1791 Push

README.md

@@ -0,0 +1,35 @@
+---
+library_name: ml-agents
+tags:
+- SoccerTwos
+- deep-reinforcement-learning
+- reinforcement-learning
+- ML-Agents-SoccerTwos
+---
+
+  # **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://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/
+
+  We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
+  - A *short tutorial* where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your
+  browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction
+  - A *longer tutorial* to understand how works ML-Agents:
+  https://huggingface.co/learn/deep-rl-course/unit5/introduction
+
+  ### Resume the training
+  ```bash
+  mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume
+  ```
+
+  ### Watch your Agent play
+  You can watch your agent **playing directly in your browser**
+
+  1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity
+  2. Step 1: Find your model_id: yy1636/poca-SoccerTwos-24-test0
+  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 sha256:7182269dfbab4da662a79a585dcb01aae1528048315d33dcc077523c59a043f3
+size 891096

SoccerTwos/SoccerTwos-12337036.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0518fa9da462a602f6665788483298926cd8bdee75f30353ce77b36e3849534b
+size 891096

SoccerTwos/SoccerTwos-12337036.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea99efa1f24307973e2f6c6f60282d9b75214f207c6253385fb84763c79e76e7
+size 10315570

SoccerTwos/SoccerTwos-12499879.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5790604ed0ce8643b6c470d2c6bcd58aceca7fed79e8a3e26d76656157fa3634
+size 891096

SoccerTwos/SoccerTwos-12499879.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc1a0c0af47407adc629a9c360235789186b99953a6d6e2d394cda9b9ecb96c1
+size 10315570

SoccerTwos/SoccerTwos-12851470.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:874e0993c43a58cd8ee199a3de076e836e5c1aeeb8b24f6b491b227bb3ef3ce8
+size 891096

SoccerTwos/SoccerTwos-12851470.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27583589f28e96ada1e97fce44a5daf45fbcee8cfc41d285da3a11f6200f0d04
+size 10315570

SoccerTwos/SoccerTwos-12999958.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:551554b9a33ea1e087c6bc9d072360aab47c8bc6cbe7eb1c7b26210bf97e25fe
+size 891096

SoccerTwos/SoccerTwos-12999958.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac4664377bc53921cdf47d9b1b907438efeba1e479569381d6f0bdc2602bf845
+size 10315570

SoccerTwos/SoccerTwos-13281688.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7182269dfbab4da662a79a585dcb01aae1528048315d33dcc077523c59a043f3
+size 891096

SoccerTwos/SoccerTwos-13281688.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac9961791f5dcc255746c78988892ed65658ae5f2e621d139d042a2f464f6c91
+size 10315570

SoccerTwos/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5462f0c39c0a37789eefd46b34d3e76385d462fb37454a34540a073cc1c669ce
+size 10314310

SoccerTwos/events.out.tfevents.1713936986.WP.23126.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf4b7ba3c694bbde8bce0690518532711a8ec18467633c1bc81d5a13d50b3cb0
+size 2865708

SoccerTwos/events.out.tfevents.1713939922.WP.24341.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e22f4e848be5ecda203d991d03ceb13d438630191c14ad46efcb04d3f4a8b29
+size 165423

SoccerTwos/events.out.tfevents.1713940097.WP.24602.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f76c7be1a5bc8f21d9f4ae8d3bdf812cb7ba8b5718128960e3db4f99333c62b0
+size 8100093

SoccerTwos/events.out.tfevents.1713948179.WP.27278.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7de077d500377f8d80912b95670d3e95dc24e9137f49ae184a4385c242401cf8
+size 144857

SoccerTwos/events.out.tfevents.1713948394.WP.27507.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7f207371c5ab2f6537c804809ecfb02574a5f23dd080cffc005d600a6635adb
+size 329951

SoccerTwos/events.out.tfevents.1713948742.WP.27789.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c94e942027341cf4bb4cc9069852eb1c888a3f83b44e2bbb9a1860c0a98475e
+size 52483

SoccerTwos/events.out.tfevents.1713948833.WP.28060.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c723c6b392f2f2112ef79ecc804d51f7dc79bfc784025a73b493bbdb01de2da2
+size 144857

SoccerTwos/events.out.tfevents.1713949000.WP.28254.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af8f8bf4c56f31e0ace7f97ca58173bf94b6e25883b0b6d558f310782e7bdb15
+size 535611

SoccerTwos/events.out.tfevents.1713949550.WP.28608.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93d744c460172b8ea3a5ca36c900094339ae9fbc0b3a6225ad6d2c676596d941
+size 11351

SoccerTwos/events.out.tfevents.1713949586.WP.28773.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c041f8dd881e7e61a6b4f1bd50614e586a3f359bf28c2249923cbf6679298223
+size 535265

SoccerTwos/events.out.tfevents.1713950150.WP.29162.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:084ee21863c47bfedc342b7dbc0d18ca5559689bd5fa0d3d37d172208fa9bfb8
+size 442891

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": 256, "num_layers": 3, "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": 15000000, "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, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SoccerTwos-24-test0", "initialize_from": null, "load_model": false, "resume": true, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -0,0 +1,83 @@
+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: 256
+      num_layers: 3
+      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: 15000000
+    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
+  timeout_wait: 60
+  seed: -1
+  max_lifetime_restarts: 10
+  restarts_rate_limit_n: 1
+  restarts_rate_limit_period_s: 60
+engine_settings:
+  width: 84
+  height: 84
+  quality_level: 5
+  time_scale: 20
+  target_frame_rate: -1
+  capture_frame_rate: 60
+  no_graphics: true
+environment_parameters: null
+checkpoint_settings:
+  run_id: SoccerTwos-24-test0
+  initialize_from: null
+  load_model: false
+  resume: true
+  force: false
+  train_model: false
+  inference: false
+  results_dir: results
+torch_settings:
+  device: null
+debug: false

run_logs/Player-0.log

@@ -0,0 +1,344 @@
+Mono path[0] = '/home/robot/ml-agents/training-envs-executables/SoccerTwos/SoccerTwos_Data/Managed'
+Mono config path = '/home/robot/ml-agents/training-envs-executables/SoccerTwos/SoccerTwos_Data/MonoBleedingEdge/etc'
+Preloaded 'lib_burst_generated.so'
+Preloaded 'libgrpc_csharp_ext.x64.so'
+Initialize engine version: 2021.3.14f1 (eee1884e7226)
+[Subsystems] Discovering subsystems at path /home/robot/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  0.049 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: 0.411363 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
+Setting up 10 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]: 8114 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_Job.Worker 18]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Loading.PreloadManager]
+      Initial Block Size 256.0 KB
+      Current Block Size 300.0 KB
+      Peak Allocated Bytes 249.6 KB
+      Overflow Count 4
+    [ALLOC_TEMP_Loading.AsyncRead]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 128 B
+      Overflow Count 0
+    [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_Job.Worker 16]
+      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 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 17]
+      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 10
+      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 19
+      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_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 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_Job.Worker 15]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0.7 KB
+      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 2
+    [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]: 8115 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 4.7 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 8115 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 17.5 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]: 8114 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]: 8115 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]: 8115 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]: 8114 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]: 8115 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]: 8114 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": 1.514999270439148,
+            "min": 1.489595651626587,
+            "max": 1.601452350616455,
+            "count": 43
+        },
+        "SoccerTwos.Policy.Entropy.sum": {
+            "value": 31560.46484375,
+            "min": 27883.697265625,
+            "max": 34768.91796875,
+            "count": 43
+        },
+        "SoccerTwos.Environment.EpisodeLength.mean": {
+            "value": 53.824175824175825,
+            "min": 41.13559322033898,
+            "max": 63.36363636363637,
+            "count": 43
+        },
+        "SoccerTwos.Environment.EpisodeLength.sum": {
+            "value": 19592.0,
+            "min": 16812.0,
+            "max": 20084.0,
+            "count": 43
+        },
+        "SoccerTwos.Self-play.ELO.mean": {
+            "value": 1791.723449073225,
+            "min": 1754.3428175876059,
+            "max": 1791.723449073225,
+            "count": 43
+        },
+        "SoccerTwos.Self-play.ELO.sum": {
+            "value": 326093.66773132695,
+            "min": 272477.7385629466,
+            "max": 415596.7662303577,
+            "count": 43
+        },
+        "SoccerTwos.Step.mean": {
+            "value": 13279943.0,
+            "min": 12859946.0,
+            "max": 13279943.0,
+            "count": 43
+        },
+        "SoccerTwos.Step.sum": {
+            "value": 13279943.0,
+            "min": 12859946.0,
+            "max": 13279943.0,
+            "count": 43
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
+            "value": 0.06306133419275284,
+            "min": -0.05972757562994957,
+            "max": 0.07309861481189728,
+            "count": 43
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
+            "value": 11.47716236114502,
+            "min": -10.930146217346191,
+            "max": 14.181131362915039,
+            "count": 43
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 0.06298738718032837,
+            "min": -0.055884044617414474,
+            "max": 0.0707717165350914,
+            "count": 43
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 11.463704109191895,
+            "min": -10.22677993774414,
+            "max": 13.729713439941406,
+            "count": 43
+        },
+        "SoccerTwos.Environment.CumulativeReward.mean": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 43
+        },
+        "SoccerTwos.Environment.CumulativeReward.sum": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 43
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.mean": {
+            "value": 0.14293516337216555,
+            "min": -0.2126644797663871,
+            "max": 0.22874545199530466,
+            "count": 43
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.sum": {
+            "value": 26.01419973373413,
+            "min": -38.91759979724884,
+            "max": 42.61020004749298,
+            "count": 43
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.mean": {
+            "value": 0.14293516337216555,
+            "min": -0.2126644797663871,
+            "max": 0.22874545199530466,
+            "count": 43
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.sum": {
+            "value": 26.01419973373413,
+            "min": -38.91759979724884,
+            "max": 42.61020004749298,
+            "count": 43
+        },
+        "SoccerTwos.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 43
+        },
+        "SoccerTwos.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 43
+        },
+        "SoccerTwos.Losses.PolicyLoss.mean": {
+            "value": 0.01759544127077485,
+            "min": 0.011227267006567369,
+            "max": 0.020452462819715342,
+            "count": 20
+        },
+        "SoccerTwos.Losses.PolicyLoss.sum": {
+            "value": 0.01759544127077485,
+            "min": 0.011227267006567369,
+            "max": 0.020452462819715342,
+            "count": 20
+        },
+        "SoccerTwos.Losses.ValueLoss.mean": {
+            "value": 0.11412317032615343,
+            "min": 0.10178396105766296,
+            "max": 0.12401819825172425,
+            "count": 20
+        },
+        "SoccerTwos.Losses.ValueLoss.sum": {
+            "value": 0.11412317032615343,
+            "min": 0.10178396105766296,
+            "max": 0.12401819825172425,
+            "count": 20
+        },
+        "SoccerTwos.Losses.BaselineLoss.mean": {
+            "value": 0.11528436491886775,
+            "min": 0.1030850184460481,
+            "max": 0.1254842718442281,
+            "count": 20
+        },
+        "SoccerTwos.Losses.BaselineLoss.sum": {
+            "value": 0.11528436491886775,
+            "min": 0.1030850184460481,
+            "max": 0.1254842718442281,
+            "count": 20
+        },
+        "SoccerTwos.Policy.LearningRate.mean": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 20
+        },
+        "SoccerTwos.Policy.LearningRate.sum": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 20
+        },
+        "SoccerTwos.Policy.Epsilon.mean": {
+            "value": 0.20000000000000007,
+            "min": 0.20000000000000007,
+            "max": 0.20000000000000007,
+            "count": 20
+        },
+        "SoccerTwos.Policy.Epsilon.sum": {
+            "value": 0.20000000000000007,
+            "min": 0.20000000000000007,
+            "max": 0.20000000000000007,
+            "count": 20
+        },
+        "SoccerTwos.Policy.Beta.mean": {
+            "value": 0.005000000000000001,
+            "min": 0.005000000000000001,
+            "max": 0.005000000000000001,
+            "count": 20
+        },
+        "SoccerTwos.Policy.Beta.sum": {
+            "value": 0.005000000000000001,
+            "min": 0.005000000000000001,
+            "max": 0.005000000000000001,
+            "count": 20
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1713950149",
+        "python_version": "3.10.12 (main, Jul  5 2023, 18:54:27) [GCC 11.2.0]",
+        "command_line_arguments": "/home/robot/anaconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos-24-test0.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos-24-test0 --no-graphics --resume",
+        "mlagents_version": "1.0.0",
+        "mlagents_envs_version": "1.0.0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "2.2.2+cu121",
+        "numpy_version": "1.23.5",
+        "end_time_seconds": "1713950607"
+    },
+    "total": 457.3718859350047,
+    "count": 1,
+    "self": 0.1159048219997203,
+    "children": {
+        "run_training.setup": {
+            "total": 0.01975632600078825,
+            "count": 1,
+            "self": 0.01975632600078825
+        },
+        "TrainerController.start_learning": {
+            "total": 457.2362247870042,
+            "count": 1,
+            "self": 0.4582937658269657,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 1.0023442019955837,
+                    "count": 4,
+                    "self": 1.0023442019955837
+                },
+                "TrainerController.advance": {
+                    "total": 455.67333012618474,
+                    "count": 30291,
+                    "self": 0.4562869664368918,
+                    "children": {
+                        "env_step": {
+                            "total": 352.1429776112709,
+                            "count": 30291,
+                            "self": 262.03236804751214,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 89.82456818577339,
+                                    "count": 30291,
+                                    "self": 2.607199358084472,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 87.21736882768892,
+                                            "count": 54098,
+                                            "self": 87.21736882768892
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 0.2860413779853843,
+                                    "count": 30290,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 456.40040704779676,
+                                            "count": 30290,
+                                            "is_parallel": true,
+                                            "self": 242.38395667484292,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.0015634679948561825,
+                                                            "count": 2,
+                                                            "is_parallel": true,
+                                                            "self": 0.0003977819869760424,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.00116568600788014,
+                                                                    "count": 8,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00116568600788014
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.017318722006166354,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0003682690003188327,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.0002611540039652027,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0002611540039652027
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.015684391000831965,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.015684391000831965
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.001004908001050353,
+                                                                    "count": 2,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00019816600979538634,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.0008067419912549667,
+                                                                            "count": 8,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.0008067419912549667
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "steps_from_proto": {
+                                                    "total": 0.003151374992739875,
+                                                    "count": 6,
+                                                    "is_parallel": true,
+                                                    "self": 0.0005871999965165742,
+                                                    "children": {
+                                                        "_process_rank_one_or_two_observation": {
+                                                            "total": 0.0025641749962233007,
+                                                            "count": 24,
+                                                            "is_parallel": true,
+                                                            "self": 0.0025641749962233007
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 214.0132989979611,
+                                                    "count": 30289,
+                                                    "is_parallel": true,
+                                                    "self": 11.56873725906189,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 6.9204708298057085,
+                                                            "count": 30289,
+                                                            "is_parallel": true,
+                                                            "self": 6.9204708298057085
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 164.13787390717334,
+                                                            "count": 30289,
+                                                            "is_parallel": true,
+                                                            "self": 164.13787390717334
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 31.38621700192016,
+                                                            "count": 60578,
+                                                            "is_parallel": true,
+                                                            "self": 5.944496136136877,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 25.44172086578328,
+                                                                    "count": 242312,
+                                                                    "is_parallel": true,
+                                                                    "self": 25.44172086578328
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 103.07406554847694,
+                            "count": 30290,
+                            "self": 3.120524487036164,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 52.969188115421275,
+                                    "count": 30290,
+                                    "self": 52.89213044641656,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 0.07705766900471644,
+                                            "count": 1,
+                                            "self": 0.07705766900471644
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 46.9843529460195,
+                                    "count": 20,
+                                    "self": 29.815163639934326,
+                                    "children": {
+                                        "TorchPOCAOptimizer.update": {
+                                            "total": 17.169189306085173,
+                                            "count": 600,
+                                            "self": 17.169189306085173
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 7.839989848434925e-07,
+                    "count": 1,
+                    "self": 7.839989848434925e-07
+                },
+                "TrainerController._save_models": {
+                    "total": 0.10225590899790404,
+                    "count": 1,
+                    "self": 0.0007471069984603673,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.10150880199944368,
+                            "count": 1,
+                            "self": 0.10150880199944368
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,66 @@
+{
+    "SoccerTwos": {
+        "checkpoints": [
+            {
+                "steps": 12337036,
+                "file_path": "results/SoccerTwos-24-test0/SoccerTwos/SoccerTwos-12337036.onnx",
+                "reward": 0.0,
+                "creation_time": 1713949564.889125,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos-24-test0/SoccerTwos/SoccerTwos-12337036.pt"
+                ]
+            },
+            {
+                "steps": 12499879,
+                "file_path": "results/SoccerTwos-24-test0/SoccerTwos/SoccerTwos-12499879.onnx",
+                "reward": 0.0,
+                "creation_time": 1713949754.703464,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos-24-test0/SoccerTwos/SoccerTwos-12499879.pt"
+                ]
+            },
+            {
+                "steps": 12851470,
+                "file_path": "results/SoccerTwos-24-test0/SoccerTwos/SoccerTwos-12851470.onnx",
+                "reward": null,
+                "creation_time": 1713950128.535202,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos-24-test0/SoccerTwos/SoccerTwos-12851470.pt"
+                ]
+            },
+            {
+                "steps": 12999958,
+                "file_path": "results/SoccerTwos-24-test0/SoccerTwos/SoccerTwos-12999958.onnx",
+                "reward": 0.0,
+                "creation_time": 1713950306.6465962,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos-24-test0/SoccerTwos/SoccerTwos-12999958.pt"
+                ]
+            },
+            {
+                "steps": 13281688,
+                "file_path": "results/SoccerTwos-24-test0/SoccerTwos/SoccerTwos-13281688.onnx",
+                "reward": 0.0,
+                "creation_time": 1713950607.0127492,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos-24-test0/SoccerTwos/SoccerTwos-13281688.pt"
+                ]
+            }
+        ],
+        "elo": 1801.9175222306308,
+        "final_checkpoint": {
+            "steps": 13281688,
+            "file_path": "results/SoccerTwos-24-test0/SoccerTwos.onnx",
+            "reward": 0.0,
+            "creation_time": 1713950607.0127492,
+            "auxillary_file_paths": [
+                "results/SoccerTwos-24-test0/SoccerTwos/SoccerTwos-13281688.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "1.0.0",
+        "torch_version": "2.2.2+cu121"
+    }
+}