First 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: ahmadsyy/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 sha256:69f0e6e2805958cda451132abcf52ab3631a28c39f2429d2fd4c9901d668c4b1
+size 1768747

SoccerTwos/SoccerTwos-1500254.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cad7a994eacc8cd1cd8cb83e973e1619c85be134fd176b303f0a7c0a88151554
+size 1768747

SoccerTwos/SoccerTwos-1500254.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:215383efcb63827ea32623bf9c9d40a50e5b71a9a27ef2b63511f4ff962ba94f
+size 28430358

SoccerTwos/SoccerTwos-1999918.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:351a56213c628e834412426f2b64435667390f6e369467b5b9c65607b0afdcd8
+size 1768747

SoccerTwos/SoccerTwos-1999918.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8470ca30142d3d4c6e3247a23f0e31eb2bf2d07995e23dd1ab1d1a331c46b96
+size 28430358

SoccerTwos/SoccerTwos-2434288.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f89f7a9eea2396ab7a2af02ccb8a4cf4081d00cdc4785cc85996d7a8d79555cc
+size 1768747

SoccerTwos/SoccerTwos-2434288.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81ff3145a05a9e8d886a208ad1d37bde1f8c7051dae2c18c649f2424777082bb
+size 28430358

SoccerTwos/SoccerTwos-2499994.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64d79f50fa3c02aa1a9cce866cbe144c58c821589e0557300b1d12140df24589
+size 1768747

SoccerTwos/SoccerTwos-2499994.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1118bb60cd39ce6cfdaa837f8c214d6192c4a28c1f89b50a2c9227355c5426c5
+size 28430358

SoccerTwos/SoccerTwos-2595280.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69f0e6e2805958cda451132abcf52ab3631a28c39f2429d2fd4c9901d668c4b1
+size 1768747

SoccerTwos/SoccerTwos-2595280.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20dc7e542b9cff8fa915028009458570f153b386071cd4f13d34367b838ebfad
+size 28430358

SoccerTwos/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cfd81fc578e9a14e3509037c8685eca53447114b61e48d25d46cc3da937ff8d
+size 28429366

SoccerTwos/events.out.tfevents.1732006577.DESKTOP-BQV6K1N.21540.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22bfde5d3e951f3d0281a81980237b7ca53d15e57399c1776f998662791a07e9
+size 331001

SoccerTwos/events.out.tfevents.1732008793.DESKTOP-BQV6K1N.23304.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ab4bf5eded8485f39ace3808aca6f62e7ec31b9d4bf7235ee27650deee57742
+size 1239

SoccerTwos/events.out.tfevents.1732009617.DESKTOP-BQV6K1N.7832.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5673e410572586e3098967a320e405604cc4e86b353d493ad65f156f087e1164
+size 513836

SoccerTwos/events.out.tfevents.1732082384.DESKTOP-BQV6K1N.13736.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17fa2212f3e69e13b6c600023355dce58eaf3c21601ae772b2cea3782a9a5055
+size 11339

SoccerTwos/events.out.tfevents.1732082452.DESKTOP-BQV6K1N.26240.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1dc8d64a66ea574458a4aeef0c86711b39894790bdef068df0be96d0ee4adfe0
+size 11338

SoccerTwos/events.out.tfevents.1732082516.DESKTOP-BQV6K1N.26548.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:608d3d11ea6500961f73727aa31f9d81f33014b6545c267e88f6a13f5b21d67e
+size 32219

SoccerTwos/events.out.tfevents.1732082647.DESKTOP-BQV6K1N.20244.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98ca793453f34feb917d6fae7d2f48b109c9c76147110ea7eca2f46be2d0c60c
+size 470020

SoccerTwos/events.out.tfevents.1732085078.DESKTOP-BQV6K1N.5244.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ed3bbbe90ae69adc3eb6ae6be861c58b114ec1df13d348f45fe78ae0d271ab7
+size 971339

SoccerTwos/events.out.tfevents.1732088295.DESKTOP-BQV6K1N.24736.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f4151e11e46d59afd4faedd34d26e7fc14f5b15eb89743d0dcf71f74fb4ea1b
+size 168191

config.json

@@ -0,0 +1 @@
+{"default_settings": null, "behaviors": {"SoccerTwos": {"trainer_type": "poca", "hyperparameters": {"batch_size": 1028, "buffer_size": 10240, "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": "./training-envs-executables/SoccerTwos/SoccerTwos.exe", "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, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SoccerTwos", "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 +1,84 @@
+default_settings: null
+behaviors:
+  SoccerTwos:
+    trainer_type: poca
+    hyperparameters:
+      batch_size: 1028
+      buffer_size: 10240
+      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: ./training-envs-executables/SoccerTwos/SoccerTwos.exe
+  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
+  no_graphics_monitor: false
+environment_parameters: null
+checkpoint_settings:
+  run_id: SoccerTwos
+  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 +1,282 @@
+Mono path[0] = 'D:/python projects/ml-agents/training-envs-executables/SoccerTwos/SoccerTwos_Data/Managed'
+Mono config path = 'D:/python projects/ml-agents/training-envs-executables/SoccerTwos/MonoBleedingEdge/etc'
+Initialize engine version: 2021.3.14f1 (eee1884e7226)
+[Subsystems] Discovering subsystems at path D:/python projects/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  0.345 seconds
+ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+Microsoft Media Foundation video decoding to texture disabled: graphics device is Null, only Direct3D 11 and Direct3D 12 (only on desktop) are supported for hardware-accelerated video decoding.
+ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+WARNING: Shader Unsupported: 'Standard (Specular setup)' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
+ERROR: Shader Standard (Specular setup) shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+WARNING: Shader Unsupported: 'Standard (Specular setup)' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
+WARNING: Shader Unsupported: 'Autodesk Interactive' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
+ERROR: Shader Autodesk Interactive shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+WARNING: Shader Unsupported: 'Autodesk Interactive' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
+WARNING: Shader Unsupported: 'Standard' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
+ERROR: Shader Standard shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+WARNING: Shader Unsupported: 'Standard' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
+UnloadTime: 0.728800 ms
+Registered Communicator in Agent.
+ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+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]: 3029 frames, [2.0 MB-4.0 MB]: 1 frames
+      Initial Block Size 4.0 MB
+      Current Block Size 4.0 MB
+      Peak Allocated Bytes 2.0 MB
+      Overflow Count 0
+    [ALLOC_TEMP_Loading.AsyncRead]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 324 B
+      Overflow Count 0
+    [ALLOC_TEMP_Loading.PreloadManager]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 67.1 KB
+      Overflow Count 4
+    [ALLOC_TEMP_Background Job.Worker 8]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 54 B
+      Overflow Count 0
+    [ALLOC_TEMP_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 54 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 9]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 54 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 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 54 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 6]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 54 B
+      Overflow Count 0
+    [ALLOC_TEMP_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 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 12]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 54 B
+      Overflow Count 0
+    [ALLOC_TEMP_EnlightenWorker] x 4
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 54 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 15]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 54 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 1]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 54 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 2]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 54 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 7]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 54 B
+      Overflow Count 0
+    [ALLOC_TEMP_AssetGarbageCollectorHelper] x 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 54 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 13]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 54 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 1]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 2]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0.8 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 3]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 54 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 11]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 54 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 0]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 54 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 4]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 54 B
+      Overflow Count 0
+    [ALLOC_TEMP_BatchDeleteObjects]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 54 B
+      Overflow Count 0
+[ALLOC_DEFAULT] Dual Thread Allocator
+  Peak main deferred allocation count 3
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 0.9 MB
+    [ALLOC_DEFAULT_MAIN]
+      Peak usage frame count: [4.0 MB-8.0 MB]: 3030 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 5.0 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 3030 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 17.3 MB
+      Peak Large allocation bytes 16.0 MB
+[ALLOC_TEMP_JOB_1_FRAME]
+  Initial Block Size 2.0 MB
+  Used Block Count 1
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_TEMP_JOB_2_FRAMES]
+  Initial Block Size 2.0 MB
+  Used Block Count 1
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_TEMP_JOB_4_FRAMES (JobTemp)]
+  Initial Block Size 2.0 MB
+  Used Block Count 2
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_TEMP_JOB_ASYNC (Background)]
+  Initial Block Size 1.0 MB
+  Used Block Count 3
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_GFX] Dual Thread Allocator
+  Peak main deferred allocation count 0
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 0.9 MB
+    [ALLOC_GFX_MAIN]
+      Peak usage frame count: [32.0 KB-64.0 KB]: 3029 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]: 3030 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 173.6 KB
+      Peak Large allocation bytes 0 B
+[ALLOC_CACHEOBJECTS] Dual Thread Allocator
+  Peak main deferred allocation count 2
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 0.9 MB
+    [ALLOC_CACHEOBJECTS_MAIN]
+      Peak usage frame count: [0.5 MB-1.0 MB]: 3030 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]: 3029 frames, [2.0 MB-4.0 MB]: 1 frames
+      Requested Block Size 4.0 MB
+      Peak Block count 1
+      Peak Allocated memory 3.2 MB
+      Peak Large allocation bytes 0 B
+[ALLOC_TYPETREE] Dual Thread Allocator
+  Peak main deferred allocation count 0
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 0.9 MB
+    [ALLOC_TYPETREE_MAIN]
+      Peak usage frame count: [0-1.0 KB]: 3030 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]: 3029 frames, [2.0 KB-4.0 KB]: 1 frames
+      Requested Block Size 2.0 MB
+      Peak Block count 1
+      Peak Allocated memory 2.2 KB
+      Peak Large allocation bytes 0 B

run_logs/timers.json

@@ -0,0 +1,368 @@
+{
+    "name": "root",
+    "gauges": {
+        "SoccerTwos.Policy.Entropy.mean": {
+            "value": 2.1043341159820557,
+            "min": 2.0979535579681396,
+            "max": 2.1590776443481445,
+            "count": 16
+        },
+        "SoccerTwos.Policy.Entropy.sum": {
+            "value": 43972.1640625,
+            "min": 26032.80859375,
+            "max": 45091.49609375,
+            "count": 16
+        },
+        "SoccerTwos.Environment.EpisodeLength.mean": {
+            "value": 59.036144578313255,
+            "min": 43.96875,
+            "max": 80.04838709677419,
+            "count": 16
+        },
+        "SoccerTwos.Environment.EpisodeLength.sum": {
+            "value": 19600.0,
+            "min": 11256.0,
+            "max": 20152.0,
+            "count": 16
+        },
+        "SoccerTwos.Self-play.ELO.mean": {
+            "value": 1371.4343926038857,
+            "min": 1351.258794107496,
+            "max": 1376.8250075552155,
+            "count": 16
+        },
+        "SoccerTwos.Self-play.ELO.sum": {
+            "value": 227658.10917224502,
+            "min": 168379.3515789552,
+            "max": 295067.20596112404,
+            "count": 16
+        },
+        "SoccerTwos.Step.mean": {
+            "value": 2589954.0,
+            "min": 2439951.0,
+            "max": 2589954.0,
+            "count": 16
+        },
+        "SoccerTwos.Step.sum": {
+            "value": 2589954.0,
+            "min": 2439951.0,
+            "max": 2589954.0,
+            "count": 16
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
+            "value": -0.0010260975686833262,
+            "min": -0.042237937450408936,
+            "max": 0.05772840976715088,
+            "count": 16
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
+            "value": -0.1703321933746338,
+            "min": -7.180449485778809,
+            "max": 10.557044982910156,
+            "count": 16
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
+            "value": -0.0008884711423888803,
+            "min": -0.0447610504925251,
+            "max": 0.06113218888640404,
+            "count": 16
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
+            "value": -0.14748620986938477,
+            "min": -7.609378337860107,
+            "max": 10.162272453308105,
+            "count": 16
+        },
+        "SoccerTwos.Environment.CumulativeReward.mean": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 16
+        },
+        "SoccerTwos.Environment.CumulativeReward.sum": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 16
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.mean": {
+            "value": -0.08471084287367671,
+            "min": -0.16729411903549643,
+            "max": 0.12818064516590488,
+            "count": 16
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.sum": {
+            "value": -14.061999917030334,
+            "min": -28.440000236034393,
+            "max": 20.809599995613098,
+            "count": 16
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.mean": {
+            "value": -0.08471084287367671,
+            "min": -0.16729411903549643,
+            "max": 0.12818064516590488,
+            "count": 16
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.sum": {
+            "value": -14.061999917030334,
+            "min": -28.440000236034393,
+            "max": 20.809599995613098,
+            "count": 16
+        },
+        "SoccerTwos.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 16
+        },
+        "SoccerTwos.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 16
+        },
+        "SoccerTwos.Losses.PolicyLoss.mean": {
+            "value": 0.022567808740185918,
+            "min": 0.019185953977284953,
+            "max": 0.027850079436407046,
+            "count": 15
+        },
+        "SoccerTwos.Losses.PolicyLoss.sum": {
+            "value": 0.022567808740185918,
+            "min": 0.019185953977284953,
+            "max": 0.027850079436407046,
+            "count": 15
+        },
+        "SoccerTwos.Losses.ValueLoss.mean": {
+            "value": 0.09001306472001253,
+            "min": 0.08273657162984212,
+            "max": 0.11319424932201703,
+            "count": 15
+        },
+        "SoccerTwos.Losses.ValueLoss.sum": {
+            "value": 0.09001306472001253,
+            "min": 0.08273657162984212,
+            "max": 0.11319424932201703,
+            "count": 15
+        },
+        "SoccerTwos.Losses.BaselineLoss.mean": {
+            "value": 0.09164557605981827,
+            "min": 0.0842846728861332,
+            "max": 0.11616631199916204,
+            "count": 15
+        },
+        "SoccerTwos.Losses.BaselineLoss.sum": {
+            "value": 0.09164557605981827,
+            "min": 0.0842846728861332,
+            "max": 0.11616631199916204,
+            "count": 15
+        },
+        "SoccerTwos.Policy.LearningRate.mean": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 15
+        },
+        "SoccerTwos.Policy.LearningRate.sum": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 15
+        },
+        "SoccerTwos.Policy.Epsilon.mean": {
+            "value": 0.20000000000000004,
+            "min": 0.20000000000000004,
+            "max": 0.20000000000000007,
+            "count": 15
+        },
+        "SoccerTwos.Policy.Epsilon.sum": {
+            "value": 0.20000000000000004,
+            "min": 0.20000000000000004,
+            "max": 0.20000000000000007,
+            "count": 15
+        },
+        "SoccerTwos.Policy.Beta.mean": {
+            "value": 0.005,
+            "min": 0.005,
+            "max": 0.005000000000000001,
+            "count": 15
+        },
+        "SoccerTwos.Policy.Beta.sum": {
+            "value": 0.005,
+            "min": 0.005,
+            "max": 0.005000000000000001,
+            "count": 15
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1732088289",
+        "python_version": "3.10.4 (tags/v3.10.4:9d38120, Mar 23 2022, 23:13:41) [MSC v.1929 64 bit (AMD64)]",
+        "command_line_arguments": "D:\\python projects\\ml-agents\\venv\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.exe --run-id=SoccerTwos --no-graphics --resume",
+        "mlagents_version": "1.1.0",
+        "mlagents_envs_version": "1.1.0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "2.5.1+cpu",
+        "numpy_version": "1.23.5",
+        "end_time_seconds": "1732088761"
+    },
+    "total": 471.954658200033,
+    "count": 1,
+    "self": 4.281521999975666,
+    "children": {
+        "run_training.setup": {
+            "total": 0.3720814000116661,
+            "count": 1,
+            "self": 0.3720814000116661
+        },
+        "TrainerController.start_learning": {
+            "total": 467.3010548000457,
+            "count": 1,
+            "self": 0.2854381112847477,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 8.18414569995366,
+                    "count": 2,
+                    "self": 8.18414569995366
+                },
+                "TrainerController.advance": {
+                    "total": 458.6811532888096,
+                    "count": 11195,
+                    "self": 0.2861784966662526,
+                    "children": {
+                        "env_step": {
+                            "total": 207.8955141028855,
+                            "count": 11195,
+                            "self": 162.24072081502527,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 45.47821909491904,
+                                    "count": 11195,
+                                    "self": 1.5987130993744358,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 43.879505995544605,
+                                            "count": 20198,
+                                            "self": 43.879505995544605
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 0.1765741929411888,
+                                    "count": 11194,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 461.4469671078259,
+                                            "count": 11194,
+                                            "is_parallel": true,
+                                            "self": 330.1103191067232,
+                                            "children": {
+                                                "steps_from_proto": {
+                                                    "total": 0.002890500007197261,
+                                                    "count": 4,
+                                                    "is_parallel": true,
+                                                    "self": 0.0005716999294236302,
+                                                    "children": {
+                                                        "_process_rank_one_or_two_observation": {
+                                                            "total": 0.0023188000777736306,
+                                                            "count": 16,
+                                                            "is_parallel": true,
+                                                            "self": 0.0023188000777736306
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 131.33375750109553,
+                                                    "count": 11194,
+                                                    "is_parallel": true,
+                                                    "self": 6.943547705188394,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 5.550321500981227,
+                                                            "count": 11194,
+                                                            "is_parallel": true,
+                                                            "self": 5.550321500981227
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 98.2395213979762,
+                                                            "count": 11194,
+                                                            "is_parallel": true,
+                                                            "self": 98.2395213979762
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 20.60036689694971,
+                                                            "count": 22388,
+                                                            "is_parallel": true,
+                                                            "self": 4.042497379472479,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 16.55786951747723,
+                                                                    "count": 89552,
+                                                                    "is_parallel": true,
+                                                                    "self": 16.55786951747723
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 250.49946068925783,
+                            "count": 11194,
+                            "self": 1.9064420951763168,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 49.97855669434648,
+                                    "count": 11194,
+                                    "self": 49.55093809426762,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 0.42761860007885844,
+                                            "count": 1,
+                                            "self": 0.42761860007885844
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 198.61446189973503,
+                                    "count": 15,
+                                    "self": 20.9438984983135,
+                                    "children": {
+                                        "TorchPOCAOptimizer.update": {
+                                            "total": 177.67056340142153,
+                                            "count": 438,
+                                            "self": 177.67056340142153
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 1.800013706088066e-06,
+                    "count": 1,
+                    "self": 1.800013706088066e-06
+                },
+                "TrainerController._save_models": {
+                    "total": 0.15031589998397976,
+                    "count": 1,
+                    "self": 0.002495500026270747,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.14782039995770901,
+                            "count": 1,
+                            "self": 0.14782039995770901
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,66 @@
+{
+    "SoccerTwos": {
+        "checkpoints": [
+            {
+                "steps": 1500254,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-1500254.onnx",
+                "reward": 0.0,
+                "creation_time": 1732083936.7681327,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-1500254.pt"
+                ]
+            },
+            {
+                "steps": 1999918,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-1999918.onnx",
+                "reward": 0.0,
+                "creation_time": 1732086538.8482232,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-1999918.pt"
+                ]
+            },
+            {
+                "steps": 2434288,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-2434288.onnx",
+                "reward": 0.0,
+                "creation_time": 1732087816.7232904,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-2434288.pt"
+                ]
+            },
+            {
+                "steps": 2499994,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-2499994.onnx",
+                "reward": 0.0,
+                "creation_time": 1732088478.368934,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-2499994.pt"
+                ]
+            },
+            {
+                "steps": 2595280,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-2595280.onnx",
+                "reward": 0.0,
+                "creation_time": 1732088757.6685371,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-2595280.pt"
+                ]
+            }
+        ],
+        "elo": 1379.7441604815701,
+        "final_checkpoint": {
+            "steps": 2595280,
+            "file_path": "results\\SoccerTwos\\SoccerTwos.onnx",
+            "reward": 0.0,
+            "creation_time": 1732088757.6685371,
+            "auxillary_file_paths": [
+                "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-2595280.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "1.1.0",
+        "torch_version": "2.5.1+cpu"
+    }
+}