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: alexsung/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:d9ab5b8318321a54504cbe6810afba53611ec04ee810f1a6c0fb2ecb87fea172
+size 1768747

SoccerTwos/SoccerTwos-31999932.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1299d6c64d6b08620d3f02e45c25210ac2c50a2bf13040d81c8151aa13eed8db
+size 1768747

SoccerTwos/SoccerTwos-31999932.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28c023f6582828e17abe55a075af4ab31289c08779cb8aadc57f19a8b0c19857
+size 28432146

SoccerTwos/SoccerTwos-32499972.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e337409ad76ec02f83986f50b96fd2806a0bed2b958edbd7b5b1972ae355b2a2
+size 1768747

SoccerTwos/SoccerTwos-32499972.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99764173619ca7061faacaa4daf3b4f70b8705a68977ae547de8bb18a742fa1b
+size 28432146

SoccerTwos/SoccerTwos-32999952.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c26b1987002331a2e370fe43886db17e428a03547494636b9cd9050435728deb
+size 1768747

SoccerTwos/SoccerTwos-32999952.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6480a024a2e67eeb845537208b308c61da59f2f742974a97db9a74b541c1154
+size 28432146

SoccerTwos/SoccerTwos-33499915.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4725bccf984f4c9f476d2b433482b9bb104a88e112ea3eec69052554743551b3
+size 1768747

SoccerTwos/SoccerTwos-33499915.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2bfd174e945c485d68b6f614d064e03760c332957522c570625ad9ff9a1d6901
+size 28432146

SoccerTwos/SoccerTwos-33999986.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f27d1e5a6cc9726f5cad5d92160133aa3306c2267b486e4dcecf2446eebc89f
+size 1768747

SoccerTwos/SoccerTwos-33999986.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2bb6a389b6c4527724c7bd7bcec69cd7c509433d38f6f8755e39108d9e0e3f7f
+size 28432146

SoccerTwos/SoccerTwos-43876.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9ab5b8318321a54504cbe6810afba53611ec04ee810f1a6c0fb2ecb87fea172
+size 1768747

SoccerTwos/SoccerTwos-43876.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:490ea29349acc6105e769dd3f144eb0afd3ea6987e956b66631c05e2d59de90e
+size 28431774

SoccerTwos/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b302e7d0929db5a4a69ed2d09c9f25064caad2253d0481fdc12476589639de3
+size 28431030

SoccerTwos/events.out.tfevents.1739482165.sdiaadmin-ThinkStation-P920.65938.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b22d7c1d9aebf81ff0955e68931010043c001db415d33defb15e473f8655916
+size 35079802

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": 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.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": 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: 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.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: false
+  force: false
+  train_model: false
+  inference: false
+  results_dir: results
+torch_settings:
+  device: null
+debug: false

run_logs/Player-0.log

@@ -0,0 +1,585 @@
+Mono path[0] = '/home/sdiaadmin/workshop/alex/hf_rl/ml-agents/training-envs-executables/SoccerTwos_Data/Managed'
+Mono config path = '/home/sdiaadmin/workshop/alex/hf_rl/ml-agents/training-envs-executables/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/sdiaadmin/workshop/alex/hf_rl/ml-agents/training-envs-executables/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  0.076 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: 0.897104 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
+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
+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
+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
+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
+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
+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
+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
+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
+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
+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
+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
+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
+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
+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
+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
+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
+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
+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
+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
+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
+TOO LONG
+TOO LONG
+TOO LONG

run_logs/timers.json

@@ -0,0 +1,403 @@
+{
+    "name": "root",
+    "gauges": {
+        "SoccerTwos.Policy.Entropy.mean": {
+            "value": 3.288881301879883,
+            "min": 3.282517910003662,
+            "max": 3.295713424682617,
+            "count": 4
+        },
+        "SoccerTwos.Policy.Entropy.sum": {
+            "value": 65251.40625,
+            "min": 45692.6484375,
+            "max": 105462.765625,
+            "count": 4
+        },
+        "SoccerTwos.Environment.EpisodeLength.mean": {
+            "value": 864.0,
+            "min": 738.7777777777778,
+            "max": 886.0,
+            "count": 4
+        },
+        "SoccerTwos.Environment.EpisodeLength.sum": {
+            "value": 24192.0,
+            "min": 15592.0,
+            "max": 26596.0,
+            "count": 4
+        },
+        "SoccerTwos.Self-play.ELO.mean": {
+            "value": 1198.025705444381,
+            "min": 1198.025705444381,
+            "max": 1198.6368125508247,
+            "count": 4
+        },
+        "SoccerTwos.Self-play.ELO.sum": {
+            "value": 2396.051410888762,
+            "min": 2396.051410888762,
+            "max": 9589.094500406598,
+            "count": 4
+        },
+        "SoccerTwos.Step.mean": {
+            "value": 39876.0,
+            "min": 9316.0,
+            "max": 39876.0,
+            "count": 4
+        },
+        "SoccerTwos.Step.sum": {
+            "value": 39876.0,
+            "min": 9316.0,
+            "max": 39876.0,
+            "count": 4
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
+            "value": -0.036910559982061386,
+            "min": -0.04539959505200386,
+            "max": -0.036910559982061386,
+            "count": 4
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
+            "value": -0.4429267346858978,
+            "min": -0.6355534195899963,
+            "max": -0.4429267346858978,
+            "count": 4
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
+            "value": -0.04023938998579979,
+            "min": -0.04540951922535896,
+            "max": -0.04023938998579979,
+            "count": 4
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
+            "value": -0.4828726649284363,
+            "min": -0.6356660723686218,
+            "max": -0.4828726649284363,
+            "count": 4
+        },
+        "SoccerTwos.Environment.CumulativeReward.mean": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 4
+        },
+        "SoccerTwos.Environment.CumulativeReward.sum": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 4
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.mean": {
+            "value": 0.1574666698773702,
+            "min": -0.3723999985626766,
+            "max": 0.1574666698773702,
+            "count": 4
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.sum": {
+            "value": 1.8896000385284424,
+            "min": -5.213599979877472,
+            "max": 1.8896000385284424,
+            "count": 4
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.mean": {
+            "value": 0.1574666698773702,
+            "min": -0.3723999985626766,
+            "max": 0.1574666698773702,
+            "count": 4
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.sum": {
+            "value": 1.8896000385284424,
+            "min": -5.213599979877472,
+            "max": 1.8896000385284424,
+            "count": 4
+        },
+        "SoccerTwos.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 4
+        },
+        "SoccerTwos.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 4
+        },
+        "SoccerTwos.Losses.PolicyLoss.mean": {
+            "value": 0.017958800479148825,
+            "min": 0.017958800479148825,
+            "max": 0.017958800479148825,
+            "count": 1
+        },
+        "SoccerTwos.Losses.PolicyLoss.sum": {
+            "value": 0.017958800479148825,
+            "min": 0.017958800479148825,
+            "max": 0.017958800479148825,
+            "count": 1
+        },
+        "SoccerTwos.Losses.ValueLoss.mean": {
+            "value": 0.00371873223533233,
+            "min": 0.00371873223533233,
+            "max": 0.00371873223533233,
+            "count": 1
+        },
+        "SoccerTwos.Losses.ValueLoss.sum": {
+            "value": 0.00371873223533233,
+            "min": 0.00371873223533233,
+            "max": 0.00371873223533233,
+            "count": 1
+        },
+        "SoccerTwos.Losses.BaselineLoss.mean": {
+            "value": 0.003505130197542409,
+            "min": 0.003505130197542409,
+            "max": 0.003505130197542409,
+            "count": 1
+        },
+        "SoccerTwos.Losses.BaselineLoss.sum": {
+            "value": 0.003505130197542409,
+            "min": 0.003505130197542409,
+            "max": 0.003505130197542409,
+            "count": 1
+        },
+        "SoccerTwos.Policy.LearningRate.mean": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 1
+        },
+        "SoccerTwos.Policy.LearningRate.sum": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 1
+        },
+        "SoccerTwos.Policy.Epsilon.mean": {
+            "value": 0.20000000000000007,
+            "min": 0.20000000000000007,
+            "max": 0.20000000000000007,
+            "count": 1
+        },
+        "SoccerTwos.Policy.Epsilon.sum": {
+            "value": 0.20000000000000007,
+            "min": 0.20000000000000007,
+            "max": 0.20000000000000007,
+            "count": 1
+        },
+        "SoccerTwos.Policy.Beta.mean": {
+            "value": 0.005000000000000001,
+            "min": 0.005000000000000001,
+            "max": 0.005000000000000001,
+            "count": 1
+        },
+        "SoccerTwos.Policy.Beta.sum": {
+            "value": 0.005000000000000001,
+            "min": 0.005000000000000001,
+            "max": 0.005000000000000001,
+            "count": 1
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1739481968",
+        "python_version": "3.10.12 (main, Feb 13 2025, 10:55:24) [GCC 13.3.0]",
+        "command_line_arguments": "/home/sdiaadmin/workshop/alex/hf_rl/ml-agents-env/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.x86_64 --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+cu124",
+        "numpy_version": "1.23.5",
+        "end_time_seconds": "1739482046"
+    },
+    "total": 78.78807352704462,
+    "count": 1,
+    "self": 0.1325466490816325,
+    "children": {
+        "run_training.setup": {
+            "total": 0.02017277997219935,
+            "count": 1,
+            "self": 0.02017277997219935
+        },
+        "TrainerController.start_learning": {
+            "total": 78.63535409799078,
+            "count": 1,
+            "self": 0.05489160702563822,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 2.275416558026336,
+                    "count": 1,
+                    "self": 2.275416558026336
+                },
+                "TrainerController.advance": {
+                    "total": 76.12623380793957,
+                    "count": 3013,
+                    "self": 0.04798580065835267,
+                    "children": {
+                        "env_step": {
+                            "total": 64.4578452668502,
+                            "count": 3013,
+                            "self": 49.03936653031269,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 15.39188690361334,
+                                    "count": 3013,
+                                    "self": 0.3131978992023505,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 15.07868900441099,
+                                            "count": 6000,
+                                            "self": 15.07868900441099
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 0.026591832924168557,
+                                    "count": 3013,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 74.66723270865623,
+                                            "count": 3013,
+                                            "is_parallel": true,
+                                            "self": 33.73665810591774,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.006514078995678574,
+                                                            "count": 2,
+                                                            "is_parallel": true,
+                                                            "self": 0.0014143039006739855,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.005099775095004588,
+                                                                    "count": 8,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.005099775095004588
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.030795760976616293,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0008101999992504716,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.00127127900486812,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00127127900486812
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.026238952996209264,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.026238952996209264
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.002475328976288438,
+                                                                    "count": 2,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0004469578852877021,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.0020283710910007358,
+                                                                            "count": 8,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.0020283710910007358
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 40.93057460273849,
+                                                    "count": 3012,
+                                                    "is_parallel": true,
+                                                    "self": 1.482369762728922,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 0.9531680770451203,
+                                                            "count": 3012,
+                                                            "is_parallel": true,
+                                                            "self": 0.9531680770451203
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 33.82491795549868,
+                                                            "count": 3012,
+                                                            "is_parallel": true,
+                                                            "self": 33.82491795549868
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 4.670118807465769,
+                                                            "count": 6024,
+                                                            "is_parallel": true,
+                                                            "self": 0.8190037218737416,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 3.8511150855920278,
+                                                                    "count": 24096,
+                                                                    "is_parallel": true,
+                                                                    "self": 3.8511150855920278
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 11.620402740431018,
+                            "count": 3013,
+                            "self": 0.36845785117475316,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 3.6779552212683484,
+                                    "count": 3013,
+                                    "self": 3.6779552212683484
+                                },
+                                "_update_policy": {
+                                    "total": 7.573989667987917,
+                                    "count": 2,
+                                    "self": 5.098582395003177,
+                                    "children": {
+                                        "TorchPOCAOptimizer.update": {
+                                            "total": 2.4754072729847394,
+                                            "count": 52,
+                                            "self": 2.4754072729847394
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 1.033011358231306e-06,
+                    "count": 1,
+                    "self": 1.033011358231306e-06
+                },
+                "TrainerController._save_models": {
+                    "total": 0.1788110919878818,
+                    "count": 1,
+                    "self": 0.0011170660145580769,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.17769402597332373,
+                            "count": 1,
+                            "self": 0.17769402597332373
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,30 @@
+{
+    "SoccerTwos": {
+        "elo": 1198.025705444381,
+        "checkpoints": [
+            {
+                "steps": 43876,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-43876.onnx",
+                "reward": null,
+                "creation_time": 1739482046.8590965,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-43876.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 43876,
+            "file_path": "results/SoccerTwos/SoccerTwos.onnx",
+            "reward": null,
+            "creation_time": 1739482046.8590965,
+            "auxillary_file_paths": [
+                "results/SoccerTwos/SoccerTwos/SoccerTwos-43876.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "1.2.0.dev0",
+        "torch_version": "2.6.0+cu124"
+    }
+}