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: amostof/poca-SoccerTwos
+  3. Step 2: Select your *.nn /*.onnx file
+  4. Click on Watch the agent play 👀
+  

SoccerTwos/SoccerTwos-71934.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41c70643a040a13fa22fee2e02eaf8fcd5a8ecba5b4812106e852fc1e7d9398f
+size 28430110

SoccerTwos/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36e4d1a14ff43e51d9290fb5e530154503a55149bf7993c051f9882b29c8eb7f
+size 28429366

SoccerTwos/events.out.tfevents.1740688154.Laptop-Amir.local.21257.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d10560c2f915d2ed26cc3f11be1679287a887b3bb87aa6d38a5263378c6f0de4
+size 43953

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": 300000, "swap_steps": 2000, "window": 10, "play_against_latest_model_ratio": 0.5, "initial_elo": 1200.0}, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/SoccerTwos/SoccerTwos.app", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SoccerTwos", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -0,0 +1,84 @@
+default_settings: null
+behaviors:
+  SoccerTwos:
+    trainer_type: poca
+    hyperparameters:
+      batch_size: 2048
+      buffer_size: 20480
+      learning_rate: 0.0003
+      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: 300000
+      swap_steps: 2000
+      window: 10
+      play_against_latest_model_ratio: 0.5
+      initial_elo: 1200.0
+    behavioral_cloning: null
+env_settings:
+  env_path: ./training-envs-executables/SoccerTwos/SoccerTwos.app
+  env_args: null
+  base_port: 5005
+  num_envs: 1
+  num_areas: 1
+  timeout_wait: 60
+  seed: -1
+  max_lifetime_restarts: 10
+  restarts_rate_limit_n: 1
+  restarts_rate_limit_period_s: 60
+engine_settings:
+  width: 84
+  height: 84
+  quality_level: 5
+  time_scale: 20
+  target_frame_rate: -1
+  capture_frame_rate: 60
+  no_graphics: true
+  no_graphics_monitor: false
+environment_parameters: null
+checkpoint_settings:
+  run_id: SoccerTwos
+  initialize_from: null
+  load_model: false
+  resume: false
+  force: false
+  train_model: false
+  inference: false
+  results_dir: results
+torch_settings:
+  device: null
+debug: false

run_logs/Player-0.log

@@ -0,0 +1,325 @@
+Mono path[0] = '/Users/amir/Documents/DeepRL/ml-agents/training-envs-executables/SoccerTwos/SoccerTwos.app/Contents/Resources/Data/Managed'
+Mono config path = '/Users/amir/Documents/DeepRL/ml-agents/training-envs-executables/SoccerTwos/SoccerTwos.app/Contents/MonoBleedingEdge/etc'
+New input system (experimental) initialized
+Initialize engine version: 2021.3.17f1 (3e8111cac19d)
+[Subsystems] Discovering subsystems at path /Users/amir/Documents/DeepRL/ml-agents/training-envs-executables/SoccerTwos/SoccerTwos.app/Contents/Resources/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  0.084 seconds
+ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+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: 0.410208 ms
+Registered Communicator in Agent.
+ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+Thread 0x170cef000 may have been prematurely finalized
+Setting up 5 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]: 1493 frames, [2.0 MB-4.0 MB]: 1 frames
+      Initial Block Size 4.0 MB
+      Current Block Size 4.0 MB
+      Peak Allocated Bytes 2.1 MB
+      Overflow Count 0
+    [ALLOC_TEMP_Loading.AsyncRead]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 141 B
+      Overflow Count 0
+    [ALLOC_TEMP_Loading.PreloadManager]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 78.8 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 0 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 0 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 0 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 0 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 0 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 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_EnlightenWorker] x 5
+      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 15]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 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 0 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 0 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 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_AssetGarbageCollectorHelper] x 9
+      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 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 13]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 8]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_OSX HID Input]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 7]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 1]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0.7 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 2]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 3]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 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 0 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 0 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 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_BatchDeleteObjects]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 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 1.0 MB
+    [ALLOC_DEFAULT_MAIN]
+      Peak usage frame count: [4.0 MB-8.0 MB]: 1494 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 4.8 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 1494 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 1.0 MB
+    [ALLOC_GFX_MAIN]
+      Peak usage frame count: [32.0 KB-64.0 KB]: 1493 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]: 1494 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 173.5 KB
+      Peak Large allocation bytes 0 B
+[ALLOC_CACHEOBJECTS] Dual Thread Allocator
+  Peak main deferred allocation count 0
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 1.0 MB
+    [ALLOC_CACHEOBJECTS_MAIN]
+      Peak usage frame count: [0.5 MB-1.0 MB]: 1494 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]: 1493 frames, [2.0 MB-4.0 MB]: 1 frames
+      Requested Block Size 4.0 MB
+      Peak Block count 1
+      Peak Allocated memory 3.0 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 1.0 MB
+    [ALLOC_TYPETREE_MAIN]
+      Peak usage frame count: [0-1.0 KB]: 1494 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]: 1493 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 +1,356 @@
+{
+    "name": "root",
+    "gauges": {
+        "SoccerTwos.Policy.Entropy.mean": {
+            "value": 3.273122549057007,
+            "min": 3.273122549057007,
+            "max": 3.2956995964050293,
+            "count": 7
+        },
+        "SoccerTwos.Policy.Entropy.sum": {
+            "value": 88819.453125,
+            "min": 36824.328125,
+            "max": 105462.390625,
+            "count": 7
+        },
+        "SoccerTwos.Environment.EpisodeLength.mean": {
+            "value": 986.3333333333334,
+            "min": 349.0,
+            "max": 999.0,
+            "count": 7
+        },
+        "SoccerTwos.Environment.EpisodeLength.sum": {
+            "value": 23672.0,
+            "min": 1396.0,
+            "max": 31968.0,
+            "count": 7
+        },
+        "SoccerTwos.Self-play.ELO.mean": {
+            "value": 1198.320921595067,
+            "min": 1197.273575898641,
+            "max": 1199.3173316810933,
+            "count": 6
+        },
+        "SoccerTwos.Self-play.ELO.sum": {
+            "value": 4793.283686380268,
+            "min": 2394.547151797282,
+            "max": 14377.498515805344,
+            "count": 6
+        },
+        "SoccerTwos.Step.mean": {
+            "value": 69978.0,
+            "min": 9354.0,
+            "max": 69978.0,
+            "count": 7
+        },
+        "SoccerTwos.Step.sum": {
+            "value": 69978.0,
+            "min": 9354.0,
+            "max": 69978.0,
+            "count": 7
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
+            "value": -0.029395604506134987,
+            "min": -0.029395604506134987,
+            "max": -0.027391143143177032,
+            "count": 5
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
+            "value": -0.4703296720981598,
+            "min": -0.4703296720981598,
+            "max": -0.27665016055107117,
+            "count": 5
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
+            "value": -0.027215536683797836,
+            "min": -0.027613306418061256,
+            "max": -0.025287168100476265,
+            "count": 5
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
+            "value": -0.4354485869407654,
+            "min": -0.4354485869407654,
+            "max": -0.2761234641075134,
+            "count": 5
+        },
+        "SoccerTwos.Environment.CumulativeReward.mean": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 7
+        },
+        "SoccerTwos.Environment.CumulativeReward.sum": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 7
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.mean": {
+            "value": -0.08109090544960716,
+            "min": -0.38461538461538464,
+            "max": 0.3400000110268593,
+            "count": 7
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.sum": {
+            "value": -0.8919999599456787,
+            "min": -5.045199990272522,
+            "max": 5.4400001764297485,
+            "count": 7
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.mean": {
+            "value": -0.08109090544960716,
+            "min": -0.38461538461538464,
+            "max": 0.3400000110268593,
+            "count": 7
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.sum": {
+            "value": -0.8919999599456787,
+            "min": -5.045199990272522,
+            "max": 5.4400001764297485,
+            "count": 7
+        },
+        "SoccerTwos.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 7
+        },
+        "SoccerTwos.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 7
+        },
+        "SoccerTwos.Losses.PolicyLoss.mean": {
+            "value": 0.020737362704433812,
+            "min": 0.019029662696647437,
+            "max": 0.020737362704433812,
+            "count": 2
+        },
+        "SoccerTwos.Losses.PolicyLoss.sum": {
+            "value": 0.020737362704433812,
+            "min": 0.019029662696647437,
+            "max": 0.020737362704433812,
+            "count": 2
+        },
+        "SoccerTwos.Losses.ValueLoss.mean": {
+            "value": 0.0020418568774836048,
+            "min": 0.0020418568774836048,
+            "max": 0.0020418568774836048,
+            "count": 1
+        },
+        "SoccerTwos.Losses.ValueLoss.sum": {
+            "value": 0.0020418568774836048,
+            "min": 0.0020418568774836048,
+            "max": 0.0020418568774836048,
+            "count": 1
+        },
+        "SoccerTwos.Losses.BaselineLoss.mean": {
+            "value": 0.001893633756221139,
+            "min": 0.001893633756221139,
+            "max": 0.001893633756221139,
+            "count": 1
+        },
+        "SoccerTwos.Losses.BaselineLoss.sum": {
+            "value": 0.001893633756221139,
+            "min": 0.001893633756221139,
+            "max": 0.001893633756221139,
+            "count": 1
+        },
+        "SoccerTwos.Policy.LearningRate.mean": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 2
+        },
+        "SoccerTwos.Policy.LearningRate.sum": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 2
+        },
+        "SoccerTwos.Policy.Epsilon.mean": {
+            "value": 0.20000000000000007,
+            "min": 0.19999999999999996,
+            "max": 0.20000000000000007,
+            "count": 2
+        },
+        "SoccerTwos.Policy.Epsilon.sum": {
+            "value": 0.20000000000000007,
+            "min": 0.19999999999999996,
+            "max": 0.20000000000000007,
+            "count": 2
+        },
+        "SoccerTwos.Policy.Beta.mean": {
+            "value": 0.005000000000000001,
+            "min": 0.005,
+            "max": 0.005000000000000001,
+            "count": 2
+        },
+        "SoccerTwos.Policy.Beta.sum": {
+            "value": 0.005000000000000001,
+            "min": 0.005,
+            "max": 0.005000000000000001,
+            "count": 2
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1740688151",
+        "python_version": "3.10.12 (main, Jul  5 2023, 15:02:25) [Clang 14.0.6 ]",
+        "command_line_arguments": "/Users/amir/anaconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.app --run-id=SoccerTwos --no-graphics",
+        "mlagents_version": "1.2.0.dev0",
+        "mlagents_envs_version": "1.2.0.dev0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "2.6.0",
+        "numpy_version": "1.23.5",
+        "end_time_seconds": "1740688431"
+    },
+    "total": 280.2057829590012,
+    "count": 1,
+    "self": 0.224106584002584,
+    "children": {
+        "run_training.setup": {
+            "total": 0.022819750000053318,
+            "count": 1,
+            "self": 0.022819750000053318
+        },
+        "TrainerController.start_learning": {
+            "total": 279.9588566249986,
+            "count": 1,
+            "self": 0.0579930067397072,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 3.7447732920009003,
+                    "count": 1,
+                    "self": 3.7447732920009003
+                },
+                "TrainerController.advance": {
+                    "total": 276.02421032625716,
+                    "count": 5001,
+                    "self": 0.053040216935187345,
+                    "children": {
+                        "env_step": {
+                            "total": 225.45828245407756,
+                            "count": 5001,
+                            "self": 215.46659168500264,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 9.953332595054235,
+                                    "count": 5001,
+                                    "self": 0.24310704026720487,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 9.71022555478703,
+                                            "count": 9958,
+                                            "self": 9.71022555478703
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 0.03835817402068642,
+                                    "count": 5000,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 276.7622806810941,
+                                            "count": 5000,
+                                            "is_parallel": true,
+                                            "self": 69.43057033927471,
+                                            "children": {
+                                                "steps_from_proto": {
+                                                    "total": 0.001644916002987884,
+                                                    "count": 2,
+                                                    "is_parallel": true,
+                                                    "self": 0.0002262499947391916,
+                                                    "children": {
+                                                        "_process_rank_one_or_two_observation": {
+                                                            "total": 0.0014186660082486924,
+                                                            "count": 8,
+                                                            "is_parallel": true,
+                                                            "self": 0.0014186660082486924
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 207.33006542581643,
+                                                    "count": 5000,
+                                                    "is_parallel": true,
+                                                    "self": 0.6085860606945062,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 3.5735817189524823,
+                                                            "count": 5000,
+                                                            "is_parallel": true,
+                                                            "self": 3.5735817189524823
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 195.70611232615192,
+                                                            "count": 5000,
+                                                            "is_parallel": true,
+                                                            "self": 195.70611232615192
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 7.441785320017516,
+                                                            "count": 10000,
+                                                            "is_parallel": true,
+                                                            "self": 0.8515734473185148,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 6.590211872699001,
+                                                                    "count": 40000,
+                                                                    "is_parallel": true,
+                                                                    "self": 6.590211872699001
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 50.51288765524441,
+                            "count": 5000,
+                            "self": 0.45996707937592873,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 7.4487364088709,
+                                    "count": 5000,
+                                    "self": 7.4487364088709
+                                },
+                                "_update_policy": {
+                                    "total": 42.604184166997584,
+                                    "count": 3,
+                                    "self": 4.489408828998421,
+                                    "children": {
+                                        "TorchPOCAOptimizer.update": {
+                                            "total": 38.11477533799916,
+                                            "count": 102,
+                                            "self": 38.11477533799916
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "TrainerController._save_models": {
+                    "total": 0.13188000000081956,
+                    "count": 1,
+                    "self": 2.0459003280848265e-05,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.13185954099753872,
+                            "count": 1,
+                            "self": 0.13185954099753872
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,10 @@
+{
+    "SoccerTwos": {
+        "elo": 1199.0723016025067
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "1.2.0.dev0",
+        "torch_version": "2.6.0"
+    }
+}