Test training huggy.

Huggy.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c50219d6e29b697a7601795126ce0c3b22dc80ce2ead599108cab15a7c43631c
-size 2270373
+oid sha256:1e16430337efe3f3d4c7ec7cf1cab6d742442a67afad7ecc94e002140ab11435
+size 616163

Huggy/Huggy-1199989.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28d075d807d22e16210c2fc79e4e88168a78aeb5f89fdbc191f061f1aa85fc45
+size 616163

Huggy/Huggy-1199989.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d59a92cadeb4a3fad3b9c09a574d4ff57f15fe4fa557263f3bd5c28e3baf134
+size 3622497

Huggy/Huggy-1399938.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8fa422759216cbe829588cc3cecbdc3099d694dbb52fd58b0ccfdf7de6ca311
+size 616163

Huggy/Huggy-1399938.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:651d409a427221a162f9ebe1a878a4f4557f1235b9e89249baa08be9684bd792
+size 3622497

Huggy/Huggy-1599893.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ecd8e7251e8f6f2f3ce5bd6fcdd31db5d62fc129e59a6874a6179d16639ea786
+size 616163

Huggy/Huggy-1599893.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7af270a58a4aeef123a4cf90fac7de50b263b1371c12d1355378982439817f98
+size 3622497

Huggy/Huggy-1799962.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f727be70957eb3437743887a2aff8727d04efb7246f48be0b0bb96b655c623e6
+size 616163

Huggy/Huggy-1799962.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:693b61331aa3e2457fd19febedc8800f02c94324526d0fcd7028b1e7d7038694
+size 3622497

Huggy/Huggy-199918.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1fb18790f0d6b2822b846d86ae60d56cec08fd24eb3a755aa9e1fd24e2a988ed
+size 616163

Huggy/Huggy-199918.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a7d7070ce2593390c45ad5f5f6dcca31a0bb472ed17d4b5910201f51e062a78
+size 3622412

Huggy/Huggy-1999981.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2691b39280a3276ed71d38c3bc14078d72937622897dd90d020ce11ff77592c9
+size 616163

Huggy/Huggy-1999981.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ec2a5e0303f26f8e5034c47e7b986d4c5ad7778736673e68ee663308d0f1367
+size 3622497

Huggy/Huggy-2000026.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e16430337efe3f3d4c7ec7cf1cab6d742442a67afad7ecc94e002140ab11435
+size 616163

Huggy/Huggy-2000026.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45d829173c3d58db59a9d82776b96338680bb69afdab761bcb9884996b2a66fa
+size 3622497

Huggy/Huggy-399925.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1494727d764af911c79ed1c98bfdb6a27f3155c400a1e567737fd36f98f91b5f
+size 616163

Huggy/Huggy-399925.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:635df97df3ea75bd650ad4b153d09989cec230c34931198e01b5d110ef4f1b57
+size 3622412

Huggy/Huggy-599920.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10db810cf11b76935378aafddeff8605f1d8adc43859ada6eaa4f13ae844bdb2
+size 616163

Huggy/Huggy-599920.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c74836f8e8b92247ca9fb46321b312087cf36e94e13264724f218556a5de3b0d
+size 3622412

Huggy/Huggy-799940.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eaf8c2982463393999b9d6209c0af36227ecead3c58d9a67adad692f61523bcf
+size 616163

Huggy/Huggy-799940.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75a966fffa8215672a4522592c0f79e827037c8649b0bca2cc9a3b4a2d46361e
+size 3622412

Huggy/Huggy-999983.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f856b6b307236dab8242f21f61ba7943e3f189186d124da772d7161aad649c4
+size 616163

Huggy/Huggy-999983.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d65a84c8131bb46799e6a069b82045c1852a21d969cd5507a53e33c1948232e
+size 3622412

Huggy/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1144651243d19e99ce5e44f0a7b4f2a621d1db9900af8677a2213af3ff6104be
-size 13505250
+oid sha256:0da50269719c8dba4b65d910e4df7d1437912c22fd302a648f6c3e152185116b
+size 3622242

Huggy/events.out.tfevents.1736535485.veldin.105539.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:328d5b193e3051f7b6c8d94b7b9cda434887ce5b2006e57e61fe5368179309b1
+size 341489

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: Lpremier/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: Lpremier/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": 256, "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": "./envs/Huggy/Huggy.x86_64", "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, "no_graphics_monitor": false}, "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

@@ -10,12 +10,14 @@ 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
+      hidden_units: 256
       num_layers: 3
       vis_encode_type: simple
       memory: null
@@ -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
@@ -43,11 +45,12 @@ behaviors:
     self_play: null
     behavioral_cloning: null
 env_settings:
-  env_path: ./trained-envs-executables/linux/Huggy/Huggy
+  env_path: ./envs/Huggy/Huggy.x86_64
   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
@@ -60,6 +63,7 @@ engine_settings:
   target_frame_rate: -1
   capture_frame_rate: 60
   no_graphics: true
+  no_graphics_monitor: false
 environment_parameters: null
 checkpoint_settings:
   run_id: Huggy

run_logs/Player-0.log

@@ -1,40 +1,17 @@
-Mono path[0] = '/content/ml-agents/trained-envs-executables/linux/Huggy/Huggy_Data/Managed'
-Mono config path = '/content/ml-agents/trained-envs-executables/linux/Huggy/Huggy_Data/MonoBleedingEdge/etc'
+Mono path[0] = '/home/lucien/Workspace/deep-rl-hugging-face/units/unit_1_bonus/envs/Huggy/Huggy_Data/Managed'
+Mono config path = '/home/lucien/Workspace/deep-rl-hugging-face/units/unit_1_bonus/envs/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
+[Subsystems] Discovering subsystems at path /home/lucien/Workspace/deep-rl-hugging-face/units/unit_1_bonus/envs/Huggy/Huggy_Data/UnitySubsystems
 Forcing GfxDevice: Null
 GfxDevice: creating device client; threaded=0; jobified=0
 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
-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
-FMOD failed to initialize the output device.: "Error initializing output device. " (60)
-FMOD initialized on nosound output
 Begin MonoManager ReloadAssembly
-- Completed reload, in  0.084 seconds
+- Completed reload, in  0.144 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 +55,14 @@ 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: 0.780936 ms
+UnloadTime: 1.208127 ms
 requesting resize 84 x 84
-Setting up 1 worker threads for Enlighten.
+Setting up 6 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]: 26746 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [4.0 KB-8.0 KB]: 26761 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
@@ -93,21 +70,21 @@ Memory Statistics:
     [ALLOC_TEMP_Loading.AsyncRead]
       Initial Block Size 64.0 KB
       Current Block Size 64.0 KB
-      Peak Allocated Bytes 136 B
+      Peak Allocated Bytes 240 B
       Overflow Count 0
     [ALLOC_TEMP_Loading.PreloadManager]
       Initial Block Size 256.0 KB
       Current Block Size 296.0 KB
-      Peak Allocated Bytes 211.5 KB
+      Peak Allocated Bytes 211.6 KB
       Overflow Count 4
     [ALLOC_TEMP_Background Job.Worker 8]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 9]
-      Initial Block Size 32.0 KB
-      Current Block Size 32.0 KB
+    [ALLOC_TEMP_Job.Worker 6]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
     [ALLOC_TEMP_Job.Worker 0]
@@ -120,6 +97,16 @@ Memory Statistics:
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 9]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 5]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
     [ALLOC_TEMP_Background Job.Worker 14]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
@@ -130,12 +117,22 @@ Memory Statistics:
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 4]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 3]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
     [ALLOC_TEMP_Background Job.Worker 12]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_EnlightenWorker]
+    [ALLOC_TEMP_EnlightenWorker] x 6
       Initial Block Size 64.0 KB
       Current Block Size 64.0 KB
       Peak Allocated Bytes 0 B
@@ -160,7 +157,7 @@ Memory Statistics:
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_AssetGarbageCollectorHelper]
+    [ALLOC_TEMP_AssetGarbageCollectorHelper] x 11
       Initial Block Size 64.0 KB
       Current Block Size 64.0 KB
       Peak Allocated Bytes 0 B
@@ -170,21 +167,51 @@ Memory Statistics:
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 9]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
     [ALLOC_TEMP_Background Job.Worker 13]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 11]
+    [ALLOC_TEMP_Job.Worker 8]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 7]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 1]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 2]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 3]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Background Job.Worker 3]
+    [ALLOC_TEMP_Background Job.Worker 11]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 10]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
     [ALLOC_TEMP_Background Job.Worker 0]
       Initial Block Size 32.0 KB
       Current Block Size 32.0 KB
@@ -201,19 +228,19 @@ Memory Statistics:
       Peak Allocated Bytes 0 B
       Overflow Count 0
 [ALLOC_DEFAULT] Dual Thread Allocator
-  Peak main deferred allocation count 307
+  Peak main deferred allocation count 38
     [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]: 26747 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 26762 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 23.5 MB
+      Peak Allocated memory 24.1 MB
       Peak Large allocation bytes 16.0 MB
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [2.0 MB-4.0 MB]: 26747 frames
+      Peak usage frame count: [2.0 MB-4.0 MB]: 26762 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 2.5 MB
@@ -245,13 +272,13 @@ 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]: 26746 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 26761 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]: 26747 frames
+      Peak usage frame count: [64.0 KB-128.0 KB]: 26762 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 81.8 KB
@@ -263,13 +290,13 @@ 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]: 26746 frames, [16.0 MB-32.0 MB]: 1 frames
+      Peak usage frame count: [1.0 MB-2.0 MB]: 26761 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]: 26746 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 26761 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 +308,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 1.4 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 26747 frames
+      Peak usage frame count: [0-1.0 KB]: 26762 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]: 26747 frames
+      Peak usage frame count: [4.0 KB-8.0 KB]: 26762 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": 1.405726432800293,
-            "min": 1.405726432800293,
-            "max": 1.4263414144515991,
+            "value": 1.419002652168274,
+            "min": 1.419002652168274,
+            "max": 1.4336585998535156,
             "count": 40
         },
         "Huggy.Policy.Entropy.sum": {
-            "value": 69340.265625,
-            "min": 69020.09375,
-            "max": 78233.6328125,
+            "value": 70015.0078125,
+            "min": 69644.9765625,
+            "max": 77138.2265625,
             "count": 40
         },
         "Huggy.Environment.EpisodeLength.mean": {
-            "value": 84.90721649484536,
-            "min": 78.81789137380191,
-            "max": 382.39694656488547,
+            "value": 100.04444444444445,
+            "min": 80.8983606557377,
+            "max": 393.74015748031496,
             "count": 40
         },
         "Huggy.Environment.EpisodeLength.sum": {
-            "value": 49416.0,
-            "min": 49245.0,
-            "max": 50094.0,
+            "value": 49522.0,
+            "min": 49085.0,
+            "max": 50123.0,
             "count": 40
         },
         "Huggy.Step.mean": {
-            "value": 1999951.0,
-            "min": 49588.0,
-            "max": 1999951.0,
+            "value": 1999981.0,
+            "min": 49720.0,
+            "max": 1999981.0,
             "count": 40
         },
         "Huggy.Step.sum": {
-            "value": 1999951.0,
-            "min": 49588.0,
-            "max": 1999951.0,
+            "value": 1999981.0,
+            "min": 49720.0,
+            "max": 1999981.0,
             "count": 40
         },
         "Huggy.Policy.ExtrinsicValueEstimate.mean": {
-            "value": 2.438652992248535,
-            "min": 0.014100411906838417,
-            "max": 2.4592137336730957,
+            "value": 2.345958709716797,
+            "min": 0.026557682082057,
+            "max": 2.4552905559539795,
             "count": 40
         },
         "Huggy.Policy.ExtrinsicValueEstimate.sum": {
-            "value": 1419.2960205078125,
-            "min": 1.8330535888671875,
-            "max": 1518.3631591796875,
+            "value": 1161.24951171875,
+            "min": 3.3462679386138916,
+            "max": 1458.442626953125,
             "count": 40
         },
         "Huggy.Environment.CumulativeReward.mean": {
-            "value": 3.8545736519946265,
-            "min": 1.7930911387388522,
-            "max": 4.0001908488707105,
+            "value": 3.426805532821501,
+            "min": 1.855288378776066,
+            "max": 3.8521291624729326,
             "count": 40
         },
         "Huggy.Environment.CumulativeReward.sum": {
-            "value": 2243.3618654608727,
-            "min": 233.1018480360508,
-            "max": 2408.9233707785606,
+            "value": 1696.268738746643,
+            "min": 233.7663357257843,
+            "max": 2277.3595340251923,
             "count": 40
         },
         "Huggy.Policy.ExtrinsicReward.mean": {
-            "value": 3.8545736519946265,
-            "min": 1.7930911387388522,
-            "max": 4.0001908488707105,
+            "value": 3.426805532821501,
+            "min": 1.855288378776066,
+            "max": 3.8521291624729326,
             "count": 40
         },
         "Huggy.Policy.ExtrinsicReward.sum": {
-            "value": 2243.3618654608727,
-            "min": 233.1018480360508,
-            "max": 2408.9233707785606,
+            "value": 1696.268738746643,
+            "min": 233.7663357257843,
+            "max": 2277.3595340251923,
             "count": 40
         },
         "Huggy.Losses.PolicyLoss.mean": {
-            "value": 0.018762715171841488,
-            "min": 0.013664930166366199,
-            "max": 0.019786716312470767,
+            "value": 0.01618660277971584,
+            "min": 0.013231132179013609,
+            "max": 0.019874131717369892,
             "count": 40
         },
         "Huggy.Losses.PolicyLoss.sum": {
-            "value": 0.05628814551552447,
-            "min": 0.027329860332732398,
-            "max": 0.0580980720076089,
+            "value": 0.04855980833914752,
+            "min": 0.026462264358027218,
+            "max": 0.05543710958590964,
             "count": 40
         },
         "Huggy.Losses.ValueLoss.mean": {
-            "value": 0.0572844391895665,
-            "min": 0.023200623008112112,
-            "max": 0.05991571222742398,
+            "value": 0.055792152881622314,
+            "min": 0.0228065116951863,
+            "max": 0.06833089163733853,
             "count": 40
         },
         "Huggy.Losses.ValueLoss.sum": {
-            "value": 0.1718533175686995,
-            "min": 0.046401246016224224,
-            "max": 0.17854056159655254,
+            "value": 0.16737645864486694,
+            "min": 0.0456130233903726,
+            "max": 0.20499267491201562,
             "count": 40
         },
         "Huggy.Policy.LearningRate.mean": {
-            "value": 3.7098487634166665e-06,
-            "min": 3.7098487634166665e-06,
-            "max": 0.0002953389015537,
+            "value": 3.772898742399987e-06,
+            "min": 3.772898742399987e-06,
+            "max": 0.0002953864515378499,
             "count": 40
         },
         "Huggy.Policy.LearningRate.sum": {
-            "value": 1.112954629025e-05,
-            "min": 1.112954629025e-05,
-            "max": 0.0008441758686080499,
+            "value": 1.131869622719996e-05,
+            "min": 1.131869622719996e-05,
+            "max": 0.0008441346186217997,
             "count": 40
         },
         "Huggy.Policy.Epsilon.mean": {
-            "value": 0.10123658333333334,
-            "min": 0.10123658333333334,
-            "max": 0.19844630000000002,
+            "value": 0.1012576,
+            "min": 0.1012576,
+            "max": 0.19846214999999995,
             "count": 40
         },
         "Huggy.Policy.Epsilon.sum": {
-            "value": 0.30370975,
-            "min": 0.20760709999999993,
-            "max": 0.58139195,
+            "value": 0.3037728,
+            "min": 0.20765795000000004,
+            "max": 0.5813781999999998,
             "count": 40
         },
         "Huggy.Policy.Beta.mean": {
-            "value": 7.170550833333337e-05,
-            "min": 7.170550833333337e-05,
-            "max": 0.004922470369999998,
+            "value": 7.275423999999982e-05,
+            "min": 7.275423999999982e-05,
+            "max": 0.004923261284999999,
             "count": 40
         },
         "Huggy.Policy.Beta.sum": {
-            "value": 0.0002151165250000001,
-            "min": 0.0002151165250000001,
-            "max": 0.014071458304999996,
+            "value": 0.00021826271999999945,
+            "min": 0.00021826271999999945,
+            "max": 0.01407077218,
             "count": 40
         },
         "Huggy.IsTraining.mean": {
@@ -148,74 +148,67 @@
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1678010773",
-        "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]",
-        "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",
+        "start_time_seconds": "1736535484",
+        "python_version": "3.11.2 (main, Sep 14 2024, 03:00:30) [GCC 12.2.0]",
+        "command_line_arguments": "/home/lucien/Workspace/deep-rl-hugging-face/.venv/bin/mlagents-learn ./Huggy.yaml --env=./envs/Huggy/Huggy.x86_64 --run-id=Huggy --no-graphics",
+        "mlagents_version": "1.2.0.dev0",
+        "mlagents_envs_version": "1.2.0.dev0",
         "communication_protocol_version": "1.5.0",
-        "pytorch_version": "1.8.1+cu102",
-        "numpy_version": "1.22.4",
-        "end_time_seconds": "1678013330"
+        "pytorch_version": "2.5.1+cpu",
+        "numpy_version": "1.23.5",
+        "end_time_seconds": "1736539714"
     },
-    "total": 2556.9234070820003,
+    "total": 4229.777110309005,
     "count": 1,
-    "self": 0.44735435299980963,
+    "self": 0.2690794260124676,
     "children": {
         "run_training.setup": {
-            "total": 0.10933865300000889,
+            "total": 0.017177205998450518,
             "count": 1,
-            "self": 0.10933865300000889
+            "self": 0.017177205998450518
         },
         "TrainerController.start_learning": {
-            "total": 2556.3667140760003,
+            "total": 4229.490853676994,
             "count": 1,
-            "self": 4.4882349459512625,
+            "self": 3.1951357410580385,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 9.055713848999972,
+                    "total": 1.757877448995714,
                     "count": 1,
-                    "self": 9.055713848999972
+                    "self": 1.757877448995714
                 },
                 "TrainerController.advance": {
-                    "total": 2542.708416552049,
-                    "count": 232571,
-                    "self": 5.007388583979264,
+                    "total": 4224.50203892494,
+                    "count": 232622,
+                    "self": 2.6429820155608468,
                     "children": {
                         "env_step": {
-                            "total": 1992.7663725089785,
-                            "count": 232571,
-                            "self": 1661.9360057240442,
+                            "total": 3802.9597281361494,
+                            "count": 232622,
+                            "self": 3606.446267847874,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 327.8137563659159,
-                                    "count": 232571,
-                                    "self": 17.136968068879924,
+                                    "total": 194.3614402624371,
+                                    "count": 232622,
+                                    "self": 13.616157618060242,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 310.67678829703596,
-                                            "count": 222890,
-                                            "self": 76.58572337603255,
-                                            "children": {
-                                                "TorchPolicy.sample_actions": {
-                                                    "total": 234.0910649210034,
-                                                    "count": 222890,
-                                                    "self": 234.0910649210034
-                                                }
-                                            }
+                                            "total": 180.74528264437686,
+                                            "count": 223017,
+                                            "self": 180.74528264437686
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 3.016610419018434,
-                                    "count": 232571,
+                                    "total": 2.152020025838283,
+                                    "count": 232622,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 2547.5337124109574,
-                                            "count": 232571,
+                                            "total": 4222.5241382354,
+                                            "count": 232622,
                                             "is_parallel": true,
-                                            "self": 1201.6221207699393,
+                                            "self": 871.2681235457858,
                                             "children": {
                                                 "run_training.setup": {
                                                     "total": 0.0,
@@ -224,48 +217,48 @@
                                                     "self": 0.0,
                                                     "children": {
                                                         "steps_from_proto": {
-                                                            "total": 0.0009447439999803464,
+                                                            "total": 0.000538847001735121,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.00035215299999435956,
+                                                            "self": 0.00012182000500615686,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 0.0005925909999859869,
+                                                                    "total": 0.00041702699672896415,
                                                                     "count": 2,
                                                                     "is_parallel": true,
-                                                                    "self": 0.0005925909999859869
+                                                                    "self": 0.00041702699672896415
                                                                 }
                                                             }
                                                         },
                                                         "UnityEnvironment.step": {
-                                                            "total": 0.03221907500000043,
+                                                            "total": 0.029837320995284244,
                                                             "count": 1,
                                                             "is_parallel": true,
-                                                            "self": 0.0003044010000508024,
+                                                            "self": 0.0001549629814689979,
                                                             "children": {
                                                                 "UnityEnvironment._generate_step_input": {
-                                                                    "total": 0.00020616999995581864,
+                                                                    "total": 0.0003500400052871555,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.00020616999995581864
+                                                                    "self": 0.0003500400052871555
                                                                 },
                                                                 "communicator.exchange": {
-                                                                    "total": 0.029476224000006823,
+                                                                    "total": 0.028739330009557307,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.029476224000006823
+                                                                    "self": 0.028739330009557307
                                                                 },
                                                                 "steps_from_proto": {
-                                                                    "total": 0.002232279999986986,
+                                                                    "total": 0.0005929879989707842,
                                                                     "count": 1,
                                                                     "is_parallel": true,
-                                                                    "self": 0.000282737000020461,
+                                                                    "self": 0.00015834698569960892,
                                                                     "children": {
                                                                         "_process_rank_one_or_two_observation": {
-                                                                            "total": 0.0019495429999665248,
+                                                                            "total": 0.0004346410132711753,
                                                                             "count": 2,
                                                                             "is_parallel": true,
-                                                                            "self": 0.0019495429999665248
+                                                                            "self": 0.0004346410132711753
                                                                         }
                                                                     }
                                                                 }
@@ -274,34 +267,34 @@
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 1345.911591641018,
-                                                    "count": 232570,
+                                                    "total": 3351.256014689614,
+                                                    "count": 232621,
                                                     "is_parallel": true,
-                                                    "self": 39.45110602499335,
+                                                    "self": 24.912083958523,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 86.66661465906628,
-                                                            "count": 232570,
+                                                            "total": 250.86380107582954,
+                                                            "count": 232621,
                                                             "is_parallel": true,
-                                                            "self": 86.66661465906628
+                                                            "self": 250.86380107582954
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 1123.5662537380235,
-                                                            "count": 232570,
+                                                            "total": 2994.8188047677104,
+                                                            "count": 232621,
                                                             "is_parallel": true,
-                                                            "self": 1123.5662537380235
+                                                            "self": 2994.8188047677104
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 96.227617218935,
-                                                            "count": 232570,
+                                                            "total": 80.66132488755102,
+                                                            "count": 232621,
                                                             "is_parallel": true,
-                                                            "self": 41.96254788289923,
+                                                            "self": 23.57657541986555,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 54.265069336035765,
-                                                                    "count": 465140,
+                                                                    "total": 57.08474946768547,
+                                                                    "count": 465242,
                                                                     "is_parallel": true,
-                                                                    "self": 54.265069336035765
+                                                                    "self": 57.08474946768547
                                                                 }
                                                             }
                                                         }
@@ -314,31 +307,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 544.9346554590913,
-                            "count": 232571,
-                            "self": 6.589558967025255,
+                            "total": 418.8993287732301,
+                            "count": 232622,
+                            "self": 5.2829950310406275,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 179.92486521606605,
-                                    "count": 232571,
-                                    "self": 178.65975071206543,
+                                    "total": 99.63399304414634,
+                                    "count": 232622,
+                                    "self": 99.09129381917592,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 1.2651145040006213,
+                                            "total": 0.5426992249704199,
                                             "count": 10,
-                                            "self": 1.2651145040006213
+                                            "self": 0.5426992249704199
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 358.42023127600004,
+                                    "total": 313.9823406980431,
                                     "count": 97,
-                                    "self": 300.2295895649817,
+                                    "self": 169.1170613021386,
                                     "children": {
                                         "TorchPPOOptimizer.update": {
-                                            "total": 58.190641711018316,
+                                            "total": 144.8652793959045,
                                             "count": 2910,
-                                            "self": 58.190641711018316
+                                            "self": 144.8652793959045
                                         }
                                     }
                                 }
@@ -347,19 +340,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 1.2770001376338769e-06,
+                    "total": 6.00994098931551e-07,
                     "count": 1,
-                    "self": 1.2770001376338769e-06
+                    "self": 6.00994098931551e-07
                 },
                 "TrainerController._save_models": {
-                    "total": 0.11434745199994722,
+                    "total": 0.035800961006316356,
                     "count": 1,
-                    "self": 0.002078798999718856,
+                    "self": 0.000968530002865009,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.11226865300022837,
+                            "total": 0.03483243100345135,
                             "count": 1,
-                            "self": 0.11226865300022837
+                            "self": 0.03483243100345135
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,118 +2,118 @@
     "Huggy": {
         "checkpoints": [
             {
-                "steps": 199821,
-                "file_path": "results/Huggy/Huggy/Huggy-199821.onnx",
-                "reward": 3.236910421300579,
-                "creation_time": 1678011027.2623742,
+                "steps": 199918,
+                "file_path": "results/Huggy/Huggy/Huggy-199918.onnx",
+                "reward": 3.400942102762369,
+                "creation_time": 1736535883.5360057,
                 "auxillary_file_paths": [
-                    "results/Huggy/Huggy/Huggy-199821.pt"
+                    "results/Huggy/Huggy/Huggy-199918.pt"
                 ]
             },
             {
-                "steps": 399984,
-                "file_path": "results/Huggy/Huggy/Huggy-399984.onnx",
-                "reward": 3.5537834299935236,
-                "creation_time": 1678011278.6911852,
+                "steps": 399925,
+                "file_path": "results/Huggy/Huggy/Huggy-399925.onnx",
+                "reward": 3.794162377134546,
+                "creation_time": 1736536307.219438,
                 "auxillary_file_paths": [
-                    "results/Huggy/Huggy/Huggy-399984.pt"
+                    "results/Huggy/Huggy/Huggy-399925.pt"
                 ]
             },
             {
-                "steps": 599975,
-                "file_path": "results/Huggy/Huggy/Huggy-599975.onnx",
-                "reward": 3.9430414027181167,
-                "creation_time": 1678011537.0830588,
+                "steps": 599920,
+                "file_path": "results/Huggy/Huggy/Huggy-599920.onnx",
+                "reward": 3.4047936706831963,
+                "creation_time": 1736536735.0910494,
                 "auxillary_file_paths": [
-                    "results/Huggy/Huggy/Huggy-599975.pt"
+                    "results/Huggy/Huggy/Huggy-599920.pt"
                 ]
             },
             {
-                "steps": 799882,
-                "file_path": "results/Huggy/Huggy/Huggy-799882.onnx",
-                "reward": 3.6970330740339192,
-                "creation_time": 1678011790.190062,
+                "steps": 799940,
+                "file_path": "results/Huggy/Huggy/Huggy-799940.onnx",
+                "reward": 3.9033032980832187,
+                "creation_time": 1736537156.446953,
                 "auxillary_file_paths": [
-                    "results/Huggy/Huggy/Huggy-799882.pt"
+                    "results/Huggy/Huggy/Huggy-799940.pt"
                 ]
             },
             {
-                "steps": 999976,
-                "file_path": "results/Huggy/Huggy/Huggy-999976.onnx",
-                "reward": 3.8214572721148192,
-                "creation_time": 1678012047.3796005,
+                "steps": 999983,
+                "file_path": "results/Huggy/Huggy/Huggy-999983.onnx",
+                "reward": 3.597542370038648,
+                "creation_time": 1736537576.4089515,
                 "auxillary_file_paths": [
-                    "results/Huggy/Huggy/Huggy-999976.pt"
+                    "results/Huggy/Huggy/Huggy-999983.pt"
                 ]
             },
             {
-                "steps": 1199963,
-                "file_path": "results/Huggy/Huggy/Huggy-1199963.onnx",
-                "reward": 3.8122292449186137,
-                "creation_time": 1678012302.6624,
+                "steps": 1199989,
+                "file_path": "results/Huggy/Huggy/Huggy-1199989.onnx",
+                "reward": 3.544571946064631,
+                "creation_time": 1736538004.9613855,
                 "auxillary_file_paths": [
-                    "results/Huggy/Huggy/Huggy-1199963.pt"
+                    "results/Huggy/Huggy/Huggy-1199989.pt"
                 ]
             },
             {
-                "steps": 1399979,
-                "file_path": "results/Huggy/Huggy/Huggy-1399979.onnx",
-                "reward": 2.502593517303467,
-                "creation_time": 1678012562.6009378,
+                "steps": 1399938,
+                "file_path": "results/Huggy/Huggy/Huggy-1399938.onnx",
+                "reward": 4.092764544486999,
+                "creation_time": 1736538435.850968,
                 "auxillary_file_paths": [
-                    "results/Huggy/Huggy/Huggy-1399979.pt"
+                    "results/Huggy/Huggy/Huggy-1399938.pt"
                 ]
             },
             {
-                "steps": 1599942,
-                "file_path": "results/Huggy/Huggy/Huggy-1599942.onnx",
-                "reward": 3.862941087602259,
-                "creation_time": 1678012814.7416115,
+                "steps": 1599893,
+                "file_path": "results/Huggy/Huggy/Huggy-1599893.onnx",
+                "reward": 3.921031305664464,
+                "creation_time": 1736538863.194114,
                 "auxillary_file_paths": [
-                    "results/Huggy/Huggy/Huggy-1599942.pt"
+                    "results/Huggy/Huggy/Huggy-1599893.pt"
                 ]
             },
             {
-                "steps": 1799959,
-                "file_path": "results/Huggy/Huggy/Huggy-1799959.onnx",
-                "reward": 3.896692361150469,
-                "creation_time": 1678013074.162421,
+                "steps": 1799962,
+                "file_path": "results/Huggy/Huggy/Huggy-1799962.onnx",
+                "reward": 3.424738976310511,
+                "creation_time": 1736539293.5376668,
                 "auxillary_file_paths": [
-                    "results/Huggy/Huggy/Huggy-1799959.pt"
+                    "results/Huggy/Huggy/Huggy-1799962.pt"
                 ]
             },
             {
-                "steps": 1999951,
-                "file_path": "results/Huggy/Huggy/Huggy-1999951.onnx",
-                "reward": 3.5194035041623,
-                "creation_time": 1678013329.4887567,
+                "steps": 1999981,
+                "file_path": "results/Huggy/Huggy/Huggy-1999981.onnx",
+                "reward": 3.362255166406217,
+                "creation_time": 1736539714.2023585,
                 "auxillary_file_paths": [
-                    "results/Huggy/Huggy/Huggy-1999951.pt"
+                    "results/Huggy/Huggy/Huggy-1999981.pt"
                 ]
             },
             {
-                "steps": 2000042,
-                "file_path": "results/Huggy/Huggy/Huggy-2000042.onnx",
-                "reward": 3.5517807688031877,
-                "creation_time": 1678013329.6081042,
+                "steps": 2000026,
+                "file_path": "results/Huggy/Huggy/Huggy-2000026.onnx",
+                "reward": 3.3276518481843014,
+                "creation_time": 1736539714.2399833,
                 "auxillary_file_paths": [
-                    "results/Huggy/Huggy/Huggy-2000042.pt"
+                    "results/Huggy/Huggy/Huggy-2000026.pt"
                 ]
             }
         ],
         "final_checkpoint": {
-            "steps": 2000042,
+            "steps": 2000026,
             "file_path": "results/Huggy/Huggy.onnx",
-            "reward": 3.5517807688031877,
-            "creation_time": 1678013329.6081042,
+            "reward": 3.3276518481843014,
+            "creation_time": 1736539714.2399833,
             "auxillary_file_paths": [
-                "results/Huggy/Huggy/Huggy-2000042.pt"
+                "results/Huggy/Huggy/Huggy-2000026.pt"
             ]
         }
     },
     "metadata": {
         "stats_format_version": "0.3.0",
-        "mlagents_version": "0.29.0.dev0",
-        "torch_version": "1.8.1+cu102"
+        "mlagents_version": "1.2.0.dev0",
+        "torch_version": "2.5.1+cpu"
     }
 }