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: Misbah17311/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 sha256:866a1844cb655290a547938347ab609c0421a85fb5554c03a44273bafea65881
+size 1768747

SoccerTwos/SoccerTwos-28499924.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc614b957e06c4e363522422b28b98f04749eb5beeb2faa3a5eedab9571bbdf1
+size 1768747

SoccerTwos/SoccerTwos-28499924.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c71312655fd1431e1d77928c073a7735b30ba0e5ed139fea30361dbe2e5a254
+size 28430967

SoccerTwos/SoccerTwos-28999974.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1867e3ce227b9b6540ae19a538cdf71fba52c6e61ba0d07661663d9e67e3654
+size 1768747

SoccerTwos/SoccerTwos-28999974.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf16abc5b7292c3a26085abe5b7c696b437b52f12f7c3fb420fc8cb546a93020
+size 28430967

SoccerTwos/SoccerTwos-29499971.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5969a99f373b3197f06b05fe7c59d71a2443d9bbce2ffc36328c0cf59b738502
+size 1768747

SoccerTwos/SoccerTwos-29499971.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bddbdac53ba49616035cf57451797483d0d6616ed724dc85b1127b65521c0e46
+size 28430967

SoccerTwos/SoccerTwos-29999974.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:866a1844cb655290a547938347ab609c0421a85fb5554c03a44273bafea65881
+size 1768747

SoccerTwos/SoccerTwos-29999974.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78fc66b00975ee20c22dbc1cab6294088c2f6cf3b7dfffb82c396ae56323a4a5
+size 28430967

SoccerTwos/SoccerTwos-30000018.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:866a1844cb655290a547938347ab609c0421a85fb5554c03a44273bafea65881
+size 1768747

SoccerTwos/SoccerTwos-30000018.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ad253889b3c21aa03dc3a9dcfbf8ef2f9d1aed64ffc649d618b55d43ef27f04
+size 28430967

SoccerTwos/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25fe8fb05a61c2b51b1e1c2fc308b15a93581b398b8bdfed3cb1ba74b3f12b7f
+size 28429769

SoccerTwos/events.out.tfevents.1747938902.misbah-IdeaPad-Gaming-3-15IAH7.13047.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d24dc461a765e4b5f9c43fa94556349d1e558db7df3c1de4e2eabaf64d70575
+size 27537620

SoccerTwos/events.out.tfevents.1747997677.misbah-IdeaPad-Gaming-3-15IAH7.102445.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b83be4e8d7615892136c4d4d333178765ee34295b0c04c2b9068bc8dbde869a8
+size 2364947

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": 30000000, "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/SoccerTwos.x86_64", "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": true, "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: 30000000
+    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/SoccerTwos.x86_64
+  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: true
+  force: false
+  train_model: false
+  inference: false
+  results_dir: results
+torch_settings:
+  device: null
+debug: false

run_logs/Player-0.log

@@ -0,0 +1,284 @@
+Mono path[0] = '/home/misbah/ml-agents/training-envs-executables/SoccerTwos/SoccerTwos_Data/Managed'
+Mono config path = '/home/misbah/ml-agents/training-envs-executables/SoccerTwos/SoccerTwos_Data/MonoBleedingEdge/etc'
+Preloaded 'lib_burst_generated.so'
+Preloaded 'libgrpc_csharp_ext.x64.so'
+Initialize engine version: 2021.3.14f1 (eee1884e7226)
+[Subsystems] Discovering subsystems at path /home/misbah/ml-agents/training-envs-executables/SoccerTwos/SoccerTwos_Data/UnitySubsystems
+Forcing GfxDevice: Null
+GfxDevice: creating device client; threaded=0; jobified=0
+NullGfxDevice:
+    Version:  NULL 1.0 [1.0]
+    Renderer: Null Device
+    Vendor:   Unity Technologies
+Begin MonoManager ReloadAssembly
+- Completed reload, in  0.059 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: 0.408562 ms
+Registered Communicator in Agent.
+ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+requesting resize 84 x 84
+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]: 43318 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 128 B
+      Overflow Count 0
+    [ALLOC_TEMP_Loading.PreloadManager]
+      Initial Block Size 256.0 KB
+      Current Block Size 300.0 KB
+      Peak Allocated Bytes 249.6 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 0.7 KB
+      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 4
+      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 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 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 1]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 2]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 3]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 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]: 43319 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]: 43319 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 1.0 MB
+    [ALLOC_GFX_MAIN]
+      Peak usage frame count: [32.0 KB-64.0 KB]: 43318 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]: 43319 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]: 43319 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]: 43318 frames, [4.0 MB-8.0 MB]: 1 frames
+      Requested Block Size 4.0 MB
+      Peak Block count 2
+      Peak Allocated memory 4.5 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]: 43319 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]: 43318 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 +1,424 @@
+{
+    "name": "root",
+    "gauges": {
+        "SoccerTwos.Policy.Entropy.mean": {
+            "value": 1.5260498523712158,
+            "min": 1.47836434841156,
+            "max": 1.5717905759811401,
+            "count": 230
+        },
+        "SoccerTwos.Policy.Entropy.sum": {
+            "value": 30472.1640625,
+            "min": 23978.40234375,
+            "max": 38699.16796875,
+            "count": 230
+        },
+        "SoccerTwos.Environment.EpisodeLength.mean": {
+            "value": 70.20289855072464,
+            "min": 58.97560975609756,
+            "max": 111.08695652173913,
+            "count": 230
+        },
+        "SoccerTwos.Environment.EpisodeLength.sum": {
+            "value": 19376.0,
+            "min": 14248.0,
+            "max": 21124.0,
+            "count": 230
+        },
+        "SoccerTwos.Self-play.ELO.mean": {
+            "value": 1712.0493582103122,
+            "min": 1700.9733828056937,
+            "max": 1764.6453188312037,
+            "count": 230
+        },
+        "SoccerTwos.Self-play.ELO.sum": {
+            "value": 236262.81143302307,
+            "min": 135199.9946404582,
+            "max": 293076.2351296764,
+            "count": 230
+        },
+        "SoccerTwos.Step.mean": {
+            "value": 29999974.0,
+            "min": 27709981.0,
+            "max": 29999974.0,
+            "count": 230
+        },
+        "SoccerTwos.Step.sum": {
+            "value": 29999974.0,
+            "min": 27709981.0,
+            "max": 29999974.0,
+            "count": 230
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
+            "value": -0.02527669444680214,
+            "min": -0.12162230163812637,
+            "max": 0.04789558798074722,
+            "count": 230
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
+            "value": -3.513460636138916,
+            "min": -18.121723175048828,
+            "max": 7.892575263977051,
+            "count": 230
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
+            "value": -0.02623376064002514,
+            "min": -0.12381523102521896,
+            "max": 0.050768427550792694,
+            "count": 230
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
+            "value": -3.6464927196502686,
+            "min": -18.448469161987305,
+            "max": 8.272490501403809,
+            "count": 230
+        },
+        "SoccerTwos.Environment.CumulativeReward.mean": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 230
+        },
+        "SoccerTwos.Environment.CumulativeReward.sum": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 230
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.mean": {
+            "value": 0.09223597041136927,
+            "min": -0.3490041961203088,
+            "max": 0.36174961674304407,
+            "count": 230
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.sum": {
+            "value": 12.820799887180328,
+            "min": -49.90760004520416,
+            "max": 47.389199793338776,
+            "count": 230
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.mean": {
+            "value": 0.09223597041136927,
+            "min": -0.3490041961203088,
+            "max": 0.36174961674304407,
+            "count": 230
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.sum": {
+            "value": 12.820799887180328,
+            "min": -49.90760004520416,
+            "max": 47.389199793338776,
+            "count": 230
+        },
+        "SoccerTwos.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 230
+        },
+        "SoccerTwos.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 230
+        },
+        "SoccerTwos.Losses.PolicyLoss.mean": {
+            "value": 0.01872896176064387,
+            "min": 0.012019599394019071,
+            "max": 0.024193876256079723,
+            "count": 111
+        },
+        "SoccerTwos.Losses.PolicyLoss.sum": {
+            "value": 0.01872896176064387,
+            "min": 0.012019599394019071,
+            "max": 0.024193876256079723,
+            "count": 111
+        },
+        "SoccerTwos.Losses.ValueLoss.mean": {
+            "value": 0.09518186748027802,
+            "min": 0.0706393318871657,
+            "max": 0.09518186748027802,
+            "count": 111
+        },
+        "SoccerTwos.Losses.ValueLoss.sum": {
+            "value": 0.09518186748027802,
+            "min": 0.0706393318871657,
+            "max": 0.09518186748027802,
+            "count": 111
+        },
+        "SoccerTwos.Losses.BaselineLoss.mean": {
+            "value": 0.09562629113594691,
+            "min": 0.07152016038695971,
+            "max": 0.09562629113594691,
+            "count": 111
+        },
+        "SoccerTwos.Losses.BaselineLoss.sum": {
+            "value": 0.09562629113594691,
+            "min": 0.07152016038695971,
+            "max": 0.09562629113594691,
+            "count": 111
+        },
+        "SoccerTwos.Policy.LearningRate.mean": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 111
+        },
+        "SoccerTwos.Policy.LearningRate.sum": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 111
+        },
+        "SoccerTwos.Policy.Epsilon.mean": {
+            "value": 0.20000000000000007,
+            "min": 0.20000000000000007,
+            "max": 0.20000000000000007,
+            "count": 111
+        },
+        "SoccerTwos.Policy.Epsilon.sum": {
+            "value": 0.20000000000000007,
+            "min": 0.20000000000000007,
+            "max": 0.20000000000000007,
+            "count": 111
+        },
+        "SoccerTwos.Policy.Beta.mean": {
+            "value": 0.005000000000000001,
+            "min": 0.005000000000000001,
+            "max": 0.005000000000000001,
+            "count": 111
+        },
+        "SoccerTwos.Policy.Beta.sum": {
+            "value": 0.005000000000000001,
+            "min": 0.005000000000000001,
+            "max": 0.005000000000000001,
+            "count": 111
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1747997676",
+        "python_version": "3.10.12 (main, Jul  5 2023, 18:54:27) [GCC 11.2.0]",
+        "command_line_arguments": "/home/misbah/miniconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --resume",
+        "mlagents_version": "1.2.0.dev0",
+        "mlagents_envs_version": "1.2.0.dev0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "2.7.0+cu126",
+        "numpy_version": "1.23.5",
+        "end_time_seconds": "1748003870"
+    },
+    "total": 6193.243015332002,
+    "count": 1,
+    "self": 0.2190838940005051,
+    "children": {
+        "run_training.setup": {
+            "total": 0.008608447009464726,
+            "count": 1,
+            "self": 0.008608447009464726
+        },
+        "TrainerController.start_learning": {
+            "total": 6193.015322990992,
+            "count": 1,
+            "self": 2.8038882425171323,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 1.4619750839920016,
+                    "count": 13,
+                    "self": 1.4619750839920016
+                },
+                "TrainerController.advance": {
+                    "total": 6188.660720257481,
+                    "count": 155986,
+                    "self": 2.6640657623356674,
+                    "children": {
+                        "env_step": {
+                            "total": 1907.5624348415295,
+                            "count": 155986,
+                            "self": 1611.387107489776,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 294.368761390273,
+                                    "count": 155986,
+                                    "self": 14.094670786944334,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 280.27409060332866,
+                                            "count": 288798,
+                                            "self": 280.27409060332866
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 1.8065659614803735,
+                                    "count": 155986,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 6188.076122690254,
+                                            "count": 155986,
+                                            "is_parallel": true,
+                                            "self": 4824.377654081254,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.0013928839907748625,
+                                                            "count": 2,
+                                                            "is_parallel": true,
+                                                            "self": 0.000349724039551802,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.0010431599512230605,
+                                                                    "count": 8,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0010431599512230605
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.014681180997285992,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.00035585599835030735,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.0002818450011545792,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0002818450011545792
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.013071444001980126,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.013071444001980126
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.0009720359958009794,
+                                                                    "count": 2,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0001990060118259862,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.0007730299839749932,
+                                                                            "count": 8,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.0007730299839749932
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "steps_from_proto": {
+                                                    "total": 0.014256768015911803,
+                                                    "count": 24,
+                                                    "is_parallel": true,
+                                                    "self": 0.002820325084030628,
+                                                    "children": {
+                                                        "_process_rank_one_or_two_observation": {
+                                                            "total": 0.011436442931881174,
+                                                            "count": 96,
+                                                            "is_parallel": true,
+                                                            "self": 0.011436442931881174
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 1363.684211840984,
+                                                    "count": 155985,
+                                                    "is_parallel": true,
+                                                    "self": 67.68927301358781,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 75.72199507434561,
+                                                            "count": 155985,
+                                                            "is_parallel": true,
+                                                            "self": 75.72199507434561
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 1002.7482204776024,
+                                                            "count": 155985,
+                                                            "is_parallel": true,
+                                                            "self": 1002.7482204776024
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 217.5247232754482,
+                                                            "count": 311970,
+                                                            "is_parallel": true,
+                                                            "self": 46.355050702157314,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 171.16967257329088,
+                                                                    "count": 1247880,
+                                                                    "is_parallel": true,
+                                                                    "self": 171.16967257329088
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 4278.434219653616,
+                            "count": 155986,
+                            "self": 18.51109605266538,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 281.2572263569018,
+                                    "count": 155986,
+                                    "self": 280.7852156188892,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 0.47201073801261373,
+                                            "count": 5,
+                                            "self": 0.47201073801261373
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 3978.665897244049,
+                                    "count": 111,
+                                    "self": 154.19840713523445,
+                                    "children": {
+                                        "TorchPOCAOptimizer.update": {
+                                            "total": 3824.4674901088147,
+                                            "count": 3330,
+                                            "self": 3824.4674901088147
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 5.970068741589785e-07,
+                    "count": 1,
+                    "self": 5.970068741589785e-07
+                },
+                "TrainerController._save_models": {
+                    "total": 0.08873880999453831,
+                    "count": 1,
+                    "self": 0.0013925339881097898,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.08734627600642852,
+                            "count": 1,
+                            "self": 0.08734627600642852
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,66 @@
+{
+    "SoccerTwos": {
+        "checkpoints": [
+            {
+                "steps": 28499924,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-28499924.onnx",
+                "reward": 0.0,
+                "creation_time": 1747999744.5327501,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-28499924.pt"
+                ]
+            },
+            {
+                "steps": 28999974,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-28999974.onnx",
+                "reward": 0.0,
+                "creation_time": 1748001079.5168242,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-28999974.pt"
+                ]
+            },
+            {
+                "steps": 29499971,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-29499971.onnx",
+                "reward": 0.0,
+                "creation_time": 1748002462.2329793,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-29499971.pt"
+                ]
+            },
+            {
+                "steps": 29999974,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-29999974.onnx",
+                "reward": 0.0,
+                "creation_time": 1748003869.6849742,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-29999974.pt"
+                ]
+            },
+            {
+                "steps": 30000018,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-30000018.onnx",
+                "reward": 0.0,
+                "creation_time": 1748003869.7789714,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-30000018.pt"
+                ]
+            }
+        ],
+        "elo": 1711.6315221749464,
+        "final_checkpoint": {
+            "steps": 30000018,
+            "file_path": "results/SoccerTwos/SoccerTwos.onnx",
+            "reward": 0.0,
+            "creation_time": 1748003869.7789714,
+            "auxillary_file_paths": [
+                "results/SoccerTwos/SoccerTwos/SoccerTwos-30000018.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "1.2.0.dev0",
+        "torch_version": "2.7.0+cu126"
+    }
+}