First commit

README.md

@@ -0,0 +1,31 @@
+
+---
+      tags:
+      - unity-ml-agents
+      - ml-agents
+      - deep-reinforcement-learning
+      - reinforcement-learning
+      - ML-Agents-SoccerTwos
+      library_name: ml-agents
+---
+    
+  # **poca** Agent playing **SoccerTwos**
+  This is a trained model of a **poca** agent playing **SoccerTwos** 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-SoccerTwos
+  2. Step 1: Write your model_id: kinkpunk/poca-MLAgents-SoccerTwos-v0.9
+  3. Step 2: Select your *.nn /*.onnx file
+  4. Click on Watch the agent play 👀
+  

SoccerTwos.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64a827754bcf3b7b06ec475fd644f4275741c5d6688e97a966654db3ccadcb1e
+size 2820313

SoccerTwos/SoccerTwos-1499980.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e866f57fce6a50c950025a224fcbd74e06d18d97fd79ec699649d184436cb3b9
+size 2820313

SoccerTwos/SoccerTwos-1499980.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:810b7d856e831bfdf3e2b487aae6fa1f81c68a809999fddddf32e01b63a1a8fa
+size 34740447

SoccerTwos/SoccerTwos-1999984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64a827754bcf3b7b06ec475fd644f4275741c5d6688e97a966654db3ccadcb1e
+size 2820313

SoccerTwos/SoccerTwos-1999984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3b4566057cda224297373d5ac7b997dcc53139d8f6651477e09aa2b2ef37eb0
+size 34740447

SoccerTwos/SoccerTwos-2000022.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64a827754bcf3b7b06ec475fd644f4275741c5d6688e97a966654db3ccadcb1e
+size 2820313

SoccerTwos/SoccerTwos-2000022.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51037c93f230ef69bfed168629a72ba71c430c5d59ca8e62d0ad07f260463455
+size 34740447

SoccerTwos/SoccerTwos-499020.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aade5bc6bf37691fb5d3e05895e788b071b71503c62cde6966f084d7d3fd8d66
+size 2820313

SoccerTwos/SoccerTwos-499020.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:521602e972b6f7a083683c6ff4f04ba4cb7393794db1d0171b40651a35060035
+size 34740309

SoccerTwos/SoccerTwos-999406.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d36c801806067af3314612f97b3d7b61376f055b5f9a21485a2672aac4beb377
+size 2820313

SoccerTwos/SoccerTwos-999406.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e638017a1dd9dea686f11890053077f3fd29c78e8337cd9a3837a8617aa68a5e
+size 34740309

SoccerTwos/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f190b13e03baa703195cbe1832bf2fa209848e6b84da116c28affa6b4eca5cb1
+size 34739343

SoccerTwos/events.out.tfevents.1675611397.RODEATH.11372.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c52911b38138ea6ecec97b390456503551a86140b3cd8c23b62b623b6855a5b8
+size 1898496

config.json

@@ -0,0 +1 @@
+{"default_settings": null, "behaviors": {"SoccerTwos": {"trainer_type": "poca", "hyperparameters": {"batch_size": 2048, "buffer_size": 40960, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "learning_rate_schedule": "constant", "beta_schedule": "constant", "epsilon_schedule": "constant"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 3, "vis_encode_type": "nature_cnn", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "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, "even_checkpoints": false, "max_steps": 2000000, "time_horizon": 2048, "summary_freq": 10000, "threaded": false, "self_play": {"save_steps": 20000, "team_change": 100000, "swap_steps": 5000, "window": 10, "play_against_latest_model_ratio": 0.6, "initial_elo": 1200.0}, "behavioral_cloning": null}}, "env_settings": {"env_path": ".\\training-envs-executables\\SoccerTwos.exe", "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": "poca-SoccerTwos-v3", "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 +1,82 @@
+default_settings: null
+behaviors:
+  SoccerTwos:
+    trainer_type: poca
+    hyperparameters:
+      batch_size: 2048
+      buffer_size: 40960
+      learning_rate: 0.0003
+      beta: 0.005
+      epsilon: 0.2
+      lambd: 0.95
+      num_epoch: 3
+      learning_rate_schedule: constant
+      beta_schedule: constant
+      epsilon_schedule: constant
+    checkpoint_interval: 500000
+    network_settings:
+      normalize: false
+      hidden_units: 512
+      num_layers: 3
+      vis_encode_type: nature_cnn
+      memory: null
+      goal_conditioning_type: hyper
+      deterministic: false
+    reward_signals:
+      extrinsic:
+        gamma: 0.99
+        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
+    even_checkpoints: false
+    max_steps: 2000000
+    time_horizon: 2048
+    summary_freq: 10000
+    threaded: false
+    self_play:
+      save_steps: 20000
+      team_change: 100000
+      swap_steps: 5000
+      window: 10
+      play_against_latest_model_ratio: 0.6
+      initial_elo: 1200.0
+    behavioral_cloning: null
+env_settings:
+  env_path: .\training-envs-executables\SoccerTwos.exe
+  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: poca-SoccerTwos-v3
+  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 +1,529 @@
+Mono path[0] = 'C:/Users/kinkp/Envs/deepRL/ml-agents/training-envs-executables/SoccerTwos/SoccerTwos_Data/Managed'
+Mono config path = 'C:/Users/kinkp/Envs/deepRL/ml-agents/training-envs-executables/SoccerTwos/MonoBleedingEdge/etc'
+Initialize engine version: 2021.3.14f1 (eee1884e7226)
+[Subsystems] Discovering subsystems at path C:/Users/kinkp/Envs/deepRL/ml-agents/training-envs-executables/SoccerTwos/SoccerTwos_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
+Begin MonoManager ReloadAssembly
+- Completed reload, in  1.678 seconds
+ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+Microsoft Media Foundation video decoding to texture disabled: graphics device is Null, only Direct3D 11 and Direct3D 12 (only on desktop) are supported for hardware-accelerated video decoding.
+ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+WARNING: Shader Unsupported: 'Standard (Specular setup)' - 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 Standard (Specular setup) shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+WARNING: Shader Unsupported: 'Standard (Specular setup)' - 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: 'Autodesk Interactive' - 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 Autodesk Interactive shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+WARNING: Shader Unsupported: 'Autodesk Interactive' - 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: 'Standard' - 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 Standard shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+WARNING: Shader Unsupported: 'Standard' - 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: 1.545900 ms
+Registered Communicator in Agent.
+ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+Setting up 2 worker threads for Enlighten.
+Memory Statistics:
+[ALLOC_TEMP_TLS] TLS Allocator
+  StackAllocators : 
+    [ALLOC_TEMP_MAIN]
+      Peak usage frame count: [8.0 KB-16.0 KB]: 38539 frames, [2.0 MB-4.0 MB]: 1 frames
+      Initial Block Size 4.0 MB
+      Current Block Size 4.0 MB
+      Peak Allocated Bytes 2.0 MB
+      Overflow Count 0
+    [ALLOC_TEMP_Loading.AsyncRead]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 348 B
+      Overflow Count 0
+    [ALLOC_TEMP_Loading.PreloadManager]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 67.5 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 54 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 54 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 0]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0.8 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 10]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 54 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 54 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 54 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 54 B
+      Overflow Count 0
+    [ALLOC_TEMP_EnlightenWorker] x 2
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 54 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 54 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 54 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 54 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 54 B
+      Overflow Count 0
+    [ALLOC_TEMP_AssetGarbageCollectorHelper] x 3
+      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 54 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 54 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 54 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 54 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 54 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 54 B
+      Overflow Count 0
+    [ALLOC_TEMP_BatchDeleteObjects]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 54 B
+      Overflow Count 0
+[ALLOC_DEFAULT] Dual Thread Allocator
+  Peak main deferred allocation count 6
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 0.9 MB
+    [ALLOC_DEFAULT_MAIN]
+      Peak usage frame count: [4.0 MB-8.0 MB]: 38540 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 4.9 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 38540 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 17.4 MB
+      Peak Large allocation bytes 16.0 MB
+[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 0.9 MB
+    [ALLOC_GFX_MAIN]
+      Peak usage frame count: [32.0 KB-64.0 KB]: 38539 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: [128.0 KB-256.0 KB]: 38540 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 173.6 KB
+      Peak Large allocation bytes 0 B
+[ALLOC_CACHEOBJECTS] Dual Thread Allocator
+  Peak main deferred allocation count 2
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 0.9 MB
+    [ALLOC_CACHEOBJECTS_MAIN]
+      Peak usage frame count: [0.5 MB-1.0 MB]: 38540 frames
+      Requested Block Size 4.0 MB
+      Peak Block count 1
+      Peak Allocated memory 0.6 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_CACHEOBJECTS_THREAD]
+      Peak usage frame count: [0.5 MB-1.0 MB]: 38539 frames, [2.0 MB-4.0 MB]: 1 frames
+      Requested Block Size 4.0 MB
+      Peak Block count 1
+      Peak Allocated memory 3.2 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 0.9 MB
+    [ALLOC_TYPETREE_MAIN]
+      Peak usage frame count: [0-1.0 KB]: 38540 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: [1.0 KB-2.0 KB]: 38539 frames, [2.0 KB-4.0 KB]: 1 frames
+      Requested Block Size 2.0 MB
+      Peak Block count 1
+      Peak Allocated memory 2.2 KB
+      Peak Large allocation bytes 0 B

run_logs/timers.json

@@ -0,0 +1,368 @@
+{
+    "name": "root",
+    "gauges": {
+        "SoccerTwos.Policy.Entropy.mean": {
+            "value": 2.570845603942871,
+            "min": 2.544567823410034,
+            "max": 3.2958121299743652,
+            "count": 200
+        },
+        "SoccerTwos.Policy.Entropy.sum": {
+            "value": 49031.16796875,
+            "min": 15398.0341796875,
+            "max": 111283.015625,
+            "count": 200
+        },
+        "SoccerTwos.Environment.EpisodeLength.mean": {
+            "value": 56.95348837209303,
+            "min": 50.44329896907217,
+            "max": 999.0,
+            "count": 200
+        },
+        "SoccerTwos.Environment.EpisodeLength.sum": {
+            "value": 19592.0,
+            "min": 5844.0,
+            "max": 32264.0,
+            "count": 200
+        },
+        "SoccerTwos.Self-play.ELO.mean": {
+            "value": 1359.1144708107408,
+            "min": 1197.9860523524299,
+            "max": 1359.575260573584,
+            "count": 193
+        },
+        "SoccerTwos.Self-play.ELO.sum": {
+            "value": 233767.6889794474,
+            "min": 2395.9721047048597,
+            "max": 263757.6005512753,
+            "count": 193
+        },
+        "SoccerTwos.Step.mean": {
+            "value": 1999984.0,
+            "min": 9826.0,
+            "max": 1999984.0,
+            "count": 200
+        },
+        "SoccerTwos.Step.sum": {
+            "value": 1999984.0,
+            "min": 9826.0,
+            "max": 1999984.0,
+            "count": 200
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
+            "value": 0.02454218827188015,
+            "min": -0.07202084362506866,
+            "max": 0.1600496619939804,
+            "count": 200
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
+            "value": 4.221256256103516,
+            "min": -10.701054573059082,
+            "max": 24.32754898071289,
+            "count": 200
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 0.01749088428914547,
+            "min": -0.07970795035362244,
+            "max": 0.1572108119726181,
+            "count": 200
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 3.008432149887085,
+            "min": -11.429139137268066,
+            "max": 23.89604377746582,
+            "count": 200
+        },
+        "SoccerTwos.Environment.CumulativeReward.mean": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 200
+        },
+        "SoccerTwos.Environment.CumulativeReward.sum": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 200
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.mean": {
+            "value": 0.06486511854238289,
+            "min": -0.6220380976086571,
+            "max": 0.4643600046634674,
+            "count": 200
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.sum": {
+            "value": 11.156800389289856,
+            "min": -50.94239991903305,
+            "max": 38.23800015449524,
+            "count": 200
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.mean": {
+            "value": 0.06486511854238289,
+            "min": -0.6220380976086571,
+            "max": 0.4643600046634674,
+            "count": 200
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.sum": {
+            "value": 11.156800389289856,
+            "min": -50.94239991903305,
+            "max": 38.23800015449524,
+            "count": 200
+        },
+        "SoccerTwos.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 200
+        },
+        "SoccerTwos.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 200
+        },
+        "SoccerTwos.Losses.PolicyLoss.mean": {
+            "value": 0.019871997791293932,
+            "min": 0.014322186307011483,
+            "max": 0.02048485916948266,
+            "count": 48
+        },
+        "SoccerTwos.Losses.PolicyLoss.sum": {
+            "value": 0.019871997791293932,
+            "min": 0.014322186307011483,
+            "max": 0.02048485916948266,
+            "count": 48
+        },
+        "SoccerTwos.Losses.ValueLoss.mean": {
+            "value": 0.07948082722723485,
+            "min": 0.0006094840906977576,
+            "max": 0.08202072692414125,
+            "count": 48
+        },
+        "SoccerTwos.Losses.ValueLoss.sum": {
+            "value": 0.07948082722723485,
+            "min": 0.0006094840906977576,
+            "max": 0.08202072692414125,
+            "count": 48
+        },
+        "SoccerTwos.Losses.BaselineLoss.mean": {
+            "value": 0.08282850086688995,
+            "min": 0.0006115967594572187,
+            "max": 0.08525328847269217,
+            "count": 48
+        },
+        "SoccerTwos.Losses.BaselineLoss.sum": {
+            "value": 0.08282850086688995,
+            "min": 0.0006115967594572187,
+            "max": 0.08525328847269217,
+            "count": 48
+        },
+        "SoccerTwos.Policy.LearningRate.mean": {
+            "value": 0.0003000000000000001,
+            "min": 0.0003000000000000001,
+            "max": 0.0003000000000000001,
+            "count": 48
+        },
+        "SoccerTwos.Policy.LearningRate.sum": {
+            "value": 0.0003000000000000001,
+            "min": 0.0003000000000000001,
+            "max": 0.0003000000000000001,
+            "count": 48
+        },
+        "SoccerTwos.Policy.Epsilon.mean": {
+            "value": 0.19999999999999993,
+            "min": 0.19999999999999993,
+            "max": 0.19999999999999993,
+            "count": 48
+        },
+        "SoccerTwos.Policy.Epsilon.sum": {
+            "value": 0.19999999999999993,
+            "min": 0.19999999999999993,
+            "max": 0.19999999999999993,
+            "count": 48
+        },
+        "SoccerTwos.Policy.Beta.mean": {
+            "value": 0.005000000000000001,
+            "min": 0.005000000000000001,
+            "max": 0.005000000000000001,
+            "count": 48
+        },
+        "SoccerTwos.Policy.Beta.sum": {
+            "value": 0.005000000000000001,
+            "min": 0.005000000000000001,
+            "max": 0.005000000000000001,
+            "count": 48
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1675611391",
+        "python_version": "3.9.10 (tags/v3.9.10:f2f3f53, Jan 17 2022, 15:14:21) [MSC v.1929 64 bit (AMD64)]",
+        "command_line_arguments": "C:\\Users\\kinkp\\Envs\\deepRL\\Scripts\\mlagents-learn .\\config\\poca\\SoccerTwos.yaml --env=.\\training-envs-executables\\SoccerTwos.exe --run-id=poca-SoccerTwos-v3 --no-graphics",
+        "mlagents_version": "0.31.0.dev0",
+        "mlagents_envs_version": "0.31.0.dev0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "1.13.1+cu117",
+        "numpy_version": "1.21.2",
+        "end_time_seconds": "1675615195"
+    },
+    "total": 3803.3899787,
+    "count": 1,
+    "self": 0.8188560999997208,
+    "children": {
+        "run_training.setup": {
+            "total": 0.1332814,
+            "count": 1,
+            "self": 0.1332814
+        },
+        "TrainerController.start_learning": {
+            "total": 3802.4378412,
+            "count": 1,
+            "self": 3.1674275999798738,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 8.548302399999905,
+                    "count": 20,
+                    "self": 8.548302399999905
+                },
+                "TrainerController.advance": {
+                    "total": 3790.4530694000196,
+                    "count": 135414,
+                    "self": 2.988485600108106,
+                    "children": {
+                        "env_step": {
+                            "total": 2826.191093500044,
+                            "count": 135414,
+                            "self": 1636.0856053000684,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 1188.2722044999537,
+                                    "count": 135414,
+                                    "self": 20.450347399878183,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 1167.8218571000755,
+                                            "count": 256936,
+                                            "self": 1167.8218571000755
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 1.8332837000221645,
+                                    "count": 135414,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 3792.307463499971,
+                                            "count": 135414,
+                                            "is_parallel": true,
+                                            "self": 2490.727124699956,
+                                            "children": {
+                                                "steps_from_proto": {
+                                                    "total": 0.03699420000132747,
+                                                    "count": 40,
+                                                    "is_parallel": true,
+                                                    "self": 0.007590400000883513,
+                                                    "children": {
+                                                        "_process_rank_one_or_two_observation": {
+                                                            "total": 0.029403800000443958,
+                                                            "count": 160,
+                                                            "is_parallel": true,
+                                                            "self": 0.029403800000443958
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 1301.5433446000134,
+                                                    "count": 135414,
+                                                    "is_parallel": true,
+                                                    "self": 67.30028220010831,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 52.474329399979524,
+                                                            "count": 135414,
+                                                            "is_parallel": true,
+                                                            "self": 52.474329399979524
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 959.6854022000249,
+                                                            "count": 135414,
+                                                            "is_parallel": true,
+                                                            "self": 959.6854022000249
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 222.08333079990066,
+                                                            "count": 270828,
+                                                            "is_parallel": true,
+                                                            "self": 45.52517820000051,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 176.55815259990015,
+                                                                    "count": 1083312,
+                                                                    "is_parallel": true,
+                                                                    "self": 176.55815259990015
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 961.2734902998671,
+                            "count": 135414,
+                            "self": 22.43478799994216,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 409.8812928999257,
+                                    "count": 135414,
+                                    "self": 408.70443429992577,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 1.176858599999946,
+                                            "count": 4,
+                                            "self": 1.176858599999946
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 528.9574093999993,
+                                    "count": 48,
+                                    "self": 300.6578406000017,
+                                    "children": {
+                                        "TorchPOCAOptimizer.update": {
+                                            "total": 228.29956879999756,
+                                            "count": 2880,
+                                            "self": 228.29956879999756
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 2.200000380980782e-06,
+                    "count": 1,
+                    "self": 2.200000380980782e-06
+                },
+                "TrainerController._save_models": {
+                    "total": 0.2690396000002693,
+                    "count": 1,
+                    "self": 0.007821800000328949,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.2612177999999403,
+                            "count": 1,
+                            "self": 0.2612177999999403
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,66 @@
+{
+    "SoccerTwos": {
+        "checkpoints": [
+            {
+                "steps": 499020,
+                "file_path": "results\\poca-SoccerTwos-v3\\SoccerTwos\\SoccerTwos-499020.onnx",
+                "reward": 0.0,
+                "creation_time": 1675612305.5257838,
+                "auxillary_file_paths": [
+                    "results\\poca-SoccerTwos-v3\\SoccerTwos\\SoccerTwos-499020.pt"
+                ]
+            },
+            {
+                "steps": 999406,
+                "file_path": "results\\poca-SoccerTwos-v3\\SoccerTwos\\SoccerTwos-999406.onnx",
+                "reward": 0.0,
+                "creation_time": 1675613219.7370162,
+                "auxillary_file_paths": [
+                    "results\\poca-SoccerTwos-v3\\SoccerTwos\\SoccerTwos-999406.pt"
+                ]
+            },
+            {
+                "steps": 1499980,
+                "file_path": "results\\poca-SoccerTwos-v3\\SoccerTwos\\SoccerTwos-1499980.onnx",
+                "reward": 0.0,
+                "creation_time": 1675614151.2764907,
+                "auxillary_file_paths": [
+                    "results\\poca-SoccerTwos-v3\\SoccerTwos\\SoccerTwos-1499980.pt"
+                ]
+            },
+            {
+                "steps": 1999984,
+                "file_path": "results\\poca-SoccerTwos-v3\\SoccerTwos\\SoccerTwos-1999984.onnx",
+                "reward": 0.0,
+                "creation_time": 1675615193.989344,
+                "auxillary_file_paths": [
+                    "results\\poca-SoccerTwos-v3\\SoccerTwos\\SoccerTwos-1999984.pt"
+                ]
+            },
+            {
+                "steps": 2000022,
+                "file_path": "results\\poca-SoccerTwos-v3\\SoccerTwos\\SoccerTwos-2000022.onnx",
+                "reward": 0.0,
+                "creation_time": 1675615194.2671115,
+                "auxillary_file_paths": [
+                    "results\\poca-SoccerTwos-v3\\SoccerTwos\\SoccerTwos-2000022.pt"
+                ]
+            }
+        ],
+        "elo": 1361.8486061801063,
+        "final_checkpoint": {
+            "steps": 2000022,
+            "file_path": "results\\poca-SoccerTwos-v3\\SoccerTwos.onnx",
+            "reward": 0.0,
+            "creation_time": 1675615194.2671115,
+            "auxillary_file_paths": [
+                "results\\poca-SoccerTwos-v3\\SoccerTwos\\SoccerTwos-2000022.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "0.31.0.dev0",
+        "torch_version": "1.13.1+cu117"
+    }
+}