Huggy first training with default config PPO

Huggy.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1c53f842cc418eff6adff49b82b3fe257eb8868edc3f5b14397fc7fab9e3c51
+size 2270373

Huggy/Huggy-1499975.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e5ec82519256bd2ccddf480e38d6c6b314951b7ab9ed3eb520a259302bab84b
+size 2270373

Huggy/Huggy-1499975.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25ea853755e6c875c0142372c2309c29ccb3940ff881fbe1170f4055783d3041
+size 13505262

Huggy/Huggy-1999991.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fe7d84ffd6d1f040aafb3ac7fadec5cba20fbc39fcc8c29b43fef65653177f5
+size 2270373

Huggy/Huggy-1999991.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b40328fd9f93c6772951f87b9ab91ef26b95d94640ceb16e3bbddac82c3bb05
+size 13505262

Huggy/Huggy-2000066.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1c53f842cc418eff6adff49b82b3fe257eb8868edc3f5b14397fc7fab9e3c51
+size 2270373

Huggy/Huggy-2000066.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fff83de42e1671730ed3270dd09c3418400676a50cba863ef60a638d1273203
+size 13505262

Huggy/Huggy-499978.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:161c7e8f66c34ad5cdaec14a632a623fef512ebb9f525a56ecb48894f55ff492
+size 2270373

Huggy/Huggy-499978.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b17ae0281174768a1c9099c9fdbe0dd29f11846732ffef54195096a365552b9
+size 13505262

Huggy/Huggy-999906.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aac5a33e34cc90db6f550f7d41e4a9374e39e3014c9fdadbe3d26cce75faa19c
+size 2270373

Huggy/Huggy-999906.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78d984bc6e59cc02c4e84ec55dea64d921762a9dd4727398b5d054f191e6c6b1
+size 13505262

Huggy/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fff83de42e1671730ed3270dd09c3418400676a50cba863ef60a638d1273203
+size 13505262

Huggy/events.out.tfevents.1670438502.92839dd9f85b.347.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:345eac7bc73bcee8ff80a980626353a9fac81489d8b6277c8ea27210b5802962
+size 378447

README.md

@@ -0,0 +1,31 @@
+
+---
+      tags:
+      - unity-ml-agents
+      - ml-agents
+      - deep-reinforcement-learning
+      - reinforcement-learning
+      - ML-Agents-Huggy
+      library_name: ml-agents
+---
+    
+  # **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://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:
+
+
+  ### Resume the training
+  ```
+  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: daripaez/ppo-Huggy
+  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, "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": 5, "checkpoint_interval": 500000, "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}

configuration.yaml

@@ -0,0 +1,75 @@
+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: 5
+    checkpoint_interval: 500000
+    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

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:767:(parse_card) cannot find card '0'
+ALSA lib conf.c:4528:(_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:4528:(_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:4528:(_snd_config_evaluate) function snd_func_refer returned error: No such file or directory
+ALSA lib conf.c:5007:(snd_config_expand) Evaluate error: No such file or directory
+ALSA lib pcm.c:2495:(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:4528:(_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:4528:(_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:4528:(_snd_config_evaluate) function snd_func_refer returned error: No such file or directory
+ALSA lib conf.c:5007:(snd_config_expand) Evaluate error: No such file or directory
+ALSA lib pcm.c:2495:(snd_pcm_open_noupdate) Unknown PCM default
+FMOD failed to initialize the output device.: "Error initializing output device. " (60)
+FMOD initialized on nosound output
+Begin MonoManager ReloadAssembly
+- Completed reload, in  0.082 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: 0.804893 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]: 26746 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 136 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 328
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 1.1 MB
+    [ALLOC_DEFAULT_MAIN]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 26747 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 23.5 MB
+      Peak Large allocation bytes 16.0 MB
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [1.0 MB-2.0 MB]: 34 frames, [2.0 MB-4.0 MB]: 26713 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 2.1 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 1.1 MB
+    [ALLOC_GFX_MAIN]
+      Peak usage frame count: [32.0 KB-64.0 KB]: 26746 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
+      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 1.1 MB
+    [ALLOC_CACHEOBJECTS_MAIN]
+      Peak usage frame count: [1.0 MB-2.0 MB]: 26746 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
+      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 1.1 MB
+    [ALLOC_TYPETREE_MAIN]
+      Peak usage frame count: [0-1.0 KB]: 26747 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
+      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 +1,369 @@
+{
+    "name": "root",
+    "gauges": {
+        "Huggy.Policy.Entropy.mean": {
+            "value": 1.4088364839553833,
+            "min": 1.4088364839553833,
+            "max": 1.4288266897201538,
+            "count": 40
+        },
+        "Huggy.Policy.Entropy.sum": {
+            "value": 69125.96875,
+            "min": 67958.75,
+            "max": 76833.765625,
+            "count": 40
+        },
+        "Huggy.Environment.EpisodeLength.mean": {
+            "value": 104.04201680672269,
+            "min": 90.85531135531136,
+            "max": 386.54615384615386,
+            "count": 40
+        },
+        "Huggy.Environment.EpisodeLength.sum": {
+            "value": 49524.0,
+            "min": 48960.0,
+            "max": 50251.0,
+            "count": 40
+        },
+        "Huggy.Step.mean": {
+            "value": 1999991.0,
+            "min": 49992.0,
+            "max": 1999991.0,
+            "count": 40
+        },
+        "Huggy.Step.sum": {
+            "value": 1999991.0,
+            "min": 49992.0,
+            "max": 1999991.0,
+            "count": 40
+        },
+        "Huggy.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 2.3234262466430664,
+            "min": 0.0995357409119606,
+            "max": 2.3824241161346436,
+            "count": 40
+        },
+        "Huggy.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 1105.950927734375,
+            "min": 12.840110778808594,
+            "max": 1280.3931884765625,
+            "count": 40
+        },
+        "Huggy.Environment.CumulativeReward.mean": {
+            "value": 3.5949057628627585,
+            "min": 1.7076376492893972,
+            "max": 3.855494010402869,
+            "count": 40
+        },
+        "Huggy.Environment.CumulativeReward.sum": {
+            "value": 1711.175143122673,
+            "min": 220.28525675833225,
+            "max": 2030.16558521986,
+            "count": 40
+        },
+        "Huggy.Policy.ExtrinsicReward.mean": {
+            "value": 3.5949057628627585,
+            "min": 1.7076376492893972,
+            "max": 3.855494010402869,
+            "count": 40
+        },
+        "Huggy.Policy.ExtrinsicReward.sum": {
+            "value": 1711.175143122673,
+            "min": 220.28525675833225,
+            "max": 2030.16558521986,
+            "count": 40
+        },
+        "Huggy.Losses.PolicyLoss.mean": {
+            "value": 0.015666097746482893,
+            "min": 0.013582871308770136,
+            "max": 0.020586256164339525,
+            "count": 40
+        },
+        "Huggy.Losses.PolicyLoss.sum": {
+            "value": 0.031332195492965786,
+            "min": 0.028695884411475466,
+            "max": 0.0583777700647867,
+            "count": 40
+        },
+        "Huggy.Losses.ValueLoss.mean": {
+            "value": 0.04581902561088403,
+            "min": 0.022617052764528328,
+            "max": 0.05437094138728247,
+            "count": 40
+        },
+        "Huggy.Losses.ValueLoss.sum": {
+            "value": 0.09163805122176806,
+            "min": 0.04535687882453203,
+            "max": 0.16311282416184741,
+            "count": 40
+        },
+        "Huggy.Policy.LearningRate.mean": {
+            "value": 4.580873473075005e-06,
+            "min": 4.580873473075005e-06,
+            "max": 0.00029536792654402504,
+            "count": 40
+        },
+        "Huggy.Policy.LearningRate.sum": {
+            "value": 9.16174694615001e-06,
+            "min": 9.16174694615001e-06,
+            "max": 0.0008443270685576499,
+            "count": 40
+        },
+        "Huggy.Policy.Epsilon.mean": {
+            "value": 0.10152692500000005,
+            "min": 0.10152692500000005,
+            "max": 0.198455975,
+            "count": 40
+        },
+        "Huggy.Policy.Epsilon.sum": {
+            "value": 0.2030538500000001,
+            "min": 0.2030538500000001,
+            "max": 0.5814423500000001,
+            "count": 40
+        },
+        "Huggy.Policy.Beta.mean": {
+            "value": 8.619355750000007e-05,
+            "min": 8.619355750000007e-05,
+            "max": 0.004922953152500001,
+            "count": 40
+        },
+        "Huggy.Policy.Beta.sum": {
+            "value": 0.00017238711500000014,
+            "min": 0.00017238711500000014,
+            "max": 0.014073973265,
+            "count": 40
+        },
+        "Huggy.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 40
+        },
+        "Huggy.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 40
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1670438494",
+        "python_version": "3.8.15 (default, Oct 12 2022, 19:14:39) \n[GCC 7.5.0]",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy --no-graphics",
+        "mlagents_version": "0.29.0.dev0",
+        "mlagents_envs_version": "0.29.0.dev0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "1.8.1+cu102",
+        "numpy_version": "1.21.6",
+        "end_time_seconds": "1670440891"
+    },
+    "total": 2396.790107292,
+    "count": 1,
+    "self": 0.4002785859997857,
+    "children": {
+        "run_training.setup": {
+            "total": 0.11809149900000193,
+            "count": 1,
+            "self": 0.11809149900000193
+        },
+        "TrainerController.start_learning": {
+            "total": 2396.271737207,
+            "count": 1,
+            "self": 4.204856126065351,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 10.990058719999979,
+                    "count": 1,
+                    "self": 10.990058719999979
+                },
+                "TrainerController.advance": {
+                    "total": 2380.950918312935,
+                    "count": 231714,
+                    "self": 4.4190581728953475,
+                    "children": {
+                        "env_step": {
+                            "total": 1880.0255490469494,
+                            "count": 231714,
+                            "self": 1584.0090541549546,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 293.1739681670408,
+                                    "count": 231714,
+                                    "self": 15.361636591057504,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 277.8123315759833,
+                                            "count": 222892,
+                                            "self": 69.04148780897322,
+                                            "children": {
+                                                "TorchPolicy.sample_actions": {
+                                                    "total": 208.7708437670101,
+                                                    "count": 222892,
+                                                    "self": 208.7708437670101
+                                                }
+                                            }
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 2.842526724954041,
+                                    "count": 231714,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 2387.77907865304,
+                                            "count": 231714,
+                                            "is_parallel": true,
+                                            "self": 1085.4469075751028,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.007460876999857646,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.00036429299962037476,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.0070965840002372715,
+                                                                    "count": 2,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0070965840002372715
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.02844806600000993,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.00028992000011385244,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.0002044679999926302,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0002044679999926302
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.02716889899988928,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.02716889899988928
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.0007847790000141686,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0002602380000098492,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.0005245410000043194,
+                                                                            "count": 2,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.0005245410000043194
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 1302.3321710779371,
+                                                    "count": 231713,
+                                                    "is_parallel": true,
+                                                    "self": 36.381728045037335,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 79.04686686896844,
+                                                            "count": 231713,
+                                                            "is_parallel": true,
+                                                            "self": 79.04686686896844
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 1089.050730830006,
+                                                            "count": 231713,
+                                                            "is_parallel": true,
+                                                            "self": 1089.050730830006
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 97.85284533392542,
+                                                            "count": 231713,
+                                                            "is_parallel": true,
+                                                            "self": 39.46468159792471,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 58.388163736000706,
+                                                                    "count": 463426,
+                                                                    "is_parallel": true,
+                                                                    "self": 58.388163736000706
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 496.5063110930903,
+                            "count": 231714,
+                            "self": 6.9528885611148326,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 158.79672647097505,
+                                    "count": 231714,
+                                    "self": 158.25347529297483,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 0.5432511780002187,
+                                            "count": 4,
+                                            "self": 0.5432511780002187
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 330.7566960610004,
+                                    "count": 96,
+                                    "self": 275.6255118520005,
+                                    "children": {
+                                        "TorchPPOOptimizer.update": {
+                                            "total": 55.13118420899991,
+                                            "count": 2880,
+                                            "self": 55.13118420899991
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 8.950000847107731e-07,
+                    "count": 1,
+                    "self": 8.950000847107731e-07
+                },
+                "TrainerController._save_models": {
+                    "total": 0.12590315299985377,
+                    "count": 1,
+                    "self": 0.00752140699978554,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.11838174600006823,
+                            "count": 1,
+                            "self": 0.11838174600006823
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,65 @@
+{
+    "Huggy": {
+        "checkpoints": [
+            {
+                "steps": 499978,
+                "file_path": "results/Huggy/Huggy/Huggy-499978.onnx",
+                "reward": 3.677503084649845,
+                "creation_time": 1670439096.8997688,
+                "auxillary_file_paths": [
+                    "results/Huggy/Huggy/Huggy-499978.pt"
+                ]
+            },
+            {
+                "steps": 999906,
+                "file_path": "results/Huggy/Huggy/Huggy-999906.onnx",
+                "reward": 3.851449714878858,
+                "creation_time": 1670439697.0371943,
+                "auxillary_file_paths": [
+                    "results/Huggy/Huggy/Huggy-999906.pt"
+                ]
+            },
+            {
+                "steps": 1499975,
+                "file_path": "results/Huggy/Huggy/Huggy-1499975.onnx",
+                "reward": 3.570557139567192,
+                "creation_time": 1670440299.9607377,
+                "auxillary_file_paths": [
+                    "results/Huggy/Huggy/Huggy-1499975.pt"
+                ]
+            },
+            {
+                "steps": 1999991,
+                "file_path": "results/Huggy/Huggy/Huggy-1999991.onnx",
+                "reward": 3.6285619897078414,
+                "creation_time": 1670440891.059916,
+                "auxillary_file_paths": [
+                    "results/Huggy/Huggy/Huggy-1999991.pt"
+                ]
+            },
+            {
+                "steps": 2000066,
+                "file_path": "results/Huggy/Huggy/Huggy-2000066.onnx",
+                "reward": 3.6345172298478556,
+                "creation_time": 1670440891.183999,
+                "auxillary_file_paths": [
+                    "results/Huggy/Huggy/Huggy-2000066.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 2000066,
+            "file_path": "results/Huggy/Huggy.onnx",
+            "reward": 3.6345172298478556,
+            "creation_time": 1670440891.183999,
+            "auxillary_file_paths": [
+                "results/Huggy/Huggy/Huggy-2000066.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "0.29.0.dev0",
+        "torch_version": "1.8.1+cu102"
+    }
+}