Huggy

Huggy.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e995a998ef774d9494f78b4760a724a9bd57269c9ee341c45abfec651801517f
+oid sha256:0741d90ecf09b8027f0c2e1ef70218322e6a2233f57081350f293f932f38484c
 size 2270373

Huggy/Huggy-199592.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f36e2b30fa8aac773ed8f10a18929df75caa5bc2b12ed8cbbc6de9252404c73
+size 2270373

Huggy/Huggy-199592.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5fc76b0f2664611aee934a4c0f6360da0ad84eb4eeb56f64f3f9b6997809f7c
+size 13505262

Huggy/Huggy-2000368.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f162b3a57f0718a375c657879a42653db50ddbfeb03472c7bdefeffdf81aebeb
-size 13505262
+oid sha256:1bd8709d4da18c985a44f86815b847f7a9cbd4fd413e99e08524257067b51632
+size 13505261

Huggy/Huggy-399953.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:975ef792d7b5716aaa6056065c7c71b1935dd41298f042282188219844fa5aa3
+size 2270373

Huggy/Huggy-399953.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:056b7e0633130a1cfaf1e52ba2c8932bb5be5d2326cbc90ed547476add46cf3c
+size 13505262

Huggy/Huggy-400174.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0741d90ecf09b8027f0c2e1ef70218322e6a2233f57081350f293f932f38484c
+size 2270373

Huggy/Huggy-400174.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e98dcc1f0a83182ddd75c2beaa6d3fe3dc17fac5e435227db8512f289dd3fb2d
+size 13505262

Huggy/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f162b3a57f0718a375c657879a42653db50ddbfeb03472c7bdefeffdf81aebeb
+oid sha256:e98dcc1f0a83182ddd75c2beaa6d3fe3dc17fac5e435227db8512f289dd3fb2d
 size 13505262

Huggy/{events.out.tfevents.1673943831.a5c5d90ae2a9.3350.0 → events.out.tfevents.1673947869.a5c5d90ae2a9.20621.0}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93eb85fefba76bfa400a2a2bee7ffce5b4c61826b4b70994d63ea136bde6fa38
-size 369888
+oid sha256:f6b837a9c3318bb44a2def6add5557bc8f8d5784d4bd9d432fd28c2abf26223e
+size 46751

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, "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": 400000, "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": true, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -36,7 +36,7 @@ behaviors:
     init_path: null
     keep_checkpoints: 15
     checkpoint_interval: 200000
-    max_steps: 2000000
+    max_steps: 400000
     time_horizon: 1000
     summary_freq: 50000
     threaded: false
@@ -66,7 +66,7 @@ checkpoint_settings:
   initialize_from: null
   load_model: false
   resume: false
-  force: false
+  force: true
   train_model: false
   inference: false
   results_dir: results

run_logs/Player-0.log

@@ -2,9 +2,6 @@ Mono path[0] = '/content/ml-agents/trained-envs-executables/linux/Huggy/Huggy_Da
 Mono config path = '/content/ml-agents/trained-envs-executables/linux/Huggy/Huggy_Data/MonoBleedingEdge/etc'
 Preloaded 'lib_burst_generated.so'
 Preloaded 'libgrpc_csharp_ext.x64.so'
-PlayerPrefs - Creating folder: /root/.config/unity3d/Hugging Face
-PlayerPrefs - Creating folder: /root/.config/unity3d/Hugging Face/Huggy
-Unable to load player prefs
 Initialize engine version: 2021.3.14f1 (eee1884e7226)
 [Subsystems] Discovering subsystems at path /content/ml-agents/trained-envs-executables/linux/Huggy/Huggy_Data/UnitySubsystems
 Forcing GfxDevice: Null
@@ -34,7 +31,7 @@ ALSA lib pcm.c:2495:(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  0.076 seconds
+- Completed reload, in  0.084 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 +75,14 @@ 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: 0.696060 ms
+UnloadTime: 0.839617 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]: 26768 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [4.0 KB-8.0 KB]: 5359 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 +90,7 @@ Memory Statistics:
     [ALLOC_TEMP_Loading.AsyncRead]
       Initial Block Size 64.0 KB
       Current Block Size 64.0 KB
-      Peak Allocated Bytes 160 B
+      Peak Allocated Bytes 136 B
       Overflow Count 0
     [ALLOC_TEMP_Loading.PreloadManager]
       Initial Block Size 256.0 KB
@@ -201,19 +198,19 @@ Memory Statistics:
       Peak Allocated Bytes 0 B
       Overflow Count 0
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 231
+  Peak main deferred allocation count 174
     [ALLOC_BUCKET]
       Large Block size 4.0 MB
       Used Block count 1
       Peak Allocated bytes 1.1 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 26769 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 5360 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 23.5 MB
+      Peak Allocated memory 21.9 MB
       Peak Large allocation bytes 16.0 MB
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [2.0 MB-4.0 MB]: 26769 frames
+      Peak usage frame count: [2.0 MB-4.0 MB]: 5360 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 2.6 MB
@@ -245,13 +242,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.1 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 26768 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 5359 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]: 26769 frames
+      Peak usage frame count: [64.0 KB-128.0 KB]: 5360 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 81.8 KB
@@ -263,13 +260,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.1 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [1.0 MB-2.0 MB]: 26768 frames, [16.0 MB-32.0 MB]: 1 frames
+      Peak usage frame count: [1.0 MB-2.0 MB]: 5359 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]: 26768 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 5359 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 +278,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.1 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 26769 frames
+      Peak usage frame count: [0-1.0 KB]: 5360 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]: 26769 frames
+      Peak usage frame count: [4.0 KB-8.0 KB]: 5360 frames
       Requested Block Size 2.0 MB
       Peak Block count 1
       Peak Allocated memory 7.3 KB

run_logs/timers.json

@@ -2,220 +2,220 @@
     "name": "root",
     "gauges": {
         "Huggy.Policy.Entropy.mean": {
-            "value": 1.4093356132507324,
-            "min": 1.4093356132507324,
-            "max": 1.4248067140579224,
-            "count": 40
+            "value": 1.4252029657363892,
+            "min": 1.419218897819519,
+            "max": 1.4252029657363892,
+            "count": 8
         },
         "Huggy.Policy.Entropy.sum": {
-            "value": 70819.1171875,
-            "min": 68459.578125,
-            "max": 75706.265625,
-            "count": 40
+            "value": 70667.265625,
+            "min": 68642.0625,
+            "max": 76098.515625,
+            "count": 8
         },
         "Huggy.Environment.EpisodeLength.mean": {
-            "value": 93.27599243856332,
-            "min": 89.35018050541517,
-            "max": 420.38655462184875,
-            "count": 40
+            "value": 159.22683706070288,
+            "min": 159.22683706070288,
+            "max": 428.64102564102564,
+            "count": 8
         },
         "Huggy.Environment.EpisodeLength.sum": {
-            "value": 49343.0,
-            "min": 49042.0,
-            "max": 50026.0,
-            "count": 40
+            "value": 49838.0,
+            "min": 49428.0,
+            "max": 50190.0,
+            "count": 8
         },
         "Huggy.Step.mean": {
-            "value": 1999618.0,
-            "min": 49788.0,
-            "max": 1999618.0,
-            "count": 40
+            "value": 399953.0,
+            "min": 49518.0,
+            "max": 399953.0,
+            "count": 8
         },
         "Huggy.Step.sum": {
-            "value": 1999618.0,
-            "min": 49788.0,
-            "max": 1999618.0,
-            "count": 40
+            "value": 399953.0,
+            "min": 49518.0,
+            "max": 399953.0,
+            "count": 8
         },
         "Huggy.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 2.4039154052734375,
-            "min": 0.006670890375971794,
-            "max": 2.436444044113159,
-            "count": 40
+            "value": 1.821832299232483,
+            "min": 0.02037733420729637,
+            "max": 1.821832299232483,
+            "count": 8
         },
         "Huggy.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 1271.6712646484375,
-            "min": 0.7871650457382202,
-            "max": 1321.90185546875,
-            "count": 40
+            "value": 570.2335205078125,
+            "min": 2.3637707233428955,
+            "max": 570.2335205078125,
+            "count": 8
         },
         "Huggy.Environment.CumulativeReward.mean": {
-            "value": 3.6863200913530214,
-            "min": 1.8317292221521928,
-            "max": 3.9667136486799115,
-            "count": 40
+            "value": 3.5618624165416146,
+            "min": 1.798727259553712,
+            "max": 3.6423750658751475,
+            "count": 8
         },
         "Huggy.Environment.CumulativeReward.sum": {
-            "value": 1950.0633283257484,
-            "min": 216.14404821395874,
-            "max": 2088.398097515106,
-            "count": 40
+            "value": 1114.8629363775253,
+            "min": 208.6523621082306,
+            "max": 1114.8629363775253,
+            "count": 8
         },
         "Huggy.Policy.ExtrinsicReward.mean": {
-            "value": 3.6863200913530214,
-            "min": 1.8317292221521928,
-            "max": 3.9667136486799115,
-            "count": 40
+            "value": 3.5618624165416146,
+            "min": 1.798727259553712,
+            "max": 3.6423750658751475,
+            "count": 8
         },
         "Huggy.Policy.ExtrinsicReward.sum": {
-            "value": 1950.0633283257484,
-            "min": 216.14404821395874,
-            "max": 2088.398097515106,
-            "count": 40
+            "value": 1114.8629363775253,
+            "min": 208.6523621082306,
+            "max": 1114.8629363775253,
+            "count": 8
         },
         "Huggy.Losses.PolicyLoss.mean": {
-            "value": 0.018546779570169748,
-            "min": 0.012451620294208017,
-            "max": 0.022340301209927325,
-            "count": 40
+            "value": 0.017299644346025562,
+            "min": 0.013667032675261403,
+            "max": 0.018863478015676567,
+            "count": 8
         },
         "Huggy.Losses.PolicyLoss.sum": {
-            "value": 0.037093559140339495,
-            "min": 0.024903240588416035,
-            "max": 0.05932169744701241,
-            "count": 40
+            "value": 0.05189893303807669,
+            "min": 0.0314464112050094,
+            "max": 0.05365531451631493,
+            "count": 8
         },
         "Huggy.Losses.ValueLoss.mean": {
-            "value": 0.053515397819379966,
-            "min": 0.023432554366687935,
-            "max": 0.061066892556846136,
-            "count": 40
+            "value": 0.05003925234907203,
+            "min": 0.022400250565260647,
+            "max": 0.05003925234907203,
+            "count": 8
         },
         "Huggy.Losses.ValueLoss.sum": {
-            "value": 0.10703079563875993,
-            "min": 0.04686510873337587,
-            "max": 0.17788641328612964,
-            "count": 40
+            "value": 0.15011775704721608,
+            "min": 0.044800501130521295,
+            "max": 0.15011775704721608,
+            "count": 8
         },
         "Huggy.Policy.LearningRate.mean": {
-            "value": 4.605998464700001e-06,
-            "min": 4.605998464700001e-06,
-            "max": 0.00029534400155199997,
-            "count": 40
+            "value": 2.0441843186083336e-05,
+            "min": 2.0441843186083336e-05,
+            "max": 0.00027656813281062495,
+            "count": 8
         },
         "Huggy.Policy.LearningRate.sum": {
-            "value": 9.211996929400001e-06,
-            "min": 9.211996929400001e-06,
-            "max": 0.0008442735185754999,
-            "count": 40
+            "value": 6.132552955825001e-05,
+            "min": 6.132552955825001e-05,
+            "max": 0.0006197670934110001,
+            "count": 8
         },
         "Huggy.Policy.Epsilon.mean": {
-            "value": 0.10153529999999998,
-            "min": 0.10153529999999998,
-            "max": 0.19844799999999999,
-            "count": 40
+            "value": 0.10681391666666668,
+            "min": 0.10681391666666668,
+            "max": 0.192189375,
+            "count": 8
         },
         "Huggy.Policy.Epsilon.sum": {
-            "value": 0.20307059999999996,
-            "min": 0.20307059999999996,
-            "max": 0.5814245000000001,
-            "count": 40
+            "value": 0.32044175,
+            "min": 0.23946599999999996,
+            "max": 0.5065889999999998,
+            "count": 8
         },
         "Huggy.Policy.Beta.mean": {
-            "value": 8.661147000000003e-05,
-            "min": 8.661147000000003e-05,
-            "max": 0.0049225551999999995,
-            "count": 40
+            "value": 0.0003500144416666668,
+            "min": 0.0003500144416666668,
+            "max": 0.004610249812499999,
+            "count": 8
         },
         "Huggy.Policy.Beta.sum": {
-            "value": 0.00017322294000000007,
-            "min": 0.00017322294000000007,
-            "max": 0.014073082549999998,
-            "count": 40
+            "value": 0.0010500433250000003,
+            "min": 0.0010500433250000003,
+            "max": 0.0103387911,
+            "count": 8
         },
         "Huggy.IsTraining.mean": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 40
+            "count": 8
         },
         "Huggy.IsTraining.sum": {
             "value": 1.0,
             "min": 1.0,
             "max": 1.0,
-            "count": 40
+            "count": 8
         }
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1673943824",
+        "start_time_seconds": "1673947865",
         "python_version": "3.8.16 (default, Dec  7 2022, 01:12:13) \n[GCC 7.5.0]",
-        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy --no-graphics",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy --no-graphics --force",
         "mlagents_version": "0.29.0.dev0",
         "mlagents_envs_version": "0.29.0.dev0",
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "1.8.1+cu102",
         "numpy_version": "1.21.6",
-        "end_time_seconds": "1673946020"
+        "end_time_seconds": "1673948302"
     },
-    "total": 2195.185496661,
+    "total": 436.48621700700005,
     "count": 1,
-    "self": 0.3921560129997488,
+    "self": 0.38081205900016357,
     "children": {
         "run_training.setup": {
-            "total": 0.12222509499997614,
+            "total": 0.11837205600022571,
             "count": 1,
-            "self": 0.12222509499997614
+            "self": 0.11837205600022571
         },
         "TrainerController.start_learning": {
-            "total": 2194.671115553,
+            "total": 435.98703289199966,
             "count": 1,
-            "self": 3.8328237450632514,
+            "self": 0.7436031739207465,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 9.870770168000035,
+                    "total": 8.279316346999622,
                     "count": 1,
-                    "self": 9.870770168000035
+                    "self": 8.279316346999622
                 },
                 "TrainerController.advance": {
-                    "total": 2180.856620777937,
-                    "count": 232085,
-                    "self": 4.079740249993392,
+                    "total": 426.84714204007923,
+                    "count": 45484,
+                    "self": 0.7677341570033605,
                     "children": {
                         "env_step": {
-                            "total": 1715.980779497002,
-                            "count": 232085,
-                            "self": 1443.2369940590688,
+                            "total": 340.0658723360257,
+                            "count": 45484,
+                            "self": 285.3313452381917,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 270.2192730579693,
-                                    "count": 232085,
-                                    "self": 14.21302231299751,
+                                    "total": 54.21449395592754,
+                                    "count": 45484,
+                                    "self": 2.7995539607145474,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 256.0062507449718,
-                                            "count": 223068,
-                                            "self": 64.7235170529533,
+                                            "total": 51.41493999521299,
+                                            "count": 44666,
+                                            "self": 13.080594255178767,
                                             "children": {
                                                 "TorchPolicy.sample_actions": {
-                                                    "total": 191.2827336920185,
-                                                    "count": 223068,
-                                                    "self": 191.2827336920185
+                                                    "total": 38.33434574003422,
+                                                    "count": 44666,
+                                                    "self": 38.33434574003422
                                                 }
                                             }
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 2.524512379963994,
-                                    "count": 232085,
+                                    "total": 0.5200331419064241,
+                                    "count": 45484,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 2185.0898922280307,
-                                            "count": 232085,
+                                            "total": 434.3037274259632,
+                                            "count": 45484,
                                             "is_parallel": true,
-                                            "self": 999.6232234109398,
+                                            "self": 200.62583475385236,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -224,48 +224,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.0019205119999696763,
+                                                            "total": 0.0009342739995190641,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0003227499998956773,
+                                                            "self": 0.00042177400064247195,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.001597762000073999,
+                                                                    "total": 0.0005124999988765921,
                                                                     "count": 2,
                                                                     "is_parallel": true,
-                                                                    "self": 0.001597762000073999
+                                                                    "self": 0.0005124999988765921
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.02694881100001112,
+                                                            "total": 0.02840852899953461,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0002689680000003136,
+                                                            "self": 0.00027490399861562764,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.0001748420000922124,
+                                                                    "total": 0.00017962000038096448,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0001748420000922124
+                                                                    "self": 0.00017962000038096448
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.025652585999978328,
+                                                                    "total": 0.02723288700053672,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.025652585999978328
+                                                                    "self": 0.02723288700053672
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.0008524149999402653,
+                                                                    "total": 0.0007211180000012973,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00024084799997581285,
+                                                                    "self": 0.0002513660001568496,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0006115669999644524,
+                                                                            "total": 0.0004697519998444477,
                                                                             "count": 2,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0006115669999644524
+                                                                            "self": 0.0004697519998444477
                                                                         }
                                                                     }
                                                                 }
@@ -274,34 +274,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 1185.466668817091,
-                                                    "count": 232084,
+                                                    "total": 233.67789267211083,
+                                                    "count": 45483,
                                                     "is_parallel": true,
-                                                    "self": 34.791976631116995,
+                                                    "self": 6.932290804947115,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 77.07831680696597,
-                                                            "count": 232084,
+                                                            "total": 15.129244987075253,
+                                                            "count": 45483,
                                                             "is_parallel": true,
-                                                            "self": 77.07831680696597
+                                                            "self": 15.129244987075253
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 978.3224682350087,
-                                                            "count": 232084,
+                                                            "total": 192.62869070598026,
+                                                            "count": 45483,
                                                             "is_parallel": true,
-                                                            "self": 978.3224682350087
+                                                            "self": 192.62869070598026
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 95.27390714399917,
-                                                            "count": 232084,
+                                                            "total": 18.9876661741082,
+                                                            "count": 45483,
                                                             "is_parallel": true,
-                                                            "self": 37.86030128810796,
+                                                            "self": 7.483658854186615,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 57.413605855891205,
-                                                                    "count": 464168,
+                                                                    "total": 11.504007319921584,
+                                                                    "count": 90966,
                                                                     "is_parallel": true,
-                                                                    "self": 57.413605855891205
+                                                                    "self": 11.504007319921584
                                                                 }
                                                             }
                                                         }
@@ -314,31 +314,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 460.7961010309416,
-                            "count": 232085,
-                            "self": 6.145839495909399,
+                            "total": 86.0135355470502,
+                            "count": 45484,
+                            "self": 1.2433898461340505,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 146.21852574003344,
-                                    "count": 232085,
-                                    "self": 145.04477514803364,
+                                    "total": 24.466726267917693,
+                                    "count": 45484,
+                                    "self": 24.21626170291802,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 1.1737505919998057,
-                                            "count": 10,
-                                            "self": 1.1737505919998057
+                                            "total": 0.2504645649996746,
+                                            "count": 2,
+                                            "self": 0.2504645649996746
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 308.43173579499876,
-                                    "count": 96,
-                                    "self": 255.87299282900142,
+                                    "total": 60.30341943299845,
+                                    "count": 19,
+                                    "self": 49.86701095598983,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 52.55874296599734,
-                                            "count": 2880,
-                                            "self": 52.55874296599734
+                                            "total": 10.436408477008627,
+                                            "count": 570,
+                                            "self": 10.436408477008627
                                         }
                                     }
                                 }
@@ -347,19 +347,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 7.609996828250587e-07,
+                    "total": 8.420001904596575e-07,
                     "count": 1,
-                    "self": 7.609996828250587e-07
+                    "self": 8.420001904596575e-07
                 },
                 "TrainerController._save_models": {
-                    "total": 0.11090010099997016,
+                    "total": 0.1169704889998684,
                     "count": 1,
-                    "self": 0.0020463549999476527,
+                    "self": 0.0027403579997553607,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.10885374600002251,
+                            "total": 0.11423013100011303,
                             "count": 1,
-                            "self": 0.10885374600002251
+                            "self": 0.11423013100011303
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,112 +2,40 @@
     "Huggy": {
         "checkpoints": [
             {
-                "steps": 199833,
-                "file_path": "results/Huggy/Huggy/Huggy-199833.onnx",
-                "reward": 3.4141748198441095,
-                "creation_time": 1673944045.0324757,
+                "steps": 199592,
+                "file_path": "results/Huggy/Huggy/Huggy-199592.onnx",
+                "reward": 3.1660569958519518,
+                "creation_time": 1673948086.8228912,
                 "auxillary_file_paths": [
-                    "results/Huggy/Huggy/Huggy-199833.pt"
+                    "results/Huggy/Huggy/Huggy-199592.pt"
                 ]
             },
             {
-                "steps": 399955,
-                "file_path": "results/Huggy/Huggy/Huggy-399955.onnx",
-                "reward": 3.7999993142947344,
-                "creation_time": 1673944262.1892455,
+                "steps": 399953,
+                "file_path": "results/Huggy/Huggy/Huggy-399953.onnx",
+                "reward": 3.3712833102156474,
+                "creation_time": 1673948301.884643,
                 "auxillary_file_paths": [
-                    "results/Huggy/Huggy/Huggy-399955.pt"
+                    "results/Huggy/Huggy/Huggy-399953.pt"
                 ]
             },
             {
-                "steps": 599906,
-                "file_path": "results/Huggy/Huggy/Huggy-599906.onnx",
-                "reward": 4.196664037375615,
-                "creation_time": 1673944482.8404667,
+                "steps": 400174,
+                "file_path": "results/Huggy/Huggy/Huggy-400174.onnx",
+                "reward": 3.427222240538824,
+                "creation_time": 1673948302.009988,
                 "auxillary_file_paths": [
-                    "results/Huggy/Huggy/Huggy-599906.pt"
-                ]
-            },
-            {
-                "steps": 799920,
-                "file_path": "results/Huggy/Huggy/Huggy-799920.onnx",
-                "reward": 4.034789663630646,
-                "creation_time": 1673944700.3877366,
-                "auxillary_file_paths": [
-                    "results/Huggy/Huggy/Huggy-799920.pt"
-                ]
-            },
-            {
-                "steps": 999995,
-                "file_path": "results/Huggy/Huggy/Huggy-999995.onnx",
-                "reward": 3.674981947949058,
-                "creation_time": 1673944921.0213263,
-                "auxillary_file_paths": [
-                    "results/Huggy/Huggy/Huggy-999995.pt"
-                ]
-            },
-            {
-                "steps": 1199944,
-                "file_path": "results/Huggy/Huggy/Huggy-1199944.onnx",
-                "reward": 3.28529596489829,
-                "creation_time": 1673945140.9888778,
-                "auxillary_file_paths": [
-                    "results/Huggy/Huggy/Huggy-1199944.pt"
-                ]
-            },
-            {
-                "steps": 1399350,
-                "file_path": "results/Huggy/Huggy/Huggy-1399350.onnx",
-                "reward": 3.643525254143321,
-                "creation_time": 1673945358.2235773,
-                "auxillary_file_paths": [
-                    "results/Huggy/Huggy/Huggy-1399350.pt"
-                ]
-            },
-            {
-                "steps": 1599924,
-                "file_path": "results/Huggy/Huggy/Huggy-1599924.onnx",
-                "reward": 4.02940552704262,
-                "creation_time": 1673945581.9807956,
-                "auxillary_file_paths": [
-                    "results/Huggy/Huggy/Huggy-1599924.pt"
-                ]
-            },
-            {
-                "steps": 1799990,
-                "file_path": "results/Huggy/Huggy/Huggy-1799990.onnx",
-                "reward": 3.731682716144456,
-                "creation_time": 1673945801.2542992,
-                "auxillary_file_paths": [
-                    "results/Huggy/Huggy/Huggy-1799990.pt"
-                ]
-            },
-            {
-                "steps": 1999618,
-                "file_path": "results/Huggy/Huggy/Huggy-1999618.onnx",
-                "reward": 3.8227199737230935,
-                "creation_time": 1673946019.4852185,
-                "auxillary_file_paths": [
-                    "results/Huggy/Huggy/Huggy-1999618.pt"
-                ]
-            },
-            {
-                "steps": 2000368,
-                "file_path": "results/Huggy/Huggy/Huggy-2000368.onnx",
-                "reward": 3.785416722561406,
-                "creation_time": 1673946019.6256707,
-                "auxillary_file_paths": [
-                    "results/Huggy/Huggy/Huggy-2000368.pt"
+                    "results/Huggy/Huggy/Huggy-400174.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 2000368,
+            "steps": 400174,
             "file_path": "results/Huggy/Huggy.onnx",
-            "reward": 3.785416722561406,
-            "creation_time": 1673946019.6256707,
+            "reward": 3.427222240538824,
+            "creation_time": 1673948302.009988,
             "auxillary_file_paths": [
-                "results/Huggy/Huggy/Huggy-2000368.pt"
+                "results/Huggy/Huggy/Huggy-400174.pt"
             ]
         }
     },