FirstPush`

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: DumbleDuck/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 sha256:3b28bfe26449c97f498b8102705a0c9ed497715721036cda2d1fc42e019d7b66
+size 1773175

SoccerTwos/SoccerTwos-3499976.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d8a51065abab3f32c51990d04c0c0f2babc3bf29087893f88343491cc3f5289
+size 1773175

SoccerTwos/SoccerTwos-3499976.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:498a3749e0e1c062abf4b94d64d0d3016cc9d17b241c3aed4f1add247c9fff5d
+size 28442405

SoccerTwos/SoccerTwos-3999970.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b14113bdadef5a10a6cc45f1afba819cd539d28066b09d82dafc25c341773b97
+size 1773175

SoccerTwos/SoccerTwos-3999970.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:560ac7e5fcf821094779a7ad74355b322e8f3a50c1aa778e6717a89fc1cd0abf
+size 28442405

SoccerTwos/SoccerTwos-4499984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ecc5f48b28dfbe5cc873aa366e66a6c76736bb72fd024ed7c0ff5533836a6e29
+size 1773175

SoccerTwos/SoccerTwos-4499984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:acc683424ae8a8a05a0522fbc8c9c0162560ebce0d68cdac831c1d17c0ba02e6
+size 28442405

SoccerTwos/SoccerTwos-4999996.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e4c36de161cf641c6db1cad30db18c375731987f278334a13245a918ce83ea1
+size 1773175

SoccerTwos/SoccerTwos-4999996.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16a8d4a4290572f3dde9b7ea0691ab1a3fef981e1ab98c4585ee73637d5e173a
+size 28442405

SoccerTwos/SoccerTwos-5000042.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b28bfe26449c97f498b8102705a0c9ed497715721036cda2d1fc42e019d7b66
+size 1773175

SoccerTwos/SoccerTwos-5000042.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b7049f0f172efd2a1baedc6cdc648624f15c9e666367982f5d21cae0d1e0583
+size 28442405

SoccerTwos/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e133d2965fc1fa3b1377e4d7f3a3255499bef188302d7a0f97da98bce5dfa73
+size 28441301

SoccerTwos/events.out.tfevents.1745547244.DESKTOP-J4KFF35.41388.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1815b97993c69e8d65d2614660554e6c0b21318dde3db0cbef6bcace2645967e
+size 2609706

config.json

@@ -0,0 +1 @@
+{"default_settings": null, "behaviors": {"SoccerTwos": {"trainer_type": "poca", "hyperparameters": {"batch_size": 2048, "buffer_size": 20480, "learning_rate": 0.0005, "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": true, "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": 5000000, "time_horizon": 1000, "summary_freq": 20000, "threaded": false, "self_play": {"save_steps": 20000, "team_change": 80000, "swap_steps": 2000, "window": 10, "play_against_latest_model_ratio": 0.6, "initial_elo": 1200.0}, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/SoccerTwos.exe", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "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": "1Run", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -0,0 +1,84 @@
+default_settings: null
+behaviors:
+  SoccerTwos:
+    trainer_type: poca
+    hyperparameters:
+      batch_size: 2048
+      buffer_size: 20480
+      learning_rate: 0.0005
+      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: true
+      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: 5000000
+    time_horizon: 1000
+    summary_freq: 20000
+    threaded: false
+    self_play:
+      save_steps: 20000
+      team_change: 80000
+      swap_steps: 2000
+      window: 10
+      play_against_latest_model_ratio: 0.6
+      initial_elo: 1200.0
+    behavioral_cloning: null
+env_settings:
+  env_path: ./training-envs-executables/SoccerTwos.exe
+  env_args: null
+  base_port: 5005
+  num_envs: 1
+  num_areas: 1
+  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: 1Run
+  initialize_from: null
+  load_model: false
+  resume: false
+  force: false
+  train_model: false
+  inference: false
+  results_dir: results
+torch_settings:
+  device: null
+debug: false

run_logs/Player-0.log

@@ -0,0 +1,506 @@
+Mono path[0] = 'C:/Users/anant/ml-agents/training-envs-executables/SoccerTwos/SoccerTwos_Data/Managed'
+Mono config path = 'C:/Users/anant/ml-agents/training-envs-executables/SoccerTwos/MonoBleedingEdge/etc'
+Initialize engine version: 2021.3.14f1 (eee1884e7226)
+[Subsystems] Discovering subsystems at path C:/Users/anant/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  0.173 seconds
+ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+Microsoft Media Foundation video decoding to texture disabled: graphics device is Null, only Direct3D 11 and Direct3D 12 (only on desktop) are supported for hardware-accelerated video decoding.
+ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+WARNING: Shader Unsupported: 'Standard (Specular setup)' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
+ERROR: Shader Standard (Specular setup) shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+WARNING: Shader Unsupported: 'Standard (Specular setup)' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
+WARNING: Shader Unsupported: 'Autodesk Interactive' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
+ERROR: Shader Autodesk Interactive shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+WARNING: Shader Unsupported: 'Autodesk Interactive' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
+WARNING: Shader Unsupported: 'Standard' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
+ERROR: Shader Standard shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+WARNING: Shader Unsupported: 'Standard' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
+UnloadTime: 1.749000 ms
+Registered Communicator in Agent.
+ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+Setting up 8 worker threads for Enlighten.
+Memory Statistics:
+[ALLOC_TEMP_TLS] TLS Allocator
+  StackAllocators : 
+    [ALLOC_TEMP_MAIN]
+      Peak usage frame count: [8.0 KB-16.0 KB]: 95628 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 312 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 14]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 54 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 54 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 12]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 54 B
+      Overflow Count 0
+    [ALLOC_TEMP_EnlightenWorker] x 8
+      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 15
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 5]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 54 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 54 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 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_Job.Worker 10]
+      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 0]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 54 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 11]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 54 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 12]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 54 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 4]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 54 B
+      Overflow Count 0
+    [ALLOC_TEMP_BatchDeleteObjects]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 54 B
+      Overflow Count 0
+[ALLOC_DEFAULT] Dual Thread Allocator
+  Peak main deferred allocation count 6
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 0.9 MB
+    [ALLOC_DEFAULT_MAIN]
+      Peak usage frame count: [4.0 MB-8.0 MB]: 95629 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]: 95629 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 17.4 MB
+      Peak Large allocation bytes 16.0 MB
+[ALLOC_TEMP_JOB_1_FRAME]
+  Initial Block Size 2.0 MB
+  Used Block Count 1
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_TEMP_JOB_2_FRAMES]
+  Initial Block Size 2.0 MB
+  Used Block Count 1
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_TEMP_JOB_4_FRAMES (JobTemp)]
+  Initial Block Size 2.0 MB
+  Used Block Count 2
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_TEMP_JOB_ASYNC (Background)]
+  Initial Block Size 1.0 MB
+  Used Block Count 3
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_GFX] Dual Thread Allocator
+  Peak main deferred allocation count 0
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 0.9 MB
+    [ALLOC_GFX_MAIN]
+      Peak usage frame count: [32.0 KB-64.0 KB]: 95628 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]: 95629 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]: 95629 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]: 95628 frames, [2.0 MB-4.0 MB]: 1 frames
+      Requested Block Size 4.0 MB
+      Peak Block count 1
+      Peak Allocated memory 2.2 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]: 95629 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]: 95628 frames, [2.0 KB-4.0 KB]: 1 frames
+      Requested Block Size 2.0 MB
+      Peak Block count 1
+      Peak Allocated memory 2.2 KB
+      Peak Large allocation bytes 0 B

run_logs/timers.json

@@ -0,0 +1,368 @@
+{
+    "name": "root",
+    "gauges": {
+        "SoccerTwos.Policy.Entropy.mean": {
+            "value": 1.9529489278793335,
+            "min": 1.920395016670227,
+            "max": 3.2957565784454346,
+            "count": 250
+        },
+        "SoccerTwos.Policy.Entropy.sum": {
+            "value": 79367.84375,
+            "min": 73953.03125,
+            "max": 197956.328125,
+            "count": 250
+        },
+        "SoccerTwos.Environment.EpisodeLength.mean": {
+            "value": 70.59420289855072,
+            "min": 57.08771929824562,
+            "max": 886.8181818181819,
+            "count": 250
+        },
+        "SoccerTwos.Environment.EpisodeLength.sum": {
+            "value": 38968.0,
+            "min": 36280.0,
+            "max": 42988.0,
+            "count": 250
+        },
+        "SoccerTwos.Self-play.ELO.mean": {
+            "value": 1464.2702372201193,
+            "min": 1198.2569428535305,
+            "max": 1465.29735545878,
+            "count": 250
+        },
+        "SoccerTwos.Self-play.ELO.sum": {
+            "value": 404138.5854727529,
+            "min": 7249.82608936267,
+            "max": 499855.55087429576,
+            "count": 250
+        },
+        "SoccerTwos.Step.mean": {
+            "value": 4999996.0,
+            "min": 19522.0,
+            "max": 4999996.0,
+            "count": 250
+        },
+        "SoccerTwos.Step.sum": {
+            "value": 4999996.0,
+            "min": 19522.0,
+            "max": 4999996.0,
+            "count": 250
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
+            "value": -0.02981281280517578,
+            "min": -0.0878727063536644,
+            "max": 0.10768340528011322,
+            "count": 250
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
+            "value": -8.228336334228516,
+            "min": -24.164995193481445,
+            "max": 27.915550231933594,
+            "count": 250
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
+            "value": -0.031449221074581146,
+            "min": -0.08884181082248688,
+            "max": 0.1037328839302063,
+            "count": 250
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
+            "value": -8.679985046386719,
+            "min": -24.43149757385254,
+            "max": 26.647890090942383,
+            "count": 250
+        },
+        "SoccerTwos.Environment.CumulativeReward.mean": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 250
+        },
+        "SoccerTwos.Environment.CumulativeReward.sum": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 250
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.mean": {
+            "value": 0.006250726140063742,
+            "min": -0.5489407394219328,
+            "max": 0.24266240000724792,
+            "count": 250
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.sum": {
+            "value": 1.7252004146575928,
+            "min": -63.58240056037903,
+            "max": 56.710800647735596,
+            "count": 250
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.mean": {
+            "value": 0.006250726140063742,
+            "min": -0.5489407394219328,
+            "max": 0.24266240000724792,
+            "count": 250
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.sum": {
+            "value": 1.7252004146575928,
+            "min": -63.58240056037903,
+            "max": 56.710800647735596,
+            "count": 250
+        },
+        "SoccerTwos.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 250
+        },
+        "SoccerTwos.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 250
+        },
+        "SoccerTwos.Losses.PolicyLoss.mean": {
+            "value": 0.021301117760594936,
+            "min": 0.012588015308817072,
+            "max": 0.030014544230652973,
+            "count": 241
+        },
+        "SoccerTwos.Losses.PolicyLoss.sum": {
+            "value": 0.021301117760594936,
+            "min": 0.012588015308817072,
+            "max": 0.030014544230652973,
+            "count": 241
+        },
+        "SoccerTwos.Losses.ValueLoss.mean": {
+            "value": 0.07665027156472207,
+            "min": 0.0004876753276524444,
+            "max": 0.09533282940586409,
+            "count": 241
+        },
+        "SoccerTwos.Losses.ValueLoss.sum": {
+            "value": 0.07665027156472207,
+            "min": 0.0004876753276524444,
+            "max": 0.09533282940586409,
+            "count": 241
+        },
+        "SoccerTwos.Losses.BaselineLoss.mean": {
+            "value": 0.07971610973278681,
+            "min": 0.00047008581168483943,
+            "max": 0.09862766911586125,
+            "count": 241
+        },
+        "SoccerTwos.Losses.BaselineLoss.sum": {
+            "value": 0.07971610973278681,
+            "min": 0.00047008581168483943,
+            "max": 0.09862766911586125,
+            "count": 241
+        },
+        "SoccerTwos.Policy.LearningRate.mean": {
+            "value": 0.0005000000000000001,
+            "min": 0.0005000000000000001,
+            "max": 0.0005000000000000001,
+            "count": 241
+        },
+        "SoccerTwos.Policy.LearningRate.sum": {
+            "value": 0.0005000000000000001,
+            "min": 0.0005000000000000001,
+            "max": 0.0005000000000000001,
+            "count": 241
+        },
+        "SoccerTwos.Policy.Epsilon.mean": {
+            "value": 0.20000000000000007,
+            "min": 0.20000000000000007,
+            "max": 0.20000000000000007,
+            "count": 241
+        },
+        "SoccerTwos.Policy.Epsilon.sum": {
+            "value": 0.20000000000000007,
+            "min": 0.20000000000000007,
+            "max": 0.20000000000000007,
+            "count": 241
+        },
+        "SoccerTwos.Policy.Beta.mean": {
+            "value": 0.005000000000000001,
+            "min": 0.005000000000000001,
+            "max": 0.005000000000000001,
+            "count": 241
+        },
+        "SoccerTwos.Policy.Beta.sum": {
+            "value": 0.005000000000000001,
+            "min": 0.005000000000000001,
+            "max": 0.005000000000000001,
+            "count": 241
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1745547238",
+        "python_version": "3.10.12 | packaged by conda-forge | (main, Jun 23 2023, 22:34:57) [MSC v.1936 64 bit (AMD64)]",
+        "command_line_arguments": "\\\\?\\C:\\Users\\anant\\anaconda3\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=1Run --no-graphics",
+        "mlagents_version": "1.2.0.dev0",
+        "mlagents_envs_version": "1.2.0.dev0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "2.7.0+cpu",
+        "numpy_version": "1.23.5",
+        "end_time_seconds": "1745559900"
+    },
+    "total": 12661.5354525,
+    "count": 1,
+    "self": 1.6069960000022547,
+    "children": {
+        "run_training.setup": {
+            "total": 0.15652789999876404,
+            "count": 1,
+            "self": 0.15652789999876404
+        },
+        "TrainerController.start_learning": {
+            "total": 12659.7719286,
+            "count": 1,
+            "self": 8.530186498690455,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 9.817780500030494,
+                    "count": 63,
+                    "self": 9.817780500030494
+                },
+                "TrainerController.advance": {
+                    "total": 12641.297751701277,
+                    "count": 343197,
+                    "self": 7.509880501384032,
+                    "children": {
+                        "env_step": {
+                            "total": 5685.076145999206,
+                            "count": 343197,
+                            "self": 4508.535372601298,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 1171.2360110994632,
+                                    "count": 343197,
+                                    "self": 47.421188699576305,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 1123.814822399887,
+                                            "count": 637548,
+                                            "self": 1123.814822399887
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 5.3047622984449845,
+                                    "count": 343197,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 12643.229359900855,
+                                            "count": 343197,
+                                            "is_parallel": true,
+                                            "self": 9081.977710197876,
+                                            "children": {
+                                                "steps_from_proto": {
+                                                    "total": 0.11255010001332266,
+                                                    "count": 126,
+                                                    "is_parallel": true,
+                                                    "self": 0.020482399988395628,
+                                                    "children": {
+                                                        "_process_rank_one_or_two_observation": {
+                                                            "total": 0.09206770002492703,
+                                                            "count": 504,
+                                                            "is_parallel": true,
+                                                            "self": 0.09206770002492703
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 3561.139099602966,
+                                                    "count": 343197,
+                                                    "is_parallel": true,
+                                                    "self": 189.2527658993713,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 171.13706360138895,
+                                                            "count": 343197,
+                                                            "is_parallel": true,
+                                                            "self": 171.13706360138895
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 2613.8167306001924,
+                                                            "count": 343197,
+                                                            "is_parallel": true,
+                                                            "self": 2613.8167306001924
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 586.9325395020132,
+                                                            "count": 686394,
+                                                            "is_parallel": true,
+                                                            "self": 108.1029482959566,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 478.82959120605665,
+                                                                    "count": 2745576,
+                                                                    "is_parallel": true,
+                                                                    "self": 478.82959120605665
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 6948.7117252006865,
+                            "count": 343197,
+                            "self": 56.523976503471204,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 1215.7273217972834,
+                                    "count": 343197,
+                                    "self": 1214.2334586972866,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 1.4938630999968154,
+                                            "count": 10,
+                                            "self": 1.4938630999968154
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 5676.460426899932,
+                                    "count": 241,
+                                    "self": 737.9465077001005,
+                                    "children": {
+                                        "TorchPOCAOptimizer.update": {
+                                            "total": 4938.513919199831,
+                                            "count": 7230,
+                                            "self": 4938.513919199831
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 1.2000018614344299e-06,
+                    "count": 1,
+                    "self": 1.2000018614344299e-06
+                },
+                "TrainerController._save_models": {
+                    "total": 0.12620869999955175,
+                    "count": 1,
+                    "self": 0.013214999999036081,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.11299370000051567,
+                            "count": 1,
+                            "self": 0.11299370000051567
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,66 @@
+{
+    "SoccerTwos": {
+        "checkpoints": [
+            {
+                "steps": 3499976,
+                "file_path": "results\\1Run\\SoccerTwos\\SoccerTwos-3499976.onnx",
+                "reward": 0.0,
+                "creation_time": 1745556440.8884091,
+                "auxillary_file_paths": [
+                    "results\\1Run\\SoccerTwos\\SoccerTwos-3499976.pt"
+                ]
+            },
+            {
+                "steps": 3999970,
+                "file_path": "results\\1Run\\SoccerTwos\\SoccerTwos-3999970.onnx",
+                "reward": 0.0,
+                "creation_time": 1745557606.5963163,
+                "auxillary_file_paths": [
+                    "results\\1Run\\SoccerTwos\\SoccerTwos-3999970.pt"
+                ]
+            },
+            {
+                "steps": 4499984,
+                "file_path": "results\\1Run\\SoccerTwos\\SoccerTwos-4499984.onnx",
+                "reward": 0.0,
+                "creation_time": 1745558756.3664906,
+                "auxillary_file_paths": [
+                    "results\\1Run\\SoccerTwos\\SoccerTwos-4499984.pt"
+                ]
+            },
+            {
+                "steps": 4999996,
+                "file_path": "results\\1Run\\SoccerTwos\\SoccerTwos-4999996.onnx",
+                "reward": 0.0,
+                "creation_time": 1745559898.6711233,
+                "auxillary_file_paths": [
+                    "results\\1Run\\SoccerTwos\\SoccerTwos-4999996.pt"
+                ]
+            },
+            {
+                "steps": 5000042,
+                "file_path": "results\\1Run\\SoccerTwos\\SoccerTwos-5000042.onnx",
+                "reward": 0.0,
+                "creation_time": 1745559898.8074703,
+                "auxillary_file_paths": [
+                    "results\\1Run\\SoccerTwos\\SoccerTwos-5000042.pt"
+                ]
+            }
+        ],
+        "elo": 1464.399130226103,
+        "final_checkpoint": {
+            "steps": 5000042,
+            "file_path": "results\\1Run\\SoccerTwos.onnx",
+            "reward": 0.0,
+            "creation_time": 1745559898.8074703,
+            "auxillary_file_paths": [
+                "results\\1Run\\SoccerTwos\\SoccerTwos-5000042.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "1.2.0.dev0",
+        "torch_version": "2.7.0+cpu"
+    }
+}