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: namedotpg/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:b0668a6809ca2c16eeb51334eeb51819577c738b133f8b72dd201db7e227dcdf
+size 1768746

SoccerTwos/SoccerTwos-3999934.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59e879fbf20515a0e7e676d600d3715b069f6ac7db28958360b8623b18762fef
+size 1768746

SoccerTwos/SoccerTwos-3999934.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2613ab2158c1aedb678406c1591bc9d3e3d87c34ebf61bd8910547cfdf328ea4
+size 28429903

SoccerTwos/SoccerTwos-4499973.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:332719925d49725b30d1246582e8f13a75ffeca130a58c2e81cb04f36ad099f6
+size 1768746

SoccerTwos/SoccerTwos-4499973.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4be12827457e0fa419c5309a51211d5acbfee406ade469eceb9aadbeee83e4b
+size 28429903

SoccerTwos/SoccerTwos-499886.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37896e3f078b69aa4c105b2ce89a03ebf3ad9daf294b007a9d133652a3919b36
+size 28429781

SoccerTwos/SoccerTwos-4999971.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8e1bb853227e5afc7d69dad67634763a2f486bff1e1f494a980a0b43ade69a4
+size 1768746

SoccerTwos/SoccerTwos-4999971.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f31c69a042865563cb846bd5003e78d41dd3f29bdec40990371f192178df141
+size 28429903

SoccerTwos/SoccerTwos-5499926.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f864ef04a22f6e78ecc4668f6210dd9568ac604764ba153a0ce3994c30da064
+size 1768746

SoccerTwos/SoccerTwos-5499926.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1b5e819dbd2009b8169e5532aa43e2b93ef0365cd8e27d7281b8ed2ce6dfa25
+size 28429903

SoccerTwos/SoccerTwos-5564806.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0668a6809ca2c16eeb51334eeb51819577c738b133f8b72dd201db7e227dcdf
+size 1768746

SoccerTwos/SoccerTwos-5564806.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc8021250a58c75c5ba4c6697d20a9fc2e1fa9e4fb03b1e27e0818dfd8514e7a
+size 28429903

SoccerTwos/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d8b3b8c655198e68d1cb174d48b419b4c2515a3f13476a52f6ceb6088107e10
+size 28428927

SoccerTwos/events.out.tfevents.1689191207.DESKTOP-4K3R15L.14600.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:317e03f8e65b2a5c400c423e9506cfe4dc8b6a47a18f3dedbf12f9335ddb7ea0
+size 399284

SoccerTwos/events.out.tfevents.1689196104.DESKTOP-4K3R15L.14048.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a08c5a2eb7226706e7fa8e5c6de3551911673d235ab4daf79ef79493038a4e15
+size 2040

SoccerTwos/events.out.tfevents.1689196621.DESKTOP-4K3R15L.9152.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f441720378e68ff25835d7979916f53a6cb6ea43080e9581e5ae5856bf3171e
+size 3031624

SoccerTwos/events.out.tfevents.1689245850.DESKTOP-4K3R15L.12020.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e61cb0027a408988c2460631398ee85bcff441ac73e737e41cf2ad9994506cb3
+size 2149177

config.json

@@ -0,0 +1 @@
+{"default_settings": null, "behaviors": {"SoccerTwos": {"trainer_type": "poca", "hyperparameters": {"batch_size": 2048, "buffer_size": 20480, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "learning_rate_schedule": "constant", "beta_schedule": "constant", "epsilon_schedule": "constant"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 50000000, "time_horizon": 1000, "summary_freq": 10000, "threaded": false, "self_play": {"save_steps": 50000, "team_change": 250000, "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.exe", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SoccerTwos", "initialize_from": null, "load_model": false, "resume": true, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -0,0 +1,82 @@
+default_settings: null
+behaviors:
+  SoccerTwos:
+    trainer_type: poca
+    hyperparameters:
+      batch_size: 2048
+      buffer_size: 20480
+      learning_rate: 0.0003
+      beta: 0.005
+      epsilon: 0.2
+      lambd: 0.95
+      num_epoch: 3
+      learning_rate_schedule: constant
+      beta_schedule: constant
+      epsilon_schedule: constant
+    checkpoint_interval: 500000
+    network_settings:
+      normalize: false
+      hidden_units: 512
+      num_layers: 2
+      vis_encode_type: simple
+      memory: null
+      goal_conditioning_type: hyper
+      deterministic: false
+    reward_signals:
+      extrinsic:
+        gamma: 0.99
+        strength: 1.0
+        network_settings:
+          normalize: false
+          hidden_units: 128
+          num_layers: 2
+          vis_encode_type: simple
+          memory: null
+          goal_conditioning_type: hyper
+          deterministic: false
+    init_path: null
+    keep_checkpoints: 5
+    even_checkpoints: false
+    max_steps: 50000000
+    time_horizon: 1000
+    summary_freq: 10000
+    threaded: false
+    self_play:
+      save_steps: 50000
+      team_change: 250000
+      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.exe
+  env_args: null
+  base_port: 5005
+  num_envs: 1
+  num_areas: 1
+  seed: -1
+  max_lifetime_restarts: 10
+  restarts_rate_limit_n: 1
+  restarts_rate_limit_period_s: 60
+engine_settings:
+  width: 84
+  height: 84
+  quality_level: 5
+  time_scale: 20
+  target_frame_rate: -1
+  capture_frame_rate: 60
+  no_graphics: true
+environment_parameters: null
+checkpoint_settings:
+  run_id: SoccerTwos
+  initialize_from: null
+  load_model: false
+  resume: true
+  force: false
+  train_model: false
+  inference: false
+  results_dir: results
+torch_settings:
+  device: null
+debug: false

run_logs/Player-0.log

@@ -0,0 +1,263 @@
+Mono path[0] = 'C:/Users/Patryk/ml-agents/training-envs-executables/SoccerTwos/SoccerTwos_Data/Managed'
+Mono config path = 'C:/Users/Patryk/ml-agents/training-envs-executables/SoccerTwos/MonoBleedingEdge/etc'
+Initialize engine version: 2021.3.14f1 (eee1884e7226)
+[Subsystems] Discovering subsystems at path C:/Users/Patryk/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  0.165 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: 0.700200 ms
+Registered Communicator in Agent.
+ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+GRPC Exception: Status(StatusCode=Unknown, Detail="Exception calling application: [WinError 232] The pipe is being closed"). Disconnecting from trainer.
+Setting up 2 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]: 39222 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 315 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_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 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 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_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 2
+      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 3
+      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]: 39223 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 4.9 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 39223 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]: 39222 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]: 39223 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]: 39223 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]: 39222 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]: 39223 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]: 39222 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": 1.8603078126907349,
+            "min": 1.8603078126907349,
+            "max": 2.1334164142608643,
+            "count": 209
+        },
+        "SoccerTwos.Policy.Entropy.sum": {
+            "value": 38337.22265625,
+            "min": 12103.240234375,
+            "max": 46377.265625,
+            "count": 209
+        },
+        "SoccerTwos.Environment.EpisodeLength.mean": {
+            "value": 50.65979381443299,
+            "min": 37.25757575757576,
+            "max": 67.65277777777777,
+            "count": 209
+        },
+        "SoccerTwos.Environment.EpisodeLength.sum": {
+            "value": 19656.0,
+            "min": 4332.0,
+            "max": 20220.0,
+            "count": 209
+        },
+        "SoccerTwos.Self-play.ELO.mean": {
+            "value": 1508.4571102358263,
+            "min": 1410.7677734512024,
+            "max": 1508.4571102358263,
+            "count": 209
+        },
+        "SoccerTwos.Self-play.ELO.sum": {
+            "value": 292640.6793857503,
+            "min": 80684.63604765123,
+            "max": 389486.18281116325,
+            "count": 209
+        },
+        "SoccerTwos.Step.mean": {
+            "value": 5559968.0,
+            "min": 3479968.0,
+            "max": 5559968.0,
+            "count": 209
+        },
+        "SoccerTwos.Step.sum": {
+            "value": 5559968.0,
+            "min": 3479968.0,
+            "max": 5559968.0,
+            "count": 209
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
+            "value": 0.06590203195810318,
+            "min": -0.10732022672891617,
+            "max": 0.11532635241746902,
+            "count": 209
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
+            "value": 12.71909236907959,
+            "min": -19.74692153930664,
+            "max": 23.641902923583984,
+            "count": 209
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 0.07202169299125671,
+            "min": -0.11327219754457474,
+            "max": 0.11728597432374954,
+            "count": 209
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 13.900186538696289,
+            "min": -20.842084884643555,
+            "max": 24.043624877929688,
+            "count": 209
+        },
+        "SoccerTwos.Environment.CumulativeReward.mean": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 209
+        },
+        "SoccerTwos.Environment.CumulativeReward.sum": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 209
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.mean": {
+            "value": 0.06361761889927128,
+            "min": -0.25542857162245025,
+            "max": 0.2227913489212861,
+            "count": 209
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.sum": {
+            "value": 12.278200447559357,
+            "min": -46.77280014753342,
+            "max": 44.30399960279465,
+            "count": 209
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.mean": {
+            "value": 0.06361761889927128,
+            "min": -0.25542857162245025,
+            "max": 0.2227913489212861,
+            "count": 209
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.sum": {
+            "value": 12.278200447559357,
+            "min": -46.77280014753342,
+            "max": 44.30399960279465,
+            "count": 209
+        },
+        "SoccerTwos.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 209
+        },
+        "SoccerTwos.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 209
+        },
+        "SoccerTwos.Losses.PolicyLoss.mean": {
+            "value": 0.0165368358429987,
+            "min": 0.007948545047353643,
+            "max": 0.023904067111046364,
+            "count": 101
+        },
+        "SoccerTwos.Losses.PolicyLoss.sum": {
+            "value": 0.0165368358429987,
+            "min": 0.007948545047353643,
+            "max": 0.023904067111046364,
+            "count": 101
+        },
+        "SoccerTwos.Losses.ValueLoss.mean": {
+            "value": 0.1125721628467242,
+            "min": 0.08946814537048339,
+            "max": 0.12405024742086729,
+            "count": 101
+        },
+        "SoccerTwos.Losses.ValueLoss.sum": {
+            "value": 0.1125721628467242,
+            "min": 0.08946814537048339,
+            "max": 0.12405024742086729,
+            "count": 101
+        },
+        "SoccerTwos.Losses.BaselineLoss.mean": {
+            "value": 0.11418352921803793,
+            "min": 0.09109867264827093,
+            "max": 0.1264182907839616,
+            "count": 101
+        },
+        "SoccerTwos.Losses.BaselineLoss.sum": {
+            "value": 0.11418352921803793,
+            "min": 0.09109867264827093,
+            "max": 0.1264182907839616,
+            "count": 101
+        },
+        "SoccerTwos.Policy.LearningRate.mean": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 101
+        },
+        "SoccerTwos.Policy.LearningRate.sum": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 101
+        },
+        "SoccerTwos.Policy.Epsilon.mean": {
+            "value": 0.20000000000000007,
+            "min": 0.20000000000000007,
+            "max": 0.20000000000000007,
+            "count": 101
+        },
+        "SoccerTwos.Policy.Epsilon.sum": {
+            "value": 0.20000000000000007,
+            "min": 0.20000000000000007,
+            "max": 0.20000000000000007,
+            "count": 101
+        },
+        "SoccerTwos.Policy.Beta.mean": {
+            "value": 0.005000000000000001,
+            "min": 0.005000000000000001,
+            "max": 0.005000000000000001,
+            "count": 101
+        },
+        "SoccerTwos.Policy.Beta.sum": {
+            "value": 0.005000000000000001,
+            "min": 0.005000000000000001,
+            "max": 0.005000000000000001,
+            "count": 101
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1689245844",
+        "python_version": "3.9.17 (main, Jul  5 2023, 20:47:11) [MSC v.1916 64 bit (AMD64)]",
+        "command_line_arguments": "C:\\ProgramData\\anaconda3\\envs\\rlpython\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --no-graphics --resume",
+        "mlagents_version": "0.31.0.dev0",
+        "mlagents_envs_version": "0.31.0.dev0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "2.0.1+cpu",
+        "numpy_version": "1.21.2",
+        "end_time_seconds": "1689253155"
+    },
+    "total": 7311.0283555999995,
+    "count": 1,
+    "self": 0.22450299999945855,
+    "children": {
+        "run_training.setup": {
+            "total": 0.1409528,
+            "count": 1,
+            "self": 0.1409528
+        },
+        "TrainerController.start_learning": {
+            "total": 7310.6628998,
+            "count": 1,
+            "self": 3.4980922998493043,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 5.4822846000012735,
+                    "count": 10,
+                    "self": 5.4822846000012735
+                },
+                "TrainerController.advance": {
+                    "total": 7301.5386790001485,
+                    "count": 146863,
+                    "self": 3.700301000213585,
+                    "children": {
+                        "env_step": {
+                            "total": 2439.0040659999363,
+                            "count": 146863,
+                            "self": 1894.4940038000395,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 542.3075087999578,
+                                    "count": 146863,
+                                    "self": 20.220769500017468,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 522.0867392999403,
+                                            "count": 261486,
+                                            "self": 522.0867392999403
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 2.202553399938852,
+                                    "count": 146862,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 7300.398557500002,
+                                            "count": 146862,
+                                            "is_parallel": true,
+                                            "self": 5783.223992200098,
+                                            "children": {
+                                                "steps_from_proto": {
+                                                    "total": 0.017665900000246815,
+                                                    "count": 20,
+                                                    "is_parallel": true,
+                                                    "self": 0.0035129999989544913,
+                                                    "children": {
+                                                        "_process_rank_one_or_two_observation": {
+                                                            "total": 0.014152900001292323,
+                                                            "count": 80,
+                                                            "is_parallel": true,
+                                                            "self": 0.014152900001292323
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 1517.1568993999042,
+                                                    "count": 146862,
+                                                    "is_parallel": true,
+                                                    "self": 76.25806909964513,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 51.65471730006807,
+                                                            "count": 146862,
+                                                            "is_parallel": true,
+                                                            "self": 51.65471730006807
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 1149.6609378000794,
+                                                            "count": 146862,
+                                                            "is_parallel": true,
+                                                            "self": 1149.6609378000794
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 239.5831752001116,
+                                                            "count": 293724,
+                                                            "is_parallel": true,
+                                                            "self": 49.71732580005968,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 189.86584940005193,
+                                                                    "count": 1174896,
+                                                                    "is_parallel": true,
+                                                                    "self": 189.86584940005193
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 4858.834311999998,
+                            "count": 146862,
+                            "self": 22.310789500138526,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 1247.532006199859,
+                                    "count": 146862,
+                                    "self": 1246.6193053998581,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 0.912700800000934,
+                                            "count": 5,
+                                            "self": 0.912700800000934
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 3588.9915163,
+                                    "count": 101,
+                                    "self": 346.39863790001937,
+                                    "children": {
+                                        "TorchPOCAOptimizer.update": {
+                                            "total": 3242.5928783999807,
+                                            "count": 3030,
+                                            "self": 3242.5928783999807
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 1.100000190490391e-06,
+                    "count": 1,
+                    "self": 1.100000190490391e-06
+                },
+                "TrainerController._save_models": {
+                    "total": 0.1438428000001295,
+                    "count": 1,
+                    "self": 0.0023837999997340376,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.14145900000039546,
+                            "count": 1,
+                            "self": 0.14145900000039546
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,66 @@
+{
+    "SoccerTwos": {
+        "elo": 1509.8263280053673,
+        "checkpoints": [
+            {
+                "steps": 3999934,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-3999934.onnx",
+                "reward": 0.0,
+                "creation_time": 1689247521.7807739,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-3999934.pt"
+                ]
+            },
+            {
+                "steps": 4499973,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-4499973.onnx",
+                "reward": 0.0,
+                "creation_time": 1689249171.8248997,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-4499973.pt"
+                ]
+            },
+            {
+                "steps": 4999971,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-4999971.onnx",
+                "reward": 0.0,
+                "creation_time": 1689250949.0633352,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-4999971.pt"
+                ]
+            },
+            {
+                "steps": 5499926,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-5499926.onnx",
+                "reward": 0.0,
+                "creation_time": 1689252444.2925103,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-5499926.pt"
+                ]
+            },
+            {
+                "steps": 5564806,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-5564806.onnx",
+                "reward": 0.0,
+                "creation_time": 1689253155.6259432,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-5564806.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 5564806,
+            "file_path": "results\\SoccerTwos\\SoccerTwos.onnx",
+            "reward": 0.0,
+            "creation_time": 1689253155.6259432,
+            "auxillary_file_paths": [
+                "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-5564806.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "0.31.0.dev0",
+        "torch_version": "2.0.1+cpu"
+    }
+}