
+                "file_path": "results/Huggy/Huggy/Huggy-1599947.onnx",
+                "reward": 3.9308800111340068,
+                "creation_time": 1696953041.6891658,
                 "auxillary_file_paths": [
-                    "results/Huggy/Huggy/Huggy-1599902.pt"
+                    "results/Huggy/Huggy/Huggy-1599947.pt"
                 ]
             },
             {
-                "steps": 1799949,
-                "file_path": "results/Huggy/Huggy/Huggy-1799949.onnx",
-                "reward": 3.8176064431667327,
-                "creation_time": 1677610194.7683113,
+                "steps": 1799952,
+                "file_path": "results/Huggy/Huggy/Huggy-1799952.onnx",
+                "reward": 3.958530896546825,
+                "creation_time": 1696953286.6476877,
                 "auxillary_file_paths": [
-                    "results/Huggy/Huggy/Huggy-1799949.pt"
+                    "results/Huggy/Huggy/Huggy-1799952.pt"
                 ]
             },
             {
-                "steps": 1999982,
-                "file_path": "results/Huggy/Huggy/Huggy-1999982.onnx",
-                "reward": 3.5897830616344106,
-                "creation_time": 1677610433.8496847,
+                "steps": 1999979,
+                "file_path": "results/Huggy/Huggy/Huggy-1999979.onnx",
+                "reward": 4.117876688171836,
+                "creation_time": 1696953531.0502884,
                 "auxillary_file_paths": [
-                    "results/Huggy/Huggy/Huggy-1999982.pt"
+                    "results/Huggy/Huggy/Huggy-1999979.pt"
                 ]
             },
             {
-                "steps": 2000065,
-                "file_path": "results/Huggy/Huggy/Huggy-2000065.onnx",
-                "reward": 3.5975924760867386,
-                "creation_time": 1677610433.9677625,
+                "steps": 2000044,
+                "file_path": "results/Huggy/Huggy/Huggy-2000044.onnx",
+                "reward": 4.121083632458088,
+                "creation_time": 1696953531.1514134,
                 "auxillary_file_paths": [
-                    "results/Huggy/Huggy/Huggy-2000065.pt"
+                    "results/Huggy/Huggy/Huggy-2000044.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 2000065,
+            "steps": 2000044,
             "file_path": "results/Huggy/Huggy.onnx",
-            "reward": 3.5975924760867386,
-            "creation_time": 1677610433.9677625,
+            "reward": 4.121083632458088,
+            "creation_time": 1696953531.1514134,
             "auxillary_file_paths": [
-                "results/Huggy/Huggy/Huggy-2000065.pt"
+                "results/Huggy/Huggy/Huggy-2000044.pt"
             ]
         }
     },
     "metadata": {
         "stats_format_version": "0.3.0",
-        "mlagents_version": "0.29.0.dev0",
-        "torch_version": "1.8.1+cu102"
+        "mlagents_version": "1.1.0.dev0",
+        "torch_version": "2.0.1+cu118"
     }
 }