First Push

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: lnros/poca-SoccerTwos
+  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 sha256:0a6a73249b5db84d10938b9a4e3a3f533d5fc45c5b01ea3cf4c550eddcaeedec
+size 1764633

SoccerTwos/SoccerTwos-10000134.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a6a73249b5db84d10938b9a4e3a3f533d5fc45c5b01ea3cf4c550eddcaeedec
+size 1764633

SoccerTwos/SoccerTwos-10000134.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca65ca9193155ff797487be90ae3ff87c6d54572b62c7f6846dd1d5aad1feee4
+size 28421201

SoccerTwos/SoccerTwos-22380.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c40159c927717f9c99ef64bcc82ccbb9e9390f08ca549cbfe83856c76470c702
+size 28421137

SoccerTwos/SoccerTwos-8499928.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:210f8d33cfc4d5aa7e5b2ebe0ace63467f76c9b93cc78c434905112e316068b6
+size 1764633

SoccerTwos/SoccerTwos-8499928.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73eff7119bd1d0796fd1aedf576b2b1a0ceb3f0783bd22a8aaa9c38c0344a2f9
+size 28421201

SoccerTwos/SoccerTwos-8999956.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54e2959d07ee4689cd3b7a5fcb319ee60f8e7f47f95681e424d88bb54ae40665
+size 1764633

SoccerTwos/SoccerTwos-8999956.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15d8b3b3d134cf729d4bef6fa984b77b6155afd78bc167e1eb50c95cb2e5e519
+size 28421201

SoccerTwos/SoccerTwos-9499980.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a720b202cc15c54e097868a30a12a9f5dd16305026c5515646cd6c3633e72706
+size 1764633

SoccerTwos/SoccerTwos-9499980.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72451cc29e670d744f897ba2490aef83798ec9bb99794d0bbaaf9eaf4c73165c
+size 28421201

SoccerTwos/SoccerTwos-9999952.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a6a73249b5db84d10938b9a4e3a3f533d5fc45c5b01ea3cf4c550eddcaeedec
+size 1764633

SoccerTwos/SoccerTwos-9999952.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9cf2b9397b7e9fec89e8e3debc4c6f7626e68fb20650446c9725c26275546cf
+size 28421201

SoccerTwos/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca65ca9193155ff797487be90ae3ff87c6d54572b62c7f6846dd1d5aad1feee4
+size 28421201

SoccerTwos/events.out.tfevents.1675753474.leonardor-mac.87936.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b6105bb9430b46a7c2814d5f3c8b6ef8a3b63104ad04a15e5feb4588bef2689
+size 10050662

config.json

@@ -0,0 +1 @@
+{"default_settings": null, "behaviors": {"SoccerTwos": {"trainer_type": "poca", "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": "constant", "beta_schedule": "constant", "epsilon_schedule": "constant"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple", "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": 10000000, "time_horizon": 1000, "summary_freq": 10000, "threaded": false, "self_play": {"save_steps": 50000, "team_change": 200000, "swap_steps": 2000, "window": 10, "play_against_latest_model_ratio": 0.5, "initial_elo": 1200.0}, "behavioral_cloning": null}}, "env_settings": {"env_path": "/Users/leonardor/hf-rl/ai-ai-challenge/ml-agents/training-envs-executables/SoccerTwos/SoccerTwos.app", "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": "SoccerTwos", "initialize_from": null, "load_model": false, "resume": false, "force": true, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -0,0 +1,82 @@
+default_settings: null
+behaviors:
+  SoccerTwos:
+    trainer_type: poca
+    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: constant
+      beta_schedule: constant
+      epsilon_schedule: constant
+    checkpoint_interval: 500000
+    network_settings:
+      normalize: false
+      hidden_units: 512
+      num_layers: 2
+      vis_encode_type: simple
+      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: 10000000
+    time_horizon: 1000
+    summary_freq: 10000
+    threaded: false
+    self_play:
+      save_steps: 50000
+      team_change: 200000
+      swap_steps: 2000
+      window: 10
+      play_against_latest_model_ratio: 0.5
+      initial_elo: 1200.0
+    behavioral_cloning: null
+env_settings:
+  env_path: /Users/leonardor/hf-rl/ai-ai-challenge/ml-agents/training-envs-executables/SoccerTwos/SoccerTwos.app
+  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: SoccerTwos
+  initialize_from: null
+  load_model: false
+  resume: false
+  force: true
+  train_model: false
+  inference: false
+  results_dir: results
+torch_settings:
+  device: null
+debug: false

run_logs/Player-0.log

@@ -0,0 +1,333 @@
+Mono path[0] = '/Users/leonardor/hf-rl/ai-ai-challenge/ml-agents/training-envs-executables/SoccerTwos/SoccerTwos.app/Contents/Resources/Data/Managed'
+Mono config path = '/Users/leonardor/hf-rl/ai-ai-challenge/ml-agents/training-envs-executables/SoccerTwos/SoccerTwos.app/Contents/MonoBleedingEdge/etc'
+New input system (experimental) initialized
+Initialize engine version: 2021.3.17f1 (3e8111cac19d)
+[Subsystems] Discovering subsystems at path /Users/leonardor/hf-rl/ai-ai-challenge/ml-agents/training-envs-executables/SoccerTwos/SoccerTwos.app/Contents/Resources/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  0.144 seconds
+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)
+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: 0.673577 ms
+Registered Communicator in Agent.
+ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+Default audio device was changed, but the audio system failed to initialize it. Attempting to reset sound system.
+Default audio device was changed, but the audio system failed to initialize it. Attempting to reset sound system.
+Default audio device was changed, but the audio system failed to initialize it. Attempting to reset sound system.
+Default audio device was changed, but the audio system failed to initialize it. Attempting to reset sound system.
+Default audio device was changed, but the audio system failed to initialize it. Attempting to reset sound system.
+Default audio device was changed, but the audio system failed to initialize it. Attempting to reset sound system.
+Setting up 8 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]: 141542 frames, [2.0 MB-4.0 MB]: 1 frames
+      Initial Block Size 4.0 MB
+      Current Block Size 4.0 MB
+      Peak Allocated Bytes 2.1 MB
+      Overflow Count 0
+    [ALLOC_TEMP_Loading.AsyncRead]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 151 B
+      Overflow Count 0
+    [ALLOC_TEMP_Loading.PreloadManager]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 78.8 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_Job.Worker 6]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 0]
+      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 9]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 5]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 14]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      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_Job.Worker 4]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 14]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 3]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 13]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 12]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_EnlightenWorker] x 8
+      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] x 15
+      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_Job.Worker 9]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 13]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 8]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_OSX HID Input]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 7]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 1]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 2]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 3]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 11]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 10]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0.7 KB
+      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_Job.Worker 11]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 12]
+      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 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 19
+    [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: [4.0 MB-8.0 MB]: 141543 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 5.3 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 141543 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 1.1 MB
+    [ALLOC_GFX_MAIN]
+      Peak usage frame count: [32.0 KB-64.0 KB]: 141542 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]: 141543 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 173.5 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: [0.5 MB-1.0 MB]: 141543 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]: 141542 frames, [2.0 MB-4.0 MB]: 1 frames
+      Requested Block Size 4.0 MB
+      Peak Block count 1
+      Peak Allocated memory 3.1 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]: 141543 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]: 141542 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": 1.593675136566162,
+            "min": 1.5864510536193848,
+            "max": 3.2957065105438232,
+            "count": 1000
+        },
+        "SoccerTwos.Policy.Entropy.sum": {
+            "value": 34270.390625,
+            "min": 23033.462890625,
+            "max": 118163.2890625,
+            "count": 1000
+        },
+        "SoccerTwos.Environment.EpisodeLength.mean": {
+            "value": 49.92929292929293,
+            "min": 39.90243902439025,
+            "max": 999.0,
+            "count": 1000
+        },
+        "SoccerTwos.Environment.EpisodeLength.sum": {
+            "value": 19772.0,
+            "min": 12964.0,
+            "max": 29712.0,
+            "count": 1000
+        },
+        "SoccerTwos.Self-play.ELO.mean": {
+            "value": 1565.2675369772219,
+            "min": 1188.9518718915506,
+            "max": 1585.3477554190315,
+            "count": 993
+        },
+        "SoccerTwos.Self-play.ELO.sum": {
+            "value": 309922.97232148994,
+            "min": 2379.717050292364,
+            "max": 386296.0168967678,
+            "count": 993
+        },
+        "SoccerTwos.Step.mean": {
+            "value": 9999952.0,
+            "min": 9872.0,
+            "max": 9999952.0,
+            "count": 1000
+        },
+        "SoccerTwos.Step.sum": {
+            "value": 9999952.0,
+            "min": 9872.0,
+            "max": 9999952.0,
+            "count": 1000
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
+            "value": 0.05186678096652031,
+            "min": -0.13752011954784393,
+            "max": 0.20369955897331238,
+            "count": 1000
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
+            "value": 10.269622802734375,
+            "min": -31.904666900634766,
+            "max": 25.010807037353516,
+            "count": 1000
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 0.053542204201221466,
+            "min": -0.13888515532016754,
+            "max": 0.20256052911281586,
+            "count": 1000
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 10.601356506347656,
+            "min": -32.22135543823242,
+            "max": 25.613407135009766,
+            "count": 1000
+        },
+        "SoccerTwos.Environment.CumulativeReward.mean": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 1000
+        },
+        "SoccerTwos.Environment.CumulativeReward.sum": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 1000
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.mean": {
+            "value": 0.025313132339053683,
+            "min": -0.5714285714285714,
+            "max": 0.5189022262891133,
+            "count": 1000
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.sum": {
+            "value": 5.012000203132629,
+            "min": -59.62879991531372,
+            "max": 50.42239958047867,
+            "count": 1000
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.mean": {
+            "value": 0.025313132339053683,
+            "min": -0.5714285714285714,
+            "max": 0.5189022262891133,
+            "count": 1000
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.sum": {
+            "value": 5.012000203132629,
+            "min": -59.62879991531372,
+            "max": 50.42239958047867,
+            "count": 1000
+        },
+        "SoccerTwos.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 1000
+        },
+        "SoccerTwos.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 1000
+        },
+        "SoccerTwos.Losses.PolicyLoss.mean": {
+            "value": 0.01760308787440105,
+            "min": 0.009009791381928759,
+            "max": 0.025567311757185962,
+            "count": 483
+        },
+        "SoccerTwos.Losses.PolicyLoss.sum": {
+            "value": 0.01760308787440105,
+            "min": 0.009009791381928759,
+            "max": 0.025567311757185962,
+            "count": 483
+        },
+        "SoccerTwos.Losses.ValueLoss.mean": {
+            "value": 0.1135916568338871,
+            "min": 0.0004827751455498704,
+            "max": 0.1314438397685687,
+            "count": 483
+        },
+        "SoccerTwos.Losses.ValueLoss.sum": {
+            "value": 0.1135916568338871,
+            "min": 0.0004827751455498704,
+            "max": 0.1314438397685687,
+            "count": 483
+        },
+        "SoccerTwos.Losses.BaselineLoss.mean": {
+            "value": 0.11564597139755885,
+            "min": 0.00048459587887919044,
+            "max": 0.1354606365164121,
+            "count": 483
+        },
+        "SoccerTwos.Losses.BaselineLoss.sum": {
+            "value": 0.11564597139755885,
+            "min": 0.00048459587887919044,
+            "max": 0.1354606365164121,
+            "count": 483
+        },
+        "SoccerTwos.Policy.LearningRate.mean": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 483
+        },
+        "SoccerTwos.Policy.LearningRate.sum": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 483
+        },
+        "SoccerTwos.Policy.Epsilon.mean": {
+            "value": 0.20000000000000007,
+            "min": 0.20000000000000007,
+            "max": 0.20000000000000007,
+            "count": 483
+        },
+        "SoccerTwos.Policy.Epsilon.sum": {
+            "value": 0.20000000000000007,
+            "min": 0.20000000000000007,
+            "max": 0.20000000000000007,
+            "count": 483
+        },
+        "SoccerTwos.Policy.Beta.mean": {
+            "value": 0.005000000000000001,
+            "min": 0.005000000000000001,
+            "max": 0.005000000000000001,
+            "count": 483
+        },
+        "SoccerTwos.Policy.Beta.sum": {
+            "value": 0.005000000000000001,
+            "min": 0.005000000000000001,
+            "max": 0.005000000000000001,
+            "count": 483
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1675753472",
+        "python_version": "3.9.15 (main, Dec 26 2022, 09:56:56) \n[Clang 14.0.0 (clang-1400.0.29.202)]",
+        "command_line_arguments": "/Users/leonardor/.pyenv/versions/rl/bin/mlagents-learn config/poca/SoccerTwos.yaml --env=/Users/leonardor/hf-rl/ai-ai-challenge/ml-agents/training-envs-executables/SoccerTwos/SoccerTwos.app --run-id=SoccerTwos --no-graphics --force",
+        "mlagents_version": "0.31.0.dev0",
+        "mlagents_envs_version": "0.31.0.dev0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "1.11.0",
+        "numpy_version": "1.21.2",
+        "end_time_seconds": "1675792599"
+    },
+    "total": 39127.111362931,
+    "count": 1,
+    "self": 0.41343229400081327,
+    "children": {
+        "run_training.setup": {
+            "total": 0.03867043799999981,
+            "count": 1,
+            "self": 0.03867043799999981
+        },
+        "TrainerController.start_learning": {
+            "total": 39126.659260199,
+            "count": 1,
+            "self": 15.767297433674685,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 3.1614213149701786,
+                    "count": 50,
+                    "self": 3.1614213149701786
+                },
+                "TrainerController.advance": {
+                    "total": 39107.54231488835,
+                    "count": 694244,
+                    "self": 15.682391095084313,
+                    "children": {
+                        "env_step": {
+                            "total": 10370.916021808473,
+                            "count": 694244,
+                            "self": 8548.172325244417,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 1813.0981689851444,
+                                    "count": 694245,
+                                    "self": 78.03459047298543,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 1735.063578512159,
+                                            "count": 1258914,
+                                            "self": 1735.063578512159
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 9.645527578910407,
+                                    "count": 694244,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 39041.000326020556,
+                                            "count": 694244,
+                                            "is_parallel": true,
+                                            "self": 32281.99871794338,
+                                            "children": {
+                                                "steps_from_proto": {
+                                                    "total": 0.10447255401225064,
+                                                    "count": 102,
+                                                    "is_parallel": true,
+                                                    "self": 0.022384074015459277,
+                                                    "children": {
+                                                        "_process_rank_one_or_two_observation": {
+                                                            "total": 0.08208847999679136,
+                                                            "count": 408,
+                                                            "is_parallel": true,
+                                                            "self": 0.08208847999679136
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 6758.8971355231615,
+                                                    "count": 694244,
+                                                    "is_parallel": true,
+                                                    "self": 353.80549020160015,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 235.22910658604195,
+                                                            "count": 694244,
+                                                            "is_parallel": true,
+                                                            "self": 235.22910658604195
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 5015.0072458825525,
+                                                            "count": 694244,
+                                                            "is_parallel": true,
+                                                            "self": 5015.0072458825525
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 1154.8552928529668,
+                                                            "count": 1388488,
+                                                            "is_parallel": true,
+                                                            "self": 249.15354155573266,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 905.7017512972342,
+                                                                    "count": 5553952,
+                                                                    "is_parallel": true,
+                                                                    "self": 905.7017512972342
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 28720.94390198479,
+                            "count": 694244,
+                            "self": 99.92397128199445,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 4572.693243532864,
+                                    "count": 694244,
+                                    "self": 4568.861333312864,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 3.8319102199995996,
+                                            "count": 20,
+                                            "self": 3.8319102199995996
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 24048.32668716993,
+                                    "count": 483,
+                                    "self": 1765.557169295993,
+                                    "children": {
+                                        "TorchPOCAOptimizer.update": {
+                                            "total": 22282.769517873938,
+                                            "count": 14490,
+                                            "self": 22282.769517873938
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 1.2079981388524175e-06,
+                    "count": 1,
+                    "self": 1.2079981388524175e-06
+                },
+                "TrainerController._save_models": {
+                    "total": 0.18822535400249762,
+                    "count": 1,
+                    "self": 0.0019633940028143115,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.1862619599996833,
+                            "count": 1,
+                            "self": 0.1862619599996833
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,66 @@
+{
+    "SoccerTwos": {
+        "checkpoints": [
+            {
+                "steps": 8499928,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-8499928.onnx",
+                "reward": 0.0,
+                "creation_time": 1675786694.198246,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-8499928.pt"
+                ]
+            },
+            {
+                "steps": 8999956,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-8999956.onnx",
+                "reward": 0.0,
+                "creation_time": 1675788767.9679759,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-8999956.pt"
+                ]
+            },
+            {
+                "steps": 9499980,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-9499980.onnx",
+                "reward": 0.0,
+                "creation_time": 1675790714.202942,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-9499980.pt"
+                ]
+            },
+            {
+                "steps": 9999952,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-9999952.onnx",
+                "reward": 0.0,
+                "creation_time": 1675792598.787261,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-9999952.pt"
+                ]
+            },
+            {
+                "steps": 10000134,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-10000134.onnx",
+                "reward": 0.0,
+                "creation_time": 1675792599.051214,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-10000134.pt"
+                ]
+            }
+        ],
+        "elo": 1561.866576641707,
+        "final_checkpoint": {
+            "steps": 10000134,
+            "file_path": "results/SoccerTwos/SoccerTwos.onnx",
+            "reward": 0.0,
+            "creation_time": 1675792599.051214,
+            "auxillary_file_paths": [
+                "results/SoccerTwos/SoccerTwos/SoccerTwos-10000134.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "0.31.0.dev0",
+        "torch_version": "1.11.0"
+    }
+}