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: vper19/poca-SoccerTwos-fc
+  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 sha256:6eb19ded4dfa06c7323c3c163c1c506769b4e58a5987449eb0b5fb8a1eea3cde
+size 1768747

SoccerTwos/SoccerTwos-48499902.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81590162ebf6cf4f95cc2efe3dc39b6786831db9eb33ed09d0fca2da1188923d
+size 1768747

SoccerTwos/SoccerTwos-48499902.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62aad19e78e2ba11946e1ff41c23246b5bd01b8e204f00309e8c5cb15a2872c6
+size 28430482

SoccerTwos/SoccerTwos-48999999.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b433d60124fee5ddda1383575f1665e5d6700d671422b260d843f91982ed1566
+size 1768747

SoccerTwos/SoccerTwos-48999999.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3361542662e03f1b9c831e44e293895e14315bbcb8bb295ac1029bddc0ed940d
+size 28430482

SoccerTwos/SoccerTwos-49499907.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49045a71649bf131c2d45942c8438798344d33de4bca7c9434b1b12114c48c31
+size 1768747

SoccerTwos/SoccerTwos-49499907.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:237f32b5f9a576c5914bb55db667db5d076cc498c39ddcac0c1e6bffcc1d8bc3
+size 28430482

SoccerTwos/SoccerTwos-49999972.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6eb19ded4dfa06c7323c3c163c1c506769b4e58a5987449eb0b5fb8a1eea3cde
+size 1768747

SoccerTwos/SoccerTwos-49999972.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:652020cc5ded7bb10bb514a6ea5519f4ef247411298771a9fe136132f60a4277
+size 28430482

SoccerTwos/SoccerTwos-50000154.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6eb19ded4dfa06c7323c3c163c1c506769b4e58a5987449eb0b5fb8a1eea3cde
+size 1768747

SoccerTwos/SoccerTwos-50000154.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a95620364ec848c67688e5a86a0efd13114bd2025752eed97ad7e68c4cc20bc
+size 28430482

SoccerTwos/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f44cbe81b4f8e52c52f3168aa9af083ed92f0e82294717b5dd3d759377d69024
+size 28429366

SoccerTwos/events.out.tfevents.1726751007.it-fvalenti.2630493.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34d689e65265795cabf2bfeb46c4f1167121762c3d15d08b196dd7bebab46dc6
+size 2415897

SoccerTwos/events.out.tfevents.1726759061.it-fvalenti.2691965.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54c218f082e1efe638b4261b7dea9419c245ba4ddeca9614a6107fc3b2790e83
+size 47773105

config.json

@@ -0,0 +1 @@
+{"default_settings": null, "behaviors": {"SoccerTwos": {"trainer_type": "poca", "hyperparameters": {"batch_size": 512, "buffer_size": 20480, "learning_rate": 0.0001, "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": "fully_connected", "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": 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-fc", "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: 512
+      buffer_size: 20480
+      learning_rate: 0.0001
+      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: fully_connected
+      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: 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-fc
+  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] = '/localhome/workspace/rl/ml-agents/training-envs-executables/SoccerTwos/SoccerTwos_Data/Managed'
+Mono config path = '/localhome/workspace/rl/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 /localhome/workspace/rl/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  0.063 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: 0.544715 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]: 874693 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 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 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 0.7 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]: 874694 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 4.7 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 874694 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 17.6 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]: 874693 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]: 874694 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]: 874694 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]: 874693 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]: 874694 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]: 874693 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": 1.4176841974258423,
+            "min": 1.273084044456482,
+            "max": 3.0033085346221924,
+            "count": 4648
+        },
+        "SoccerTwos.Policy.Entropy.sum": {
+            "value": 29170.26953125,
+            "min": 23458.6953125,
+            "max": 70673.4375,
+            "count": 4648
+        },
+        "SoccerTwos.Environment.EpisodeLength.mean": {
+            "value": 62.30379746835443,
+            "min": 37.55384615384615,
+            "max": 207.04166666666666,
+            "count": 4648
+        },
+        "SoccerTwos.Environment.EpisodeLength.sum": {
+            "value": 19688.0,
+            "min": 11432.0,
+            "max": 21432.0,
+            "count": 4648
+        },
+        "SoccerTwos.Self-play.ELO.mean": {
+            "value": 1727.9182339130577,
+            "min": 1279.6902445960654,
+            "max": 1748.2929531118036,
+            "count": 4648
+        },
+        "SoccerTwos.Self-play.ELO.sum": {
+            "value": 273011.08095826313,
+            "min": 61425.13174061114,
+            "max": 425453.41743892746,
+            "count": 4648
+        },
+        "SoccerTwos.Step.mean": {
+            "value": 49999972.0,
+            "min": 3529997.0,
+            "max": 49999972.0,
+            "count": 4648
+        },
+        "SoccerTwos.Step.sum": {
+            "value": 49999972.0,
+            "min": 3529997.0,
+            "max": 49999972.0,
+            "count": 4648
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
+            "value": 0.022920917719602585,
+            "min": -0.13662751019001007,
+            "max": 0.19496217370033264,
+            "count": 4648
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
+            "value": 3.644425868988037,
+            "min": -24.729578018188477,
+            "max": 28.065378189086914,
+            "count": 4648
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 0.021441897377371788,
+            "min": -0.1416383534669876,
+            "max": 0.19621549546718597,
+            "count": 4648
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 3.409261703491211,
+            "min": -25.3532657623291,
+            "max": 26.90790557861328,
+            "count": 4648
+        },
+        "SoccerTwos.Environment.CumulativeReward.mean": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 4648
+        },
+        "SoccerTwos.Environment.CumulativeReward.sum": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 4648
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.mean": {
+            "value": 0.11938113011654068,
+            "min": -0.45033871070031195,
+            "max": 0.30970240116119385,
+            "count": 4648
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.sum": {
+            "value": 18.98159968852997,
+            "min": -66.90920007228851,
+            "max": 55.97319972515106,
+            "count": 4648
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.mean": {
+            "value": 0.11938113011654068,
+            "min": -0.45033871070031195,
+            "max": 0.30970240116119385,
+            "count": 4648
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.sum": {
+            "value": 18.98159968852997,
+            "min": -66.90920007228851,
+            "max": 55.97319972515106,
+            "count": 4648
+        },
+        "SoccerTwos.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 4648
+        },
+        "SoccerTwos.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 4648
+        },
+        "SoccerTwos.Losses.PolicyLoss.mean": {
+            "value": 0.03528763847522593,
+            "min": 0.027559679628029698,
+            "max": 0.042686061360291204,
+            "count": 2256
+        },
+        "SoccerTwos.Losses.PolicyLoss.sum": {
+            "value": 0.03528763847522593,
+            "min": 0.027559679628029698,
+            "max": 0.042686061360291204,
+            "count": 2256
+        },
+        "SoccerTwos.Losses.ValueLoss.mean": {
+            "value": 0.10108638548602661,
+            "min": 0.030191989497296394,
+            "max": 0.12119636293500662,
+            "count": 2256
+        },
+        "SoccerTwos.Losses.ValueLoss.sum": {
+            "value": 0.10108638548602661,
+            "min": 0.030191989497296394,
+            "max": 0.12119636293500662,
+            "count": 2256
+        },
+        "SoccerTwos.Losses.BaselineLoss.mean": {
+            "value": 0.1050215252985557,
+            "min": 0.03154606261246261,
+            "max": 0.1291879069680969,
+            "count": 2256
+        },
+        "SoccerTwos.Losses.BaselineLoss.sum": {
+            "value": 0.1050215252985557,
+            "min": 0.03154606261246261,
+            "max": 0.1291879069680969,
+            "count": 2256
+        },
+        "SoccerTwos.Policy.LearningRate.mean": {
+            "value": 0.00010000000000000003,
+            "min": 0.0001,
+            "max": 0.00010000000000000003,
+            "count": 2256
+        },
+        "SoccerTwos.Policy.LearningRate.sum": {
+            "value": 0.00010000000000000003,
+            "min": 0.0001,
+            "max": 0.00010000000000000003,
+            "count": 2256
+        },
+        "SoccerTwos.Policy.Epsilon.mean": {
+            "value": 0.20000000000000004,
+            "min": 0.19999999999999998,
+            "max": 0.20000000000000004,
+            "count": 2256
+        },
+        "SoccerTwos.Policy.Epsilon.sum": {
+            "value": 0.20000000000000004,
+            "min": 0.19999999999999998,
+            "max": 0.20000000000000004,
+            "count": 2256
+        },
+        "SoccerTwos.Policy.Beta.mean": {
+            "value": 0.005,
+            "min": 0.005,
+            "max": 0.005,
+            "count": 2256
+        },
+        "SoccerTwos.Policy.Beta.sum": {
+            "value": 0.005,
+            "min": 0.005,
+            "max": 0.005,
+            "count": 2256
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1726759060",
+        "python_version": "3.10.12 (main, Jul  5 2023, 18:54:27) [GCC 11.2.0]",
+        "command_line_arguments": "/home/fvalenti/anaconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos-fc --no-graphics --resume",
+        "mlagents_version": "1.1.0.dev0",
+        "mlagents_envs_version": "1.1.0.dev0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "2.4.1+cu121",
+        "numpy_version": "1.23.5",
+        "end_time_seconds": "1726868930"
+    },
+    "total": 109870.16877528792,
+    "count": 1,
+    "self": 0.26952816790435463,
+    "children": {
+        "run_training.setup": {
+            "total": 0.025311877019703388,
+            "count": 1,
+            "self": 0.025311877019703388
+        },
+        "TrainerController.start_learning": {
+            "total": 109869.873935243,
+            "count": 1,
+            "self": 82.71270903828554,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 5.453312724130228,
+                    "count": 234,
+                    "self": 5.453312724130228
+                },
+                "TrainerController.advance": {
+                    "total": 109781.48228730948,
+                    "count": 3227280,
+                    "self": 76.4611947935773,
+                    "children": {
+                        "env_step": {
+                            "total": 52413.048648017575,
+                            "count": 3227280,
+                            "self": 40539.32292631583,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 11827.081504302332,
+                                    "count": 3227280,
+                                    "self": 406.8896792076994,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 11420.191825094633,
+                                            "count": 5831368,
+                                            "self": 11420.191825094633
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 46.64421739941463,
+                                    "count": 3227280,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 109735.25532350445,
+                                            "count": 3227280,
+                                            "is_parallel": true,
+                                            "self": 77135.77599537594,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.0023697508731856942,
+                                                            "count": 2,
+                                                            "is_parallel": true,
+                                                            "self": 0.0005974527448415756,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.0017722981283441186,
+                                                                    "count": 8,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0017722981283441186
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.0210760619957,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.00046329316683113575,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.00042729894630610943,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00042729894630610943
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.01857467892114073,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.01857467892114073
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.0016107909614220262,
+                                                                    "count": 2,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00037376873660832644,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.0012370222248136997,
+                                                                            "count": 8,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.0012370222248136997
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "steps_from_proto": {
+                                                    "total": 0.37478213489521295,
+                                                    "count": 466,
+                                                    "is_parallel": true,
+                                                    "self": 0.0801759057212621,
+                                                    "children": {
+                                                        "_process_rank_one_or_two_observation": {
+                                                            "total": 0.29460622917395085,
+                                                            "count": 1864,
+                                                            "is_parallel": true,
+                                                            "self": 0.29460622917395085
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 32599.104545993614,
+                                                    "count": 3227279,
+                                                    "is_parallel": true,
+                                                    "self": 1719.157550459844,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 1323.4723716625012,
+                                                            "count": 3227279,
+                                                            "is_parallel": true,
+                                                            "self": 1323.4723716625012
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 24196.812616513926,
+                                                            "count": 3227279,
+                                                            "is_parallel": true,
+                                                            "self": 24196.812616513926
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 5359.662007357343,
+                                                            "count": 6454558,
+                                                            "is_parallel": true,
+                                                            "self": 1150.1679583099904,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 4209.494049047353,
+                                                                    "count": 25818232,
+                                                                    "is_parallel": true,
+                                                                    "self": 4209.494049047353
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 57291.97244449833,
+                            "count": 3227280,
+                            "self": 588.5272417638917,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 12285.097310439683,
+                                    "count": 3227280,
+                                    "self": 12263.48916405777,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 21.608146381913684,
+                                            "count": 93,
+                                            "self": 21.608146381913684
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 44418.347892294754,
+                                    "count": 2256,
+                                    "self": 5420.595356966602,
+                                    "children": {
+                                        "TorchPOCAOptimizer.update": {
+                                            "total": 38997.75253532815,
+                                            "count": 270831,
+                                            "self": 38997.75253532815
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 7.180497050285339e-07,
+                    "count": 1,
+                    "self": 7.180497050285339e-07
+                },
+                "TrainerController._save_models": {
+                    "total": 0.22562545305117965,
+                    "count": 1,
+                    "self": 0.0016998150385916233,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.22392563801258802,
+                            "count": 1,
+                            "self": 0.22392563801258802
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,66 @@
+{
+    "SoccerTwos": {
+        "checkpoints": [
+            {
+                "steps": 48499902,
+                "file_path": "results/SoccerTwos-fc/SoccerTwos/SoccerTwos-48499902.onnx",
+                "reward": 0.0,
+                "creation_time": 1726865483.568378,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos-fc/SoccerTwos/SoccerTwos-48499902.pt"
+                ]
+            },
+            {
+                "steps": 48999999,
+                "file_path": "results/SoccerTwos-fc/SoccerTwos/SoccerTwos-48999999.onnx",
+                "reward": 0.0,
+                "creation_time": 1726866624.4572606,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos-fc/SoccerTwos/SoccerTwos-48999999.pt"
+                ]
+            },
+            {
+                "steps": 49499907,
+                "file_path": "results/SoccerTwos-fc/SoccerTwos/SoccerTwos-49499907.onnx",
+                "reward": 0.0,
+                "creation_time": 1726867771.5815158,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos-fc/SoccerTwos/SoccerTwos-49499907.pt"
+                ]
+            },
+            {
+                "steps": 49999972,
+                "file_path": "results/SoccerTwos-fc/SoccerTwos/SoccerTwos-49999972.onnx",
+                "reward": 0.0,
+                "creation_time": 1726868930.384542,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos-fc/SoccerTwos/SoccerTwos-49999972.pt"
+                ]
+            },
+            {
+                "steps": 50000154,
+                "file_path": "results/SoccerTwos-fc/SoccerTwos/SoccerTwos-50000154.onnx",
+                "reward": 0.0,
+                "creation_time": 1726868930.63655,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos-fc/SoccerTwos/SoccerTwos-50000154.pt"
+                ]
+            }
+        ],
+        "elo": 1730.5408199127883,
+        "final_checkpoint": {
+            "steps": 50000154,
+            "file_path": "results/SoccerTwos-fc/SoccerTwos.onnx",
+            "reward": 0.0,
+            "creation_time": 1726868930.63655,
+            "auxillary_file_paths": [
+                "results/SoccerTwos-fc/SoccerTwos/SoccerTwos-50000154.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "1.1.0.dev0",
+        "torch_version": "2.4.1+cu121"
+    }
+}