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: CzarnyRycerz/Yudkowsky
+  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 sha256:1bfd01c0118f2f15a5f3c974b6839e9951f42783ca8ddbef1db63a1005c84a1c
+size 4923442

SoccerTwos/SoccerTwos-21500167.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1bfd01c0118f2f15a5f3c974b6839e9951f42783ca8ddbef1db63a1005c84a1c
+size 4923442

SoccerTwos/SoccerTwos-21500167.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:376eb806eaf3eec6d05f14814dc0b15e2d09a96a86a08620ffc0be71ced28a94
+size 47356393

SoccerTwos/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bea81a49612bbb7c4011241b8f0dec6725887a3b8ce6267021659773bad4c8bd
+size 47354863

SoccerTwos/events.out.tfevents.1694390584.DESKTOP-L0G93AV.12928.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:626cd28e8b6b4062ff3c5d5110eb1788c7676d2d8dc9086f241bb16d29755b7f
+size 1711298

SoccerTwos/events.out.tfevents.1694397682.DESKTOP-L0G93AV.12020.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9facc3943b3754493750f74471f3a03dfe209dce2ae0d02d71da63493b06e55b
+size 274459

SoccerTwos/events.out.tfevents.1694397887.DESKTOP-L0G93AV.9792.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd7863ccbe17358b53aa447b3bfeb5c7df539901232afb754d2930320a0f4385
+size 198863

SoccerTwos/events.out.tfevents.1694398171.DESKTOP-L0G93AV.14132.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ded154a3e7fdb8044ab8886bef3dbe2f6551998c0db64e3320d67bc2f1853190
+size 867508

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": 0.01, "epsilon": 0.25, "lambd": 0.95, "num_epoch": 3, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "constant"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 5, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.986, "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": 21500000, "time_horizon": 1000, "summary_freq": 5000, "threaded": false, "self_play": {"save_steps": 200000, "team_change": 200000, "swap_steps": 2000, "window": 50, "play_against_latest_model_ratio": 0.5, "initial_elo": 1200.0}, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/SoccerTwos/SoccerTwos.exe", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "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: 0.01
+      epsilon: 0.25
+      lambd: 0.95
+      num_epoch: 3
+      learning_rate_schedule: linear
+      beta_schedule: linear
+      epsilon_schedule: constant
+    checkpoint_interval: 500000
+    network_settings:
+      normalize: false
+      hidden_units: 512
+      num_layers: 5
+      vis_encode_type: simple
+      memory: null
+      goal_conditioning_type: hyper
+      deterministic: false
+    reward_signals:
+      extrinsic:
+        gamma: 0.986
+        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: 21500000
+    time_horizon: 1000
+    summary_freq: 5000
+    threaded: false
+    self_play:
+      save_steps: 200000
+      team_change: 200000
+      swap_steps: 2000
+      window: 50
+      play_against_latest_model_ratio: 0.5
+      initial_elo: 1200.0
+    behavioral_cloning: null
+env_settings:
+  env_path: ./training-envs-executables/SoccerTwos/SoccerTwos.exe
+  env_args: null
+  base_port: 5005
+  num_envs: 1
+  num_areas: 1
+  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 +1,262 @@
+Mono path[0] = 'C:/ml-agents-2/training-envs-executables/SoccerTwos/SoccerTwos_Data/Managed'
+Mono config path = 'C:/ml-agents-2/training-envs-executables/SoccerTwos/MonoBleedingEdge/etc'
+Initialize engine version: 2021.3.14f1 (eee1884e7226)
+[Subsystems] Discovering subsystems at path C:/ml-agents-2/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  0.150 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: 0.860400 ms
+Registered Communicator in Agent.
+ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+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]: 7924 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 282 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 2
+    [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]: 7925 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]: 7925 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 17.5 MB
+      Peak Large allocation bytes 16.0 MB
+[ALLOC_TEMP_JOB_1_FRAME]
+  Initial Block Size 2.0 MB
+  Used Block Count 1
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_TEMP_JOB_2_FRAMES]
+  Initial Block Size 2.0 MB
+  Used Block Count 1
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_TEMP_JOB_4_FRAMES (JobTemp)]
+  Initial Block Size 2.0 MB
+  Used Block Count 2
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_TEMP_JOB_ASYNC (Background)]
+  Initial Block Size 1.0 MB
+  Used Block Count 3
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_GFX] Dual Thread Allocator
+  Peak main deferred allocation count 0
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 0.9 MB
+    [ALLOC_GFX_MAIN]
+      Peak usage frame count: [32.0 KB-64.0 KB]: 7924 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]: 7925 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]: 7925 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]: 7924 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]: 7925 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]: 7924 frames, [2.0 KB-4.0 KB]: 1 frames
+      Requested Block Size 2.0 MB
+      Peak Block count 1
+      Peak Allocated memory 2.2 KB
+      Peak Large allocation bytes 0 B

run_logs/timers.json

@@ -0,0 +1,368 @@
+{
+    "name": "root",
+    "gauges": {
+        "SoccerTwos.Policy.Entropy.mean": {
+            "value": 2.6468665599823,
+            "min": 2.541663646697998,
+            "max": 2.871713161468506,
+            "count": 85
+        },
+        "SoccerTwos.Policy.Entropy.sum": {
+            "value": 25748.716796875,
+            "min": 8567.4287109375,
+            "max": 36632.6953125,
+            "count": 85
+        },
+        "SoccerTwos.Environment.EpisodeLength.mean": {
+            "value": 67.88888888888889,
+            "min": 40.714285714285715,
+            "max": 135.77777777777777,
+            "count": 85
+        },
+        "SoccerTwos.Environment.EpisodeLength.sum": {
+            "value": 9776.0,
+            "min": 1140.0,
+            "max": 10680.0,
+            "count": 85
+        },
+        "SoccerTwos.Self-play.ELO.mean": {
+            "value": 2375.3358173178267,
+            "min": 2235.5589987679004,
+            "max": 2381.703469709723,
+            "count": 85
+        },
+        "SoccerTwos.Self-play.ELO.sum": {
+            "value": 171024.17884688353,
+            "min": 31488.55584315862,
+            "max": 260906.22136500393,
+            "count": 85
+        },
+        "SoccerTwos.Step.mean": {
+            "value": 21499985.0,
+            "min": 21079986.0,
+            "max": 21499985.0,
+            "count": 85
+        },
+        "SoccerTwos.Step.sum": {
+            "value": 21499985.0,
+            "min": 21079986.0,
+            "max": 21499985.0,
+            "count": 85
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
+            "value": 0.13880492746829987,
+            "min": -0.029741428792476654,
+            "max": 0.25591257214546204,
+            "count": 85
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
+            "value": 9.9939546585083,
+            "min": -2.3920230865478516,
+            "max": 20.130294799804688,
+            "count": 85
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 0.13861840963363647,
+            "min": -0.03013807162642479,
+            "max": 0.2552904188632965,
+            "count": 85
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 9.980525016784668,
+            "min": -2.4623286724090576,
+            "max": 20.086620330810547,
+            "count": 85
+        },
+        "SoccerTwos.Environment.CumulativeReward.mean": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 85
+        },
+        "SoccerTwos.Environment.CumulativeReward.sum": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 85
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.mean": {
+            "value": 0.4470666680071089,
+            "min": -0.41783611062500214,
+            "max": 0.7164689590191019,
+            "count": 85
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.sum": {
+            "value": 32.18880009651184,
+            "min": -31.340400218963623,
+            "max": 52.656800270080566,
+            "count": 85
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.mean": {
+            "value": 0.4470666680071089,
+            "min": -0.41783611062500214,
+            "max": 0.7164689590191019,
+            "count": 85
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.sum": {
+            "value": 32.18880009651184,
+            "min": -31.340400218963623,
+            "max": 52.656800270080566,
+            "count": 85
+        },
+        "SoccerTwos.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 85
+        },
+        "SoccerTwos.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 85
+        },
+        "SoccerTwos.Losses.PolicyLoss.mean": {
+            "value": 0.015227855048821463,
+            "min": 0.011556042971399923,
+            "max": 0.020092821136737864,
+            "count": 20
+        },
+        "SoccerTwos.Losses.PolicyLoss.sum": {
+            "value": 0.015227855048821463,
+            "min": 0.011556042971399923,
+            "max": 0.020092821136737864,
+            "count": 20
+        },
+        "SoccerTwos.Losses.ValueLoss.mean": {
+            "value": 0.09070096512635549,
+            "min": 0.05192163946727912,
+            "max": 0.09316741997996966,
+            "count": 20
+        },
+        "SoccerTwos.Losses.ValueLoss.sum": {
+            "value": 0.09070096512635549,
+            "min": 0.05192163946727912,
+            "max": 0.09316741997996966,
+            "count": 20
+        },
+        "SoccerTwos.Losses.BaselineLoss.mean": {
+            "value": 0.09092343325416247,
+            "min": 0.05207549768189589,
+            "max": 0.09350195775429408,
+            "count": 20
+        },
+        "SoccerTwos.Losses.BaselineLoss.sum": {
+            "value": 0.09092343325416247,
+            "min": 0.05207549768189589,
+            "max": 0.09350195775429408,
+            "count": 20
+        },
+        "SoccerTwos.Policy.LearningRate.mean": {
+            "value": 1.113511257069722e-07,
+            "min": 1.113511257069722e-07,
+            "max": 5.578772559046528e-06,
+            "count": 20
+        },
+        "SoccerTwos.Policy.LearningRate.sum": {
+            "value": 1.113511257069722e-07,
+            "min": 1.113511257069722e-07,
+            "max": 5.578772559046528e-06,
+            "count": 20
+        },
+        "SoccerTwos.Policy.Epsilon.mean": {
+            "value": 0.25,
+            "min": 0.25,
+            "max": 0.25,
+            "count": 20
+        },
+        "SoccerTwos.Policy.Epsilon.sum": {
+            "value": 0.25,
+            "min": 0.25,
+            "max": 0.25,
+            "count": 20
+        },
+        "SoccerTwos.Policy.Beta.mean": {
+            "value": 1.3704663720930079e-05,
+            "min": 1.3704663720930079e-05,
+            "max": 0.00019576985813953539,
+            "count": 20
+        },
+        "SoccerTwos.Policy.Beta.sum": {
+            "value": 1.3704663720930079e-05,
+            "min": 1.3704663720930079e-05,
+            "max": 0.00019576985813953539,
+            "count": 20
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1694398166",
+        "python_version": "3.9.17 (main, Jul  5 2023, 20:47:11) [MSC v.1916 64 bit (AMD64)]",
+        "command_line_arguments": "\\\\?\\F:\\ProgramData\\anaconda3\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/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": "1694401048"
+    },
+    "total": 2881.8619468,
+    "count": 1,
+    "self": 0.39316980000012336,
+    "children": {
+        "run_training.setup": {
+            "total": 0.14249270000000003,
+            "count": 1,
+            "self": 0.14249270000000003
+        },
+        "TrainerController.start_learning": {
+            "total": 2881.3262843,
+            "count": 1,
+            "self": 0.9726952999972127,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 5.015679300000025,
+                    "count": 4,
+                    "self": 5.015679300000025
+                },
+                "TrainerController.advance": {
+                    "total": 2875.053183500003,
+                    "count": 28831,
+                    "self": 1.0066420000871403,
+                    "children": {
+                        "env_step": {
+                            "total": 763.5760517999634,
+                            "count": 28831,
+                            "self": 499.511171099941,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 263.4686580999995,
+                                    "count": 28831,
+                                    "self": 7.140219500018418,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 256.3284385999811,
+                                            "count": 52834,
+                                            "self": 256.3284385999811
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 0.596222600022843,
+                                    "count": 28831,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 2874.6264508000168,
+                                            "count": 28831,
+                                            "is_parallel": true,
+                                            "self": 2490.8024807999996,
+                                            "children": {
+                                                "steps_from_proto": {
+                                                    "total": 0.010278200000094273,
+                                                    "count": 8,
+                                                    "is_parallel": true,
+                                                    "self": 0.0023597000005421975,
+                                                    "children": {
+                                                        "_process_rank_one_or_two_observation": {
+                                                            "total": 0.007918499999552076,
+                                                            "count": 32,
+                                                            "is_parallel": true,
+                                                            "self": 0.007918499999552076
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 383.813691800017,
+                                                    "count": 28831,
+                                                    "is_parallel": true,
+                                                    "self": 20.69146799995832,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 21.049770600046077,
+                                                            "count": 28831,
+                                                            "is_parallel": true,
+                                                            "self": 21.049770600046077
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 274.51462600000644,
+                                                            "count": 28831,
+                                                            "is_parallel": true,
+                                                            "self": 274.51462600000644
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 67.55782720000619,
+                                                            "count": 57662,
+                                                            "is_parallel": true,
+                                                            "self": 15.188267900029203,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 52.369559299976984,
+                                                                    "count": 230648,
+                                                                    "is_parallel": true,
+                                                                    "self": 52.369559299976984
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 2110.4704896999524,
+                            "count": 28831,
+                            "self": 7.441301699985161,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 285.196211699967,
+                                    "count": 28831,
+                                    "self": 284.83748069996676,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 0.3587310000002617,
+                                            "count": 1,
+                                            "self": 0.3587310000002617
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 1817.8329763000004,
+                                    "count": 20,
+                                    "self": 120.90873570000258,
+                                    "children": {
+                                        "TorchPOCAOptimizer.update": {
+                                            "total": 1696.9242405999978,
+                                            "count": 600,
+                                            "self": 1696.9242405999978
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 1.100000190490391e-06,
+                    "count": 1,
+                    "self": 1.100000190490391e-06
+                },
+                "TrainerController._save_models": {
+                    "total": 0.2847250999998323,
+                    "count": 1,
+                    "self": 0.014907899999798246,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.26981720000003406,
+                            "count": 1,
+                            "self": 0.26981720000003406
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,66 @@
+{
+    "SoccerTwos": {
+        "elo": 2378.5587485603514,
+        "checkpoints": [
+            {
+                "steps": 21000399,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-21000399.onnx",
+                "reward": 0.0,
+                "creation_time": 1694397620.4792032,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-21000399.pt"
+                ]
+            },
+            {
+                "steps": 21038137,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-21038137.onnx",
+                "reward": 0.0,
+                "creation_time": 1694397873.9209023,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-21038137.pt"
+                ]
+            },
+            {
+                "steps": 21079421,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-21079421.onnx",
+                "reward": null,
+                "creation_time": 1694398159.6217656,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-21079421.pt"
+                ]
+            },
+            {
+                "steps": 21499985,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-21499985.onnx",
+                "reward": 0.0,
+                "creation_time": 1694401047.7593436,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-21499985.pt"
+                ]
+            },
+            {
+                "steps": 21500167,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-21500167.onnx",
+                "reward": 0.0,
+                "creation_time": 1694401048.1302075,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-21500167.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 21500167,
+            "file_path": "results\\SoccerTwos\\SoccerTwos.onnx",
+            "reward": 0.0,
+            "creation_time": 1694401048.1302075,
+            "auxillary_file_paths": [
+                "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-21500167.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "0.31.0.dev0",
+        "torch_version": "2.0.1+cpu"
+    }
+}