add Huggy agent

Huggy.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f42846869f6be429a7f9f3c57bf94b6fd52d0a38999741e7017539c446a325d
+size 2273984

Huggy/Huggy-199812.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ed978f8ca1d0aa8c1a39b3a049fe236d77f8a3f14168645f4e738b366ebf3f8
+size 2273984

Huggy/Huggy-199812.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42a1919de9e29eafb00eedaafe4e5849f09639c2aca7924a5983bf8cee5b68b4
+size 13509388

Huggy/Huggy-399736.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ff4485e85e235456a4cbdc16712e304a967b978dd03f01799cacc41756fcd02
+size 2273984

Huggy/Huggy-399736.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:114f2aa936c084811285f4521f25df28a75874c769838761e2c70f7efa79f7c1
+size 13509388

Huggy/Huggy-599828.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0c2c8bafaf6a11cd9031d4f3016771e3aebcc9c36738fe34b7befef644f12d8
+size 2273984

Huggy/Huggy-599828.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7ecb2f741c92640d1e22fc06290be0d929242bbe0eed5c765571a6e2276cec0
+size 13509388

Huggy/Huggy-606071.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f42846869f6be429a7f9f3c57bf94b6fd52d0a38999741e7017539c446a325d
+size 2273984

Huggy/Huggy-606071.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a21d82b0f677daf5bd4dad1e42ee1fda053193fb45c57c58dfbbec9a78cc907
+size 13509388

Huggy/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e44ed47b778527dc50e561bbf9c3ee685aa9c582e432eba59323103601f45f0
+size 13509218

Huggy/events.out.tfevents.1714167267.964b775308b1.4081.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa0d03fdec5c9d9ce94a1ecc02d0eb78b635bf50ca55348ecd1842a2433212ed
+size 33121

README.md

@@ -0,0 +1,35 @@
+---
+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).
+
+  ## Usage (with ML-Agents)
+  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. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity
+  2. Step 1: Find your model_id: Laz4rz/hf-huggy-1-bonus
+  3. Step 2: Select your *.nn /*.onnx file
+  4. Click on Watch the agent play 👀
+  

config.json

@@ -0,0 +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, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 200000, "network_settings": {"normalize": true, "hidden_units": 512, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.995, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 15, "even_checkpoints": false, "max_steps": 2000000, "time_horizon": 1000, "summary_freq": 50000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./trained-envs-executables/linux/Huggy/Huggy", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "Huggy2", "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

@@ -0,0 +1,79 @@
+default_settings: null
+behaviors:
+  Huggy:
+    trainer_type: ppo
+    hyperparameters:
+      batch_size: 2048
+      buffer_size: 20480
+      learning_rate: 0.0003
+      beta: 0.005
+      epsilon: 0.2
+      lambd: 0.95
+      num_epoch: 3
+      shared_critic: false
+      learning_rate_schedule: linear
+      beta_schedule: linear
+      epsilon_schedule: linear
+    checkpoint_interval: 200000
+    network_settings:
+      normalize: true
+      hidden_units: 512
+      num_layers: 3
+      vis_encode_type: simple
+      memory: null
+      goal_conditioning_type: hyper
+      deterministic: false
+    reward_signals:
+      extrinsic:
+        gamma: 0.995
+        strength: 1.0
+        network_settings:
+          normalize: false
+          hidden_units: 128
+          num_layers: 2
+          vis_encode_type: simple
+          memory: null
+          goal_conditioning_type: hyper
+          deterministic: false
+    init_path: null
+    keep_checkpoints: 15
+    even_checkpoints: false
+    max_steps: 2000000
+    time_horizon: 1000
+    summary_freq: 50000
+    threaded: false
+    self_play: null
+    behavioral_cloning: null
+env_settings:
+  env_path: ./trained-envs-executables/linux/Huggy/Huggy
+  env_args: null
+  base_port: 5005
+  num_envs: 1
+  num_areas: 1
+  timeout_wait: 60
+  seed: -1
+  max_lifetime_restarts: 10
+  restarts_rate_limit_n: 1
+  restarts_rate_limit_period_s: 60
+engine_settings:
+  width: 84
+  height: 84
+  quality_level: 5
+  time_scale: 20
+  target_frame_rate: -1
+  capture_frame_rate: 60
+  no_graphics: true
+  no_graphics_monitor: false
+environment_parameters: null
+checkpoint_settings:
+  run_id: Huggy2
+  initialize_from: null
+  load_model: false
+  resume: false
+  force: false
+  train_model: false
+  inference: false
+  results_dir: results
+torch_settings:
+  device: null
+debug: false

run_logs/Player-0.log

@@ -0,0 +1,294 @@
+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'
+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
+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:855:(parse_card) cannot find card '0'
+ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_card_inum returned error: No such file or directory
+ALSA lib confmisc.c:422:(snd_func_concat) error evaluating strings
+ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_concat returned error: No such file or directory
+ALSA lib confmisc.c:1334:(snd_func_refer) error evaluating name
+ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_refer returned error: No such file or directory
+ALSA lib conf.c:5701:(snd_config_expand) Evaluate error: No such file or directory
+ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM default
+FMOD failed to initialize the output device.: "Error initializing output device. " (60)
+Forced to initialize FMOD to to the device driver's system output rate 48000, this may impact performance and/or give inconsistent experiences compared to selected sample rate 48000
+ALSA lib confmisc.c:855:(parse_card) cannot find card '0'
+ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_card_inum returned error: No such file or directory
+ALSA lib confmisc.c:422:(snd_func_concat) error evaluating strings
+ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_concat returned error: No such file or directory
+ALSA lib confmisc.c:1334:(snd_func_refer) error evaluating name
+ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_refer returned error: No such file or directory
+ALSA lib conf.c:5701:(snd_config_expand) Evaluate error: No such file or directory
+ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM default
+FMOD failed to initialize the output device.: "Error initializing output device. " (60)
+FMOD initialized on nosound output
+Begin MonoManager ReloadAssembly
+- Completed reload, in  0.104 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)
+ERROR: Shader Hidden/Universal Render Pipeline/Sampling shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+ERROR: Shader Hidden/Universal Render Pipeline/LutBuilderLdr shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+ERROR: Shader Hidden/Universal Render Pipeline/LutBuilderHdr shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+ERROR: Shader Hidden/Universal Render Pipeline/UberPost shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+WARNING: Shader Unsupported: 'Hidden/Universal Render Pipeline/FallbackError' - 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?
+ERROR: Shader Hidden/Universal Render Pipeline/FallbackError shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+WARNING: Shader Unsupported: 'Hidden/Universal Render Pipeline/FallbackError' - 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?
+ERROR: Shader Hidden/Universal Render Pipeline/Stop NaN shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+ERROR: Shader Hidden/Universal Render Pipeline/SubpixelMorphologicalAntialiasing shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+ERROR: Shader Hidden/Universal Render Pipeline/GaussianDepthOfField shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+ERROR: Shader Hidden/Universal Render Pipeline/BokehDepthOfField shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+ERROR: Shader Hidden/Universal Render Pipeline/CameraMotionBlur shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+ERROR: Shader Hidden/Universal Render Pipeline/PaniniProjection shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+ERROR: Shader Hidden/Universal Render Pipeline/Bloom shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+ERROR: Shader Hidden/Universal Render Pipeline/FinalPost shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+WARNING: Shader Unsupported: 'Hidden/Universal Render Pipeline/StencilDeferred' - 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?
+WARNING: Shader Unsupported: 'Hidden/Universal Render Pipeline/StencilDeferred' - 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?
+ERROR: Shader Hidden/Universal Render Pipeline/LensFlareDataDriven shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+ERROR: Shader Hidden/Universal Render Pipeline/Scaling Setup shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+ERROR: Shader Hidden/Universal Render Pipeline/Edge Adaptive Spatial Upsampling shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+ERROR: Shader Hidden/Universal Render Pipeline/Debug/DebugReplacement shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+ERROR: Shader Hidden/kMotion/CameraMotionVectors shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+ERROR: Shader Hidden/kMotion/ObjectMotionVectors shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+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?
+ERROR: Shader Universal Render Pipeline/Lit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+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: 0.788443 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]: 8100 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
+      Overflow Count 0
+    [ALLOC_TEMP_Loading.AsyncRead]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 144 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
+      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
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 0]
+      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 10]
+      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 14]
+      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 6]
+      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 12]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_EnlightenWorker]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 15]
+      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 1]
+      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 2]
+      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 7]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_AssetGarbageCollectorHelper]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 5]
+      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 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]
+      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]
+      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 0]
+      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 4]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_BatchDeleteObjects]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+[ALLOC_DEFAULT] Dual Thread Allocator
+  Peak main deferred allocation count 96
+    [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]: 8101 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 22.1 MB
+      Peak Large allocation bytes 16.0 MB
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [2.0 MB-4.0 MB]: 8101 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 2.5 MB
+      Peak Large allocation bytes 0 B
+[ALLOC_TEMP_JOB_1_FRAME]
+  Initial Block Size 2.0 MB
+  Used Block Count 1
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_TEMP_JOB_2_FRAMES]
+  Initial Block Size 2.0 MB
+  Used Block Count 1
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_TEMP_JOB_4_FRAMES (JobTemp)]
+  Initial Block Size 2.0 MB
+  Used Block Count 2
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_TEMP_JOB_ASYNC (Background)]
+  Initial Block Size 1.0 MB
+  Used Block Count 3
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_GFX] Dual Thread Allocator
+  Peak main deferred allocation count 0
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 1.4 MB
+    [ALLOC_GFX_MAIN]
+      Peak usage frame count: [32.0 KB-64.0 KB]: 8100 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]: 8101 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 81.8 KB
+      Peak Large allocation bytes 0 B
+[ALLOC_CACHEOBJECTS] Dual Thread Allocator
+  Peak main deferred allocation count 0
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 1.4 MB
+    [ALLOC_CACHEOBJECTS_MAIN]
+      Peak usage frame count: [1.0 MB-2.0 MB]: 8100 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]: 8100 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
+      Peak Large allocation bytes 0 B
+[ALLOC_TYPETREE] Dual Thread Allocator
+  Peak main deferred allocation count 0
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 1.4 MB
+    [ALLOC_TYPETREE_MAIN]
+      Peak usage frame count: [0-1.0 KB]: 8101 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]: 8101 frames
+      Requested Block Size 2.0 MB
+      Peak Block count 1
+      Peak Allocated memory 7.3 KB
+      Peak Large allocation bytes 0 B

run_logs/timers.json

@@ -0,0 +1,362 @@
+{
+    "name": "root",
+    "gauges": {
+        "Huggy.Policy.Entropy.mean": {
+            "value": 1.4208875894546509,
+            "min": 1.4195122718811035,
+            "max": 1.428608775138855,
+            "count": 12
+        },
+        "Huggy.Policy.Entropy.sum": {
+            "value": 70318.3046875,
+            "min": 67531.9765625,
+            "max": 78362.7578125,
+            "count": 12
+        },
+        "Huggy.Environment.EpisodeLength.mean": {
+            "value": 101.45901639344262,
+            "min": 101.45901639344262,
+            "max": 418.19166666666666,
+            "count": 12
+        },
+        "Huggy.Environment.EpisodeLength.sum": {
+            "value": 49512.0,
+            "min": 49471.0,
+            "max": 50183.0,
+            "count": 12
+        },
+        "Huggy.Step.mean": {
+            "value": 599828.0,
+            "min": 49692.0,
+            "max": 599828.0,
+            "count": 12
+        },
+        "Huggy.Step.sum": {
+            "value": 599828.0,
+            "min": 49692.0,
+            "max": 599828.0,
+            "count": 12
+        },
+        "Huggy.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 2.2470223903656006,
+            "min": 0.1304357349872589,
+            "max": 2.2470223903656006,
+            "count": 12
+        },
+        "Huggy.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 1096.546875,
+            "min": 15.521852493286133,
+            "max": 1096.546875,
+            "count": 12
+        },
+        "Huggy.Environment.CumulativeReward.mean": {
+            "value": 3.844024112600772,
+            "min": 1.7325537450173323,
+            "max": 3.844024112600772,
+            "count": 12
+        },
+        "Huggy.Environment.CumulativeReward.sum": {
+            "value": 1875.8837669491768,
+            "min": 206.17389565706253,
+            "max": 1875.8837669491768,
+            "count": 12
+        },
+        "Huggy.Policy.ExtrinsicReward.mean": {
+            "value": 3.844024112600772,
+            "min": 1.7325537450173323,
+            "max": 3.844024112600772,
+            "count": 12
+        },
+        "Huggy.Policy.ExtrinsicReward.sum": {
+            "value": 1875.8837669491768,
+            "min": 206.17389565706253,
+            "max": 1875.8837669491768,
+            "count": 12
+        },
+        "Huggy.Losses.PolicyLoss.mean": {
+            "value": 0.015931323882088892,
+            "min": 0.015931323882088892,
+            "max": 0.01996262371055006,
+            "count": 12
+        },
+        "Huggy.Losses.PolicyLoss.sum": {
+            "value": 0.04779397164626668,
+            "min": 0.03193648516995987,
+            "max": 0.058428211135712144,
+            "count": 12
+        },
+        "Huggy.Losses.ValueLoss.mean": {
+            "value": 0.0450758658349514,
+            "min": 0.022682684908310574,
+            "max": 0.0450758658349514,
+            "count": 12
+        },
+        "Huggy.Losses.ValueLoss.sum": {
+            "value": 0.1352275975048542,
+            "min": 0.04536536981662115,
+            "max": 0.1352275975048542,
+            "count": 12
+        },
+        "Huggy.Policy.LearningRate.mean": {
+            "value": 0.00021354682881773334,
+            "min": 0.00021354682881773334,
+            "max": 0.000295284076571975,
+            "count": 12
+        },
+        "Huggy.Policy.LearningRate.sum": {
+            "value": 0.0006406404864532,
+            "min": 0.00044251640249454995,
+            "max": 0.00084421756859415,
+            "count": 12
+        },
+        "Huggy.Policy.Epsilon.mean": {
+            "value": 0.1711822666666667,
+            "min": 0.1711822666666667,
+            "max": 0.19842802500000004,
+            "count": 12
+        },
+        "Huggy.Policy.Epsilon.sum": {
+            "value": 0.5135468000000001,
+            "min": 0.34750545,
+            "max": 0.5814058499999999,
+            "count": 12
+        },
+        "Huggy.Policy.Beta.mean": {
+            "value": 0.003561995106666667,
+            "min": 0.003561995106666667,
+            "max": 0.0049215584475,
+            "count": 12
+        },
+        "Huggy.Policy.Beta.sum": {
+            "value": 0.01068598532,
+            "min": 0.007380521955000003,
+            "max": 0.014072151915,
+            "count": 12
+        },
+        "Huggy.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 12
+        },
+        "Huggy.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 12
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1714167266",
+        "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy2 --no-graphics",
+        "mlagents_version": "1.1.0.dev0",
+        "mlagents_envs_version": "1.1.0.dev0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "2.2.1+cu121",
+        "numpy_version": "1.23.5",
+        "end_time_seconds": "1714167974"
+    },
+    "total": 707.8142679609999,
+    "count": 1,
+    "self": 0.4645565099998521,
+    "children": {
+        "run_training.setup": {
+            "total": 0.05461420300002828,
+            "count": 1,
+            "self": 0.05461420300002828
+        },
+        "TrainerController.start_learning": {
+            "total": 707.295097248,
+            "count": 1,
+            "self": 1.229338077027478,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 3.0657460160000483,
+                    "count": 1,
+                    "self": 3.0657460160000483
+                },
+                "TrainerController.advance": {
+                    "total": 702.6332968729723,
+                    "count": 69336,
+                    "self": 1.31836393800711,
+                    "children": {
+                        "env_step": {
+                            "total": 561.5986178859772,
+                            "count": 69336,
+                            "self": 464.3156182549809,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 96.47588595803245,
+                                    "count": 69336,
+                                    "self": 5.327319449028323,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 91.14856650900413,
+                                            "count": 67506,
+                                            "self": 91.14856650900413
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 0.8071136729638511,
+                                    "count": 69335,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 704.8895551749906,
+                                            "count": 69335,
+                                            "is_parallel": true,
+                                            "self": 328.67008184099757,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.0008809470000414876,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.00020420499993178964,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.000676742000109698,
+                                                                    "count": 2,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.000676742000109698
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.029428448000089702,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0003741300000683623,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.0002457870000398543,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0002457870000398543
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.028067412999916996,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.028067412999916996
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.000741118000064489,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0001928710001948275,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.0005482469998696615,
+                                                                            "count": 2,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.0005482469998696615
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 376.21947333399305,
+                                                    "count": 69334,
+                                                    "is_parallel": true,
+                                                    "self": 11.604857663944586,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 24.28611157903481,
+                                                            "count": 69334,
+                                                            "is_parallel": true,
+                                                            "self": 24.28611157903481
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 313.4180416690109,
+                                                            "count": 69334,
+                                                            "is_parallel": true,
+                                                            "self": 313.4180416690109
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 26.91046242200275,
+                                                            "count": 69334,
+                                                            "is_parallel": true,
+                                                            "self": 9.497006158012368,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 17.413456263990383,
+                                                                    "count": 138668,
+                                                                    "is_parallel": true,
+                                                                    "self": 17.413456263990383
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 139.716315048988,
+                            "count": 69335,
+                            "self": 1.9234566419544308,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 39.97038372403381,
+                                    "count": 69335,
+                                    "self": 39.525914113034105,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 0.44446961099970395,
+                                            "count": 3,
+                                            "self": 0.44446961099970395
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 97.82247468299977,
+                                    "count": 29,
+                                    "self": 77.86595698099893,
+                                    "children": {
+                                        "TorchPPOOptimizer.update": {
+                                            "total": 19.956517702000838,
+                                            "count": 870,
+                                            "self": 19.956517702000838
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 1.45800004247576e-06,
+                    "count": 1,
+                    "self": 1.45800004247576e-06
+                },
+                "TrainerController._save_models": {
+                    "total": 0.3667148240001552,
+                    "count": 1,
+                    "self": 0.008716064000282131,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.3579987599998731,
+                            "count": 1,
+                            "self": 0.3579987599998731
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,56 @@
+{
+    "Huggy": {
+        "checkpoints": [
+            {
+                "steps": 199812,
+                "file_path": "results/Huggy2/Huggy/Huggy-199812.onnx",
+                "reward": 3.4417674974087746,
+                "creation_time": 1714167501.851207,
+                "auxillary_file_paths": [
+                    "results/Huggy2/Huggy/Huggy-199812.pt"
+                ]
+            },
+            {
+                "steps": 399736,
+                "file_path": "results/Huggy2/Huggy/Huggy-399736.onnx",
+                "reward": 3.8206912952084697,
+                "creation_time": 1714167731.5894604,
+                "auxillary_file_paths": [
+                    "results/Huggy2/Huggy/Huggy-399736.pt"
+                ]
+            },
+            {
+                "steps": 599828,
+                "file_path": "results/Huggy2/Huggy/Huggy-599828.onnx",
+                "reward": 4.00028882920742,
+                "creation_time": 1714167967.4759374,
+                "auxillary_file_paths": [
+                    "results/Huggy2/Huggy/Huggy-599828.pt"
+                ]
+            },
+            {
+                "steps": 606071,
+                "file_path": "results/Huggy2/Huggy/Huggy-606071.onnx",
+                "reward": 3.8171471332766345,
+                "creation_time": 1714167973.8925679,
+                "auxillary_file_paths": [
+                    "results/Huggy2/Huggy/Huggy-606071.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 606071,
+            "file_path": "results/Huggy2/Huggy.onnx",
+            "reward": 3.8171471332766345,
+            "creation_time": 1714167973.8925679,
+            "auxillary_file_paths": [
+                "results/Huggy2/Huggy/Huggy-606071.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "1.1.0.dev0",
+        "torch_version": "2.2.1+cu121"
+    }
+}