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: osbm/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:f4bb7ffab05107280b5327012e7e8e055d5c583d316fcb6adef215c1e63f87bc
+size 1764633

SoccerTwos/SoccerTwos-499718.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48b6173ab2fb9b76746ba76065f057c9b892b4fc560dbd6f14dc56de51b01eb9
+size 1764633

SoccerTwos/SoccerTwos-499718.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c039a484a7a26300679223d30410dcb30c901a637a291ddc11a9662a668a450a
+size 28422481

SoccerTwos/SoccerTwos-544800.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4bb7ffab05107280b5327012e7e8e055d5c583d316fcb6adef215c1e63f87bc
+size 1764633

SoccerTwos/SoccerTwos-544800.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93fe925693d473ba87805f992d70e5be6c530c06f47209bc39098fb97022793b
+size 28422481

SoccerTwos/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93fe925693d473ba87805f992d70e5be6c530c06f47209bc39098fb97022793b
+size 28422481

SoccerTwos/events.out.tfevents.1682521439.volkan.26629.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4424b1b6d1cafd7302df52b7978d8f3b7cf3bfadb55731e368a29bd86cddb03
+size 378068

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": 50000000, "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": "./training-envs-executables/SoccerTwos/SoccerTwos.x86_64", "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: 50000000
+    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: ./training-envs-executables/SoccerTwos/SoccerTwos.x86_64
+  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 +1,513 @@
+Mono path[0] = '/home/osman/Documents/GitHub/hf-rl-chapter-7/ml-agents/training-envs-executables/SoccerTwos/SoccerTwos_Data/Managed'
+Mono config path = '/home/osman/Documents/GitHub/hf-rl-chapter-7/ml-agents/training-envs-executables/SoccerTwos/SoccerTwos_Data/MonoBleedingEdge/etc'
+Preloaded 'lib_burst_generated.so'
+Preloaded 'libgrpc_csharp_ext.x64.so'
+PlayerPrefs - Creating folder: /home/osman/.config/unity3d/Unity Technologies
+PlayerPrefs - Creating folder: /home/osman/.config/unity3d/Unity Technologies/SoccerTwos
+Unable to load player prefs
+Initialize engine version: 2021.3.14f1 (eee1884e7226)
+[Subsystems] Discovering subsystems at path /home/osman/Documents/GitHub/hf-rl-chapter-7/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  0.051 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: 0.471846 ms
+Registered Communicator in Agent.
+ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+requesting resize 84 x 84
+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
+GRPC Exception: Status(StatusCode=Unknown, Detail="Exception calling application: [Errno 32] Broken pipe"). Disconnecting from trainer.
+Setting up 4 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]: 10563 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 134 B
+      Overflow Count 0
+    [ALLOC_TEMP_Loading.PreloadManager]
+      Initial Block Size 256.0 KB
+      Current Block Size 300.0 KB
+      Peak Allocated Bytes 249.7 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 3]
+      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 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 4
+      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 7
+      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_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_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 3
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 1.0 MB
+    [ALLOC_DEFAULT_MAIN]
+      Peak usage frame count: [4.0 MB-8.0 MB]: 10564 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 4.8 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 10564 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 1.0 MB
+    [ALLOC_GFX_MAIN]
+      Peak usage frame count: [32.0 KB-64.0 KB]: 10563 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]: 10564 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 1.0 MB
+    [ALLOC_CACHEOBJECTS_MAIN]
+      Peak usage frame count: [0.5 MB-1.0 MB]: 10564 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]: 10563 frames, [4.0 MB-8.0 MB]: 1 frames
+      Requested Block Size 4.0 MB
+      Peak Block count 2
+      Peak Allocated memory 4.5 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 1.0 MB
+    [ALLOC_TYPETREE_MAIN]
+      Peak usage frame count: [0-1.0 KB]: 10564 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]: 10563 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 +1,424 @@
+{
+    "name": "root",
+    "gauges": {
+        "SoccerTwos.Policy.Entropy.mean": {
+            "value": 3.2107036113739014,
+            "min": 3.2107036113739014,
+            "max": 3.2957074642181396,
+            "count": 54
+        },
+        "SoccerTwos.Policy.Entropy.sum": {
+            "value": 57022.09765625,
+            "min": 19751.228515625,
+            "max": 120480.046875,
+            "count": 54
+        },
+        "SoccerTwos.Environment.EpisodeLength.mean": {
+            "value": 820.0,
+            "min": 410.0833333333333,
+            "max": 999.0,
+            "count": 54
+        },
+        "SoccerTwos.Environment.EpisodeLength.sum": {
+            "value": 19680.0,
+            "min": 17484.0,
+            "max": 23316.0,
+            "count": 54
+        },
+        "SoccerTwos.Self-play.ELO.mean": {
+            "value": 1194.4402875724832,
+            "min": 1191.8185477132163,
+            "max": 1202.0502547782216,
+            "count": 48
+        },
+        "SoccerTwos.Self-play.ELO.sum": {
+            "value": 4777.761150289933,
+            "min": 2386.682498380749,
+            "max": 16738.525213557245,
+            "count": 48
+        },
+        "SoccerTwos.Step.mean": {
+            "value": 539736.0,
+            "min": 9722.0,
+            "max": 539736.0,
+            "count": 54
+        },
+        "SoccerTwos.Step.sum": {
+            "value": 539736.0,
+            "min": 9722.0,
+            "max": 539736.0,
+            "count": 54
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
+            "value": -0.016038794070482254,
+            "min": -0.028663326054811478,
+            "max": 0.01893448457121849,
+            "count": 54
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
+            "value": -0.208504319190979,
+            "min": -0.43301811814308167,
+            "max": 0.28401726484298706,
+            "count": 54
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
+            "value": -0.015257940627634525,
+            "min": -0.0349409244954586,
+            "max": 0.018840912729501724,
+            "count": 54
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
+            "value": -0.19835323095321655,
+            "min": -0.5032390356063843,
+            "max": 0.2825426161289215,
+            "count": 54
+        },
+        "SoccerTwos.Environment.CumulativeReward.mean": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 54
+        },
+        "SoccerTwos.Environment.CumulativeReward.sum": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 54
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.mean": {
+            "value": -0.253753845508282,
+            "min": -0.46153846153846156,
+            "max": 0.37597333590189613,
+            "count": 54
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.sum": {
+            "value": -3.298799991607666,
+            "min": -9.589199990034103,
+            "max": 5.639600038528442,
+            "count": 54
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.mean": {
+            "value": -0.253753845508282,
+            "min": -0.46153846153846156,
+            "max": 0.37597333590189613,
+            "count": 54
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.sum": {
+            "value": -3.298799991607666,
+            "min": -9.589199990034103,
+            "max": 5.639600038528442,
+            "count": 54
+        },
+        "SoccerTwos.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 54
+        },
+        "SoccerTwos.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 54
+        },
+        "SoccerTwos.Losses.PolicyLoss.mean": {
+            "value": 0.018719479351178354,
+            "min": 0.011478485410043504,
+            "max": 0.021412606455851347,
+            "count": 25
+        },
+        "SoccerTwos.Losses.PolicyLoss.sum": {
+            "value": 0.018719479351178354,
+            "min": 0.011478485410043504,
+            "max": 0.021412606455851347,
+            "count": 25
+        },
+        "SoccerTwos.Losses.ValueLoss.mean": {
+            "value": 0.0013482887239661067,
+            "min": 0.0012590042082592846,
+            "max": 0.004628484478841225,
+            "count": 25
+        },
+        "SoccerTwos.Losses.ValueLoss.sum": {
+            "value": 0.0013482887239661067,
+            "min": 0.0012590042082592846,
+            "max": 0.004628484478841225,
+            "count": 25
+        },
+        "SoccerTwos.Losses.BaselineLoss.mean": {
+            "value": 0.0015571090955442438,
+            "min": 0.0012690392807902147,
+            "max": 0.0047715426655486224,
+            "count": 25
+        },
+        "SoccerTwos.Losses.BaselineLoss.sum": {
+            "value": 0.0015571090955442438,
+            "min": 0.0012690392807902147,
+            "max": 0.0047715426655486224,
+            "count": 25
+        },
+        "SoccerTwos.Policy.LearningRate.mean": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 25
+        },
+        "SoccerTwos.Policy.LearningRate.sum": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 25
+        },
+        "SoccerTwos.Policy.Epsilon.mean": {
+            "value": 0.20000000000000007,
+            "min": 0.20000000000000007,
+            "max": 0.20000000000000007,
+            "count": 25
+        },
+        "SoccerTwos.Policy.Epsilon.sum": {
+            "value": 0.20000000000000007,
+            "min": 0.20000000000000007,
+            "max": 0.20000000000000007,
+            "count": 25
+        },
+        "SoccerTwos.Policy.Beta.mean": {
+            "value": 0.005000000000000001,
+            "min": 0.005000000000000001,
+            "max": 0.005000000000000001,
+            "count": 25
+        },
+        "SoccerTwos.Policy.Beta.sum": {
+            "value": 0.005000000000000001,
+            "min": 0.005000000000000001,
+            "max": 0.005000000000000001,
+            "count": 25
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1682521439",
+        "python_version": "3.9.12 (main, Jun  1 2022, 11:38:51) \n[GCC 7.5.0]",
+        "command_line_arguments": "/home/osman/.pyenv/versions/miniconda3-4.7.12/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --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+cu102",
+        "numpy_version": "1.21.2",
+        "end_time_seconds": "1682525292"
+    },
+    "total": 3853.2143541509995,
+    "count": 1,
+    "self": 0.03964080599871522,
+    "children": {
+        "run_training.setup": {
+            "total": 0.011409361999540124,
+            "count": 1,
+            "self": 0.011409361999540124
+        },
+        "TrainerController.start_learning": {
+            "total": 3853.1633039830012,
+            "count": 1,
+            "self": 0.8838827939034672,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 2.1896473490014614,
+                    "count": 3,
+                    "self": 2.1896473490014614
+                },
+                "TrainerController.advance": {
+                    "total": 3849.8151345830956,
+                    "count": 35469,
+                    "self": 1.012086826023733,
+                    "children": {
+                        "env_step": {
+                            "total": 3524.0637932190184,
+                            "count": 35469,
+                            "self": 3366.3506852638566,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 157.15537886607672,
+                                    "count": 35469,
+                                    "self": 6.24865723907169,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 150.90672162700503,
+                                            "count": 70422,
+                                            "self": 150.90672162700503
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 0.5577290890851145,
+                                    "count": 35468,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 3851.248489515987,
+                                            "count": 35468,
+                                            "is_parallel": true,
+                                            "self": 586.9425321369217,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.002904982999098138,
+                                                            "count": 2,
+                                                            "is_parallel": true,
+                                                            "self": 0.000577157998122857,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.002327825000975281,
+                                                                    "count": 8,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.002327825000975281
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.12336154600052396,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.00018118299885827582,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.002515493000828428,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.002515493000828428
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.1184253510000417,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.1184253510000417
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.0022395190007955534,
+                                                                    "count": 2,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.000321391002216842,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.0019181279985787114,
+                                                                            "count": 8,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.0019181279985787114
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 3264.3009966850623,
+                                                    "count": 35467,
+                                                    "is_parallel": true,
+                                                    "self": 9.9563358037758,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 60.41453447101594,
+                                                            "count": 35467,
+                                                            "is_parallel": true,
+                                                            "self": 60.41453447101594
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 3081.7995622021717,
+                                                            "count": 35467,
+                                                            "is_parallel": true,
+                                                            "self": 3081.7995622021717
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 112.1305642080988,
+                                                            "count": 70934,
+                                                            "is_parallel": true,
+                                                            "self": 16.36381647961207,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 95.76674772848673,
+                                                                    "count": 283736,
+                                                                    "is_parallel": true,
+                                                                    "self": 95.76674772848673
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "steps_from_proto": {
+                                                    "total": 0.004960694002875243,
+                                                    "count": 4,
+                                                    "is_parallel": true,
+                                                    "self": 0.0007037500072328839,
+                                                    "children": {
+                                                        "_process_rank_one_or_two_observation": {
+                                                            "total": 0.004256943995642359,
+                                                            "count": 16,
+                                                            "is_parallel": true,
+                                                            "self": 0.004256943995642359
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 324.7392545380535,
+                            "count": 35468,
+                            "self": 5.901465543018276,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 59.90979997703835,
+                                    "count": 35468,
+                                    "self": 59.71050950603785,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 0.19929047100049502,
+                                            "count": 1,
+                                            "self": 0.19929047100049502
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 258.9279890179969,
+                                    "count": 25,
+                                    "self": 73.02800088002914,
+                                    "children": {
+                                        "TorchPOCAOptimizer.update": {
+                                            "total": 185.89998813796774,
+                                            "count": 750,
+                                            "self": 185.89998813796774
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 2.2120002540759742e-06,
+                    "count": 1,
+                    "self": 2.2120002540759742e-06
+                },
+                "TrainerController._save_models": {
+                    "total": 0.27463704500041786,
+                    "count": 1,
+                    "self": 0.0014027090001036413,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.2732343360003142,
+                            "count": 1,
+                            "self": 0.2732343360003142
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,39 @@
+{
+    "SoccerTwos": {
+        "checkpoints": [
+            {
+                "steps": 499718,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-499718.onnx",
+                "reward": 0.0,
+                "creation_time": 1682524996.8540874,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-499718.pt"
+                ]
+            },
+            {
+                "steps": 544800,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-544800.onnx",
+                "reward": 0.0,
+                "creation_time": 1682525292.3198645,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-544800.pt"
+                ]
+            }
+        ],
+        "elo": 1194.4402875724832,
+        "final_checkpoint": {
+            "steps": 544800,
+            "file_path": "results/SoccerTwos/SoccerTwos.onnx",
+            "reward": 0.0,
+            "creation_time": 1682525292.3198645,
+            "auxillary_file_paths": [
+                "results/SoccerTwos/SoccerTwos/SoccerTwos-544800.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "0.31.0.dev0",
+        "torch_version": "1.11.0+cu102"
+    }
+}