First commit

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: nokotin/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:fd88f6de608b426e755d5b8f029639d4c2a9a1a2a4977077bcbb3718c5e8af8a
+size 1763215

SoccerTwos/SoccerTwos-10032342.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd88f6de608b426e755d5b8f029639d4c2a9a1a2a4977077bcbb3718c5e8af8a
+size 1763215

SoccerTwos/SoccerTwos-10032342.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1291c66b89e101aaa23c1ba7250ffeb560e2add26862f4cdee28b2c6c58d2f1d
+size 28423631

SoccerTwos/SoccerTwos-8499935.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4a749bc7ba1fecef8fc5bc58b671ba020172a14b007919b42f2393f076737ff
+size 1763215

SoccerTwos/SoccerTwos-8499935.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bba0e5cd0c19d4af353fc6b66e66194a3da9c068ecb19673b08f8e7d8cbc13b2
+size 28423631

SoccerTwos/SoccerTwos-8999939.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07b88586ede4c91629a8322e2864f56aae244074522389e4ff0b5847c7998a15
+size 1763215

SoccerTwos/SoccerTwos-8999939.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:856e0d9db17ea205dda173ee443737930ede1055d183ed9f325a1139e8f98989
+size 28423631

SoccerTwos/SoccerTwos-9499966.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f033f5766b7c072875c3b67ad72507c0b6a38404baba17cf37b759f0c397a252
+size 1763215

SoccerTwos/SoccerTwos-9499966.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4927e8ed29120b35cea0099177f6457be81522361ca1a8bec91892ae7430ce4
+size 28423631

SoccerTwos/SoccerTwos-9999933.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8edee0f6aeb0730bead0c5b0ab0b2365db4dce446d1528880d6bb58ad2ea23ca
+size 1763215

SoccerTwos/SoccerTwos-9999933.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6132df6e40b200b29c36959ddcd430068c60cbeef3bf19357949b69b19588317
+size 28423631

SoccerTwos/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1291c66b89e101aaa23c1ba7250ffeb560e2add26862f4cdee28b2c6c58d2f1d
+size 28423631

SoccerTwos/events.out.tfevents.1691355011.DESKTOP-OT1JMDB.228.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a232f6a75143c32d54ca5ab7a04c8dcef451e66a084bed73c55221c14aa8cd0
+size 2407807

SoccerTwos/events.out.tfevents.1691417566.DESKTOP-OT1JMDB.15912.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd5d573af9ae8a88f3f9c78ee91b28fa5fcfb414840efebcb9f73a21e1864738
+size 7822600

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"}, "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, "checkpoint_interval": 500000, "max_steps": 50000000, "time_horizon": 1000, "summary_freq": 10000, "threaded": false, "self_play": {"save_steps": 50000, "team_change": 200000, "swap_steps": 2000, "window": 10, "play_against_latest_model_ratio": 0.5, "initial_elo": 1200.0}, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/SoccerTwos.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 +1,81 @@
+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
+    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
+    checkpoint_interval: 500000
+    max_steps: 50000000
+    time_horizon: 1000
+    summary_freq: 10000
+    threaded: false
+    self_play:
+      save_steps: 50000
+      team_change: 200000
+      swap_steps: 2000
+      window: 10
+      play_against_latest_model_ratio: 0.5
+      initial_elo: 1200.0
+    behavioral_cloning: null
+env_settings:
+  env_path: ./training-envs-executables/SoccerTwos.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 +1,282 @@
+Mono path[0] = 'C:/dev/ML/ml-agents/training-envs-executables/SoccerTwos/SoccerTwos_Data/Managed'
+Mono config path = 'C:/dev/ML/ml-agents/training-envs-executables/SoccerTwos/MonoBleedingEdge/etc'
+Initialize engine version: 2021.3.14f1 (eee1884e7226)
+[Subsystems] Discovering subsystems at path C:/dev/ML/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  5.129 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: 1.275200 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]: 143100 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 297 B
+      Overflow Count 0
+    [ALLOC_TEMP_Loading.PreloadManager]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 68.0 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 4
+    [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]: 143101 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]: 143101 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]: 143100 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]: 143101 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]: 143101 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]: 143100 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]: 143101 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]: 143100 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": 1.840072512626648,
+            "min": 1.5899217128753662,
+            "max": 2.4978463649749756,
+            "count": 761
+        },
+        "SoccerTwos.Policy.Entropy.sum": {
+            "value": 37390.2734375,
+            "min": 12050.388671875,
+            "max": 53777.86328125,
+            "count": 761
+        },
+        "SoccerTwos.Environment.EpisodeLength.mean": {
+            "value": 59.142857142857146,
+            "min": 38.196850393700785,
+            "max": 91.75,
+            "count": 761
+        },
+        "SoccerTwos.Environment.EpisodeLength.sum": {
+            "value": 19872.0,
+            "min": 3236.0,
+            "max": 21184.0,
+            "count": 761
+        },
+        "SoccerTwos.Self-play.ELO.mean": {
+            "value": 1529.7088135388522,
+            "min": 1422.9264545281249,
+            "max": 1573.7982628040145,
+            "count": 761
+        },
+        "SoccerTwos.Self-play.ELO.sum": {
+            "value": 256991.08067452715,
+            "min": 42878.86507428949,
+            "max": 382782.2583887068,
+            "count": 761
+        },
+        "SoccerTwos.Step.mean": {
+            "value": 10029872.0,
+            "min": 2429979.0,
+            "max": 10029872.0,
+            "count": 761
+        },
+        "SoccerTwos.Step.sum": {
+            "value": 10029872.0,
+            "min": 2429979.0,
+            "max": 10029872.0,
+            "count": 761
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
+            "value": -0.031066184863448143,
+            "min": -0.1180698424577713,
+            "max": 0.1087309867143631,
+            "count": 761
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
+            "value": -5.219119071960449,
+            "min": -21.02879524230957,
+            "max": 19.492877960205078,
+            "count": 761
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
+            "value": -0.035260315984487534,
+            "min": -0.11848477274179459,
+            "max": 0.1105712503194809,
+            "count": 761
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
+            "value": -5.923733234405518,
+            "min": -20.94308090209961,
+            "max": 19.144439697265625,
+            "count": 761
+        },
+        "SoccerTwos.Environment.CumulativeReward.mean": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 761
+        },
+        "SoccerTwos.Environment.CumulativeReward.sum": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 761
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.mean": {
+            "value": -0.2327690479301271,
+            "min": -0.32567314182009016,
+            "max": 0.32442905250208337,
+            "count": 761
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.sum": {
+            "value": -39.10520005226135,
+            "min": -57.35360014438629,
+            "max": 58.072800397872925,
+            "count": 761
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.mean": {
+            "value": -0.2327690479301271,
+            "min": -0.32567314182009016,
+            "max": 0.32442905250208337,
+            "count": 761
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.sum": {
+            "value": -39.10520005226135,
+            "min": -57.35360014438629,
+            "max": 58.072800397872925,
+            "count": 761
+        },
+        "SoccerTwos.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 761
+        },
+        "SoccerTwos.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 761
+        },
+        "SoccerTwos.Losses.PolicyLoss.mean": {
+            "value": 0.017179827320311838,
+            "min": 0.010565199363675977,
+            "max": 0.02532601624261588,
+            "count": 369
+        },
+        "SoccerTwos.Losses.PolicyLoss.sum": {
+            "value": 0.017179827320311838,
+            "min": 0.010565199363675977,
+            "max": 0.02532601624261588,
+            "count": 369
+        },
+        "SoccerTwos.Losses.ValueLoss.mean": {
+            "value": 0.0999237209558487,
+            "min": 0.07022709188361963,
+            "max": 0.12925801649689675,
+            "count": 369
+        },
+        "SoccerTwos.Losses.ValueLoss.sum": {
+            "value": 0.0999237209558487,
+            "min": 0.07022709188361963,
+            "max": 0.12925801649689675,
+            "count": 369
+        },
+        "SoccerTwos.Losses.BaselineLoss.mean": {
+            "value": 0.10240304668744406,
+            "min": 0.07139496964712938,
+            "max": 0.13219926357269288,
+            "count": 369
+        },
+        "SoccerTwos.Losses.BaselineLoss.sum": {
+            "value": 0.10240304668744406,
+            "min": 0.07139496964712938,
+            "max": 0.13219926357269288,
+            "count": 369
+        },
+        "SoccerTwos.Policy.LearningRate.mean": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 369
+        },
+        "SoccerTwos.Policy.LearningRate.sum": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 369
+        },
+        "SoccerTwos.Policy.Epsilon.mean": {
+            "value": 0.20000000000000007,
+            "min": 0.20000000000000007,
+            "max": 0.20000000000000007,
+            "count": 369
+        },
+        "SoccerTwos.Policy.Epsilon.sum": {
+            "value": 0.20000000000000007,
+            "min": 0.20000000000000007,
+            "max": 0.20000000000000007,
+            "count": 369
+        },
+        "SoccerTwos.Policy.Beta.mean": {
+            "value": 0.005000000000000001,
+            "min": 0.005000000000000001,
+            "max": 0.005000000000000001,
+            "count": 369
+        },
+        "SoccerTwos.Policy.Beta.sum": {
+            "value": 0.005000000000000001,
+            "min": 0.005000000000000001,
+            "max": 0.005000000000000001,
+            "count": 369
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1691417556",
+        "python_version": "3.8.17 (default, Jul  5 2023, 20:44:21) [MSC v.1916 64 bit (AMD64)]",
+        "command_line_arguments": "C:\\Users\\nokot\\miniconda3\\envs\\ml-agents\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --no-graphics --resume",
+        "mlagents_version": "0.30.0",
+        "mlagents_envs_version": "0.30.0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "1.7.1+cpu",
+        "numpy_version": "1.21.2",
+        "end_time_seconds": "1691501578"
+    },
+    "total": 84023.94156210001,
+    "count": 1,
+    "self": 0.33657540001149755,
+    "children": {
+        "run_training.setup": {
+            "total": 0.15175470000000013,
+            "count": 1,
+            "self": 0.15175470000000013
+        },
+        "TrainerController.start_learning": {
+            "total": 84023.453232,
+            "count": 1,
+            "self": 30.030664897349197,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 10.714601099975752,
+                    "count": 39,
+                    "self": 10.714601099975752
+                },
+                "TrainerController.advance": {
+                    "total": 83982.26639350268,
+                    "count": 527687,
+                    "self": 31.88441820141452,
+                    "children": {
+                        "env_step": {
+                            "total": 21282.278971898933,
+                            "count": 527687,
+                            "self": 16135.11157879619,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 5127.16464080181,
+                                    "count": 527687,
+                                    "self": 177.39852979446914,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 4949.76611100734,
+                                            "count": 954018,
+                                            "self": 4949.76611100734
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 20.002752300934617,
+                                    "count": 527687,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 83969.881665199,
+                                            "count": 527687,
+                                            "is_parallel": true,
+                                            "self": 71320.51937559372,
+                                            "children": {
+                                                "steps_from_proto": {
+                                                    "total": 0.19051710006376155,
+                                                    "count": 78,
+                                                    "is_parallel": true,
+                                                    "self": 0.04021390001721237,
+                                                    "children": {
+                                                        "_process_rank_one_or_two_observation": {
+                                                            "total": 0.15030320004654918,
+                                                            "count": 312,
+                                                            "is_parallel": true,
+                                                            "self": 0.15030320004654918
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 12649.171772505219,
+                                                    "count": 527687,
+                                                    "is_parallel": true,
+                                                    "self": 709.8374647020391,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 705.6238761024485,
+                                                            "count": 527687,
+                                                            "is_parallel": true,
+                                                            "self": 705.6238761024485
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 8715.422255598512,
+                                                            "count": 527687,
+                                                            "is_parallel": true,
+                                                            "self": 8715.422255598512
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 2518.2881761022186,
+                                                            "count": 1055374,
+                                                            "is_parallel": true,
+                                                            "self": 544.6141842024838,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 1973.6739918997348,
+                                                                    "count": 4221496,
+                                                                    "is_parallel": true,
+                                                                    "self": 1973.6739918997348
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 62668.10300340233,
+                            "count": 527687,
+                            "self": 174.5810705012409,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 23944.859248801124,
+                                    "count": 527687,
+                                    "self": 23938.519073401123,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 6.340175399999907,
+                                            "count": 16,
+                                            "self": 6.340175399999907
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 38548.66268409997,
+                                    "count": 369,
+                                    "self": 2733.2539645000797,
+                                    "children": {
+                                        "TorchPOCAOptimizer.update": {
+                                            "total": 35815.40871959989,
+                                            "count": 11070,
+                                            "self": 35815.40871959989
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 2.7999922167509794e-06,
+                    "count": 1,
+                    "self": 2.7999922167509794e-06
+                },
+                "TrainerController._save_models": {
+                    "total": 0.44156970000767615,
+                    "count": 1,
+                    "self": 0.01958220000960864,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.4219874999980675,
+                            "count": 1,
+                            "self": 0.4219874999980675
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,66 @@
+{
+    "SoccerTwos": {
+        "checkpoints": [
+            {
+                "steps": 8499935,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-8499935.onnx",
+                "reward": 0.0,
+                "creation_time": 1691480337.3792727,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-8499935.pt"
+                ]
+            },
+            {
+                "steps": 8999939,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-8999939.onnx",
+                "reward": 0.0,
+                "creation_time": 1691485773.2655866,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-8999939.pt"
+                ]
+            },
+            {
+                "steps": 9499966,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-9499966.onnx",
+                "reward": 0.0,
+                "creation_time": 1691490879.6117523,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-9499966.pt"
+                ]
+            },
+            {
+                "steps": 9999933,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-9999933.onnx",
+                "reward": 0.0,
+                "creation_time": 1691501234.8872063,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-9999933.pt"
+                ]
+            },
+            {
+                "steps": 10032342,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-10032342.onnx",
+                "reward": 0.0,
+                "creation_time": 1691501577.738297,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-10032342.pt"
+                ]
+            }
+        ],
+        "elo": 1526.8011975685909,
+        "final_checkpoint": {
+            "steps": 10032342,
+            "file_path": "results\\SoccerTwos\\SoccerTwos.onnx",
+            "reward": 0.0,
+            "creation_time": 1691501577.738297,
+            "auxillary_file_paths": [
+                "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-10032342.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "0.30.0",
+        "torch_version": "1.7.1+cpu"
+    }
+}