Second 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: averydd/poca-SoccerTwos1
+  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 sha256:1d0b38e62d77054206b63f301eedb066f8c91e6f5d236a7d851c6f70065484c2
+size 1768747

SoccerTwos/SoccerTwos-1999868.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e59551ac6a4396c51460cf0d9baecf913b295b478d44ae0b2813ea87eaef714
+size 5625134

SoccerTwos/SoccerTwos-1999868.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fef8e85b5610b4b372d9a60ddb085e38b91ca8f9dd4b824d94788f651b182033
+size 100861974

SoccerTwos/SoccerTwos-2499993.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fb4a7a5c96df7f5ef0416b468cdf600193344253a5caf49b3eb99c72db22189
+size 5625134

SoccerTwos/SoccerTwos-2499993.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7263a4bdd3a3efe211349f6261fac8b2ef736b7d7b8892dcf684e695ef3f833d
+size 100861974

SoccerTwos/SoccerTwos-270278.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d0b38e62d77054206b63f301eedb066f8c91e6f5d236a7d851c6f70065484c2
+size 1768747

SoccerTwos/SoccerTwos-270278.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d387a05610d0420ba9f92810c38e2a2da36297387a2b711843e1648de955cd38
+size 28430234

SoccerTwos/SoccerTwos-2999986.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf146ac69e4a48554797f5c80916e01d92dbf9dd98a8082cbf10922ff958a5b9
+size 5625134

SoccerTwos/SoccerTwos-2999986.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:248ee1f1aeda3aff383ad1ee21c07864434a99d1910e9c77ff7021a811db7fc1
+size 100861974

SoccerTwos/SoccerTwos-3499960.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5721a391c192c575dcac8794eeefb9963588f787bff5e0497017cac6c634a3d
+size 5625134

SoccerTwos/SoccerTwos-3499960.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:989bf2fcf9f8b0c23bf6c71306f9f2cb2b403204e155194a9061cafee3e0600c
+size 100861974

SoccerTwos/SoccerTwos-3999931.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36cd20f1f473593f6cbe3e98f9d694f9fdc869b9a8e0ba7ee6defe1aa8267fb9
+size 5625134

SoccerTwos/SoccerTwos-3999931.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98f82c013082e3a808919dcd3d3a28fedb381b16ed81764fa36a553182ba1779
+size 100861974

SoccerTwos/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd8e736f85f1f2866584ba212fec8cac909ed0e1af955c62eb12407b9b233b98
+size 100860982

SoccerTwos/events.out.tfevents.1731317959.192.168.91.100.non-exists.ptr.local.13539.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:881c2548fb272b6f1825c7a90509d9cf2bc3efbe3ba90bd12603ea72b52cc843
+size 4183075

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/SoccerTwos.app", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SoccerTwos", "initialize_from": null, "load_model": false, "resume": false, "force": true, "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/SoccerTwos.app
+  env_args: null
+  base_port: 5005
+  num_envs: 1
+  num_areas: 1
+  timeout_wait: 60
+  seed: -1
+  max_lifetime_restarts: 10
+  restarts_rate_limit_n: 1
+  restarts_rate_limit_period_s: 60
+engine_settings:
+  width: 84
+  height: 84
+  quality_level: 5
+  time_scale: 20
+  target_frame_rate: -1
+  capture_frame_rate: 60
+  no_graphics: true
+  no_graphics_monitor: false
+environment_parameters: null
+checkpoint_settings:
+  run_id: SoccerTwos
+  initialize_from: null
+  load_model: false
+  resume: false
+  force: true
+  train_model: false
+  inference: false
+  results_dir: results
+torch_settings:
+  device: null
+debug: false

run_logs/Player-0.log

@@ -0,0 +1,483 @@
+Mono path[0] = '/Users/xuanmai/Ai-vs-Ai/ml-agents/training-envs-executables/SoccerTwos/SoccerTwos.app/Contents/Resources/Data/Managed'
+Mono config path = '/Users/xuanmai/Ai-vs-Ai/ml-agents/training-envs-executables/SoccerTwos/SoccerTwos.app/Contents/MonoBleedingEdge/etc'
+New input system (experimental) initialized
+Initialize engine version: 2021.3.17f1 (3e8111cac19d)
+[Subsystems] Discovering subsystems at path /Users/xuanmai/Ai-vs-Ai/ml-agents/training-envs-executables/SoccerTwos/SoccerTwos.app/Contents/Resources/Data/UnitySubsystems
+Forcing GfxDevice: Null
+GfxDevice: creating device client; threaded=0; jobified=0
+NullGfxDevice:
+    Version:  NULL 1.0 [1.0]
+    Renderer: Null Device
+    Vendor:   Unity Technologies
+Begin MonoManager ReloadAssembly
+- Completed reload, in  0.101 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: 1.262875 ms
+Registered Communicator in Agent.
+ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+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 +1,361 @@
+{
+    "name": "root",
+    "gauges": {
+        "SoccerTwos.Policy.Entropy.mean": {
+            "value": 3.240445375442505,
+            "min": 3.2071869373321533,
+            "max": 3.2956974506378174,
+            "count": 27
+        },
+        "SoccerTwos.Policy.Entropy.sum": {
+            "value": 45003.3046875,
+            "min": 22694.2578125,
+            "max": 105462.3125,
+            "count": 27
+        },
+        "SoccerTwos.Environment.EpisodeLength.mean": {
+            "value": 726.5,
+            "min": 525.875,
+            "max": 999.0,
+            "count": 27
+        },
+        "SoccerTwos.Environment.EpisodeLength.sum": {
+            "value": 17436.0,
+            "min": 16828.0,
+            "max": 24800.0,
+            "count": 27
+        },
+        "SoccerTwos.Self-play.ELO.mean": {
+            "value": 1193.7578446427165,
+            "min": 1191.414963979109,
+            "max": 1197.5518243297993,
+            "count": 26
+        },
+        "SoccerTwos.Self-play.ELO.sum": {
+            "value": 4775.031378570866,
+            "min": 2384.2387313629906,
+            "max": 19143.40770044412,
+            "count": 26
+        },
+        "SoccerTwos.Step.mean": {
+            "value": 269976.0,
+            "min": 9420.0,
+            "max": 269976.0,
+            "count": 27
+        },
+        "SoccerTwos.Step.sum": {
+            "value": 269976.0,
+            "min": 9420.0,
+            "max": 269976.0,
+            "count": 27
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
+            "value": -0.014902826398611069,
+            "min": -0.02239292860031128,
+            "max": 0.0017403720412403345,
+            "count": 27
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
+            "value": -0.1937367469072342,
+            "min": -0.35947346687316895,
+            "max": 0.029586324468255043,
+            "count": 27
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
+            "value": -0.011990911327302456,
+            "min": -0.014891309663653374,
+            "max": -0.002565356669947505,
+            "count": 27
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
+            "value": -0.1558818519115448,
+            "min": -0.23826095461845398,
+            "max": -0.0343497060239315,
+            "count": 27
+        },
+        "SoccerTwos.Environment.CumulativeReward.mean": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 27
+        },
+        "SoccerTwos.Environment.CumulativeReward.sum": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 27
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.mean": {
+            "value": 0.042861534998967096,
+            "min": -0.6866823504952824,
+            "max": 0.08849411852219526,
+            "count": 27
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.sum": {
+            "value": 0.5571999549865723,
+            "min": -11.6735999584198,
+            "max": 1.5044000148773193,
+            "count": 27
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.mean": {
+            "value": 0.042861534998967096,
+            "min": -0.6866823504952824,
+            "max": 0.08849411852219526,
+            "count": 27
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.sum": {
+            "value": 0.5571999549865723,
+            "min": -11.6735999584198,
+            "max": 1.5044000148773193,
+            "count": 27
+        },
+        "SoccerTwos.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 27
+        },
+        "SoccerTwos.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 27
+        },
+        "SoccerTwos.Losses.PolicyLoss.mean": {
+            "value": 0.010117768005390342,
+            "min": 0.010117768005390342,
+            "max": 0.01865373881882988,
+            "count": 12
+        },
+        "SoccerTwos.Losses.PolicyLoss.sum": {
+            "value": 0.010117768005390342,
+            "min": 0.010117768005390342,
+            "max": 0.01865373881882988,
+            "count": 12
+        },
+        "SoccerTwos.Losses.ValueLoss.mean": {
+            "value": 0.003935955084549884,
+            "min": 0.001508021573924149,
+            "max": 0.007247587277864416,
+            "count": 12
+        },
+        "SoccerTwos.Losses.ValueLoss.sum": {
+            "value": 0.003935955084549884,
+            "min": 0.001508021573924149,
+            "max": 0.007247587277864416,
+            "count": 12
+        },
+        "SoccerTwos.Losses.BaselineLoss.mean": {
+            "value": 0.003937759677258631,
+            "min": 0.0015174899871150652,
+            "max": 0.007255641728018721,
+            "count": 12
+        },
+        "SoccerTwos.Losses.BaselineLoss.sum": {
+            "value": 0.003937759677258631,
+            "min": 0.0015174899871150652,
+            "max": 0.007255641728018721,
+            "count": 12
+        },
+        "SoccerTwos.Policy.LearningRate.mean": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 12
+        },
+        "SoccerTwos.Policy.LearningRate.sum": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 12
+        },
+        "SoccerTwos.Policy.Epsilon.mean": {
+            "value": 0.20000000000000007,
+            "min": 0.20000000000000007,
+            "max": 0.20000000000000007,
+            "count": 12
+        },
+        "SoccerTwos.Policy.Epsilon.sum": {
+            "value": 0.20000000000000007,
+            "min": 0.20000000000000007,
+            "max": 0.20000000000000007,
+            "count": 12
+        },
+        "SoccerTwos.Policy.Beta.mean": {
+            "value": 0.005000000000000001,
+            "min": 0.005000000000000001,
+            "max": 0.005000000000000001,
+            "count": 12
+        },
+        "SoccerTwos.Policy.Beta.sum": {
+            "value": 0.005000000000000001,
+            "min": 0.005000000000000001,
+            "max": 0.005000000000000001,
+            "count": 12
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1731312250",
+        "python_version": "3.10.12 (main, Jul  5 2023, 15:02:25) [Clang 14.0.6 ]",
+        "command_line_arguments": "/opt/anaconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.app --run-id=SoccerTwos --no-graphics --force",
+        "mlagents_version": "1.2.0.dev0",
+        "mlagents_envs_version": "1.2.0.dev0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "2.5.1",
+        "numpy_version": "1.23.5",
+        "end_time_seconds": "1731313487"
+    },
+    "total": 1236.545987957972,
+    "count": 1,
+    "self": 0.004797665984369814,
+    "children": {
+        "run_training.setup": {
+            "total": 0.01639762509148568,
+            "count": 1,
+            "self": 0.01639762509148568
+        },
+        "TrainerController.start_learning": {
+            "total": 1236.5247926668962,
+            "count": 1,
+            "self": 0.22838388779200613,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 4.5475917919538915,
+                    "count": 2,
+                    "self": 4.5475917919538915
+                },
+                "TrainerController.advance": {
+                    "total": 1231.0880667380989,
+                    "count": 17821,
+                    "self": 0.21842296177055687,
+                    "children": {
+                        "env_step": {
+                            "total": 992.9914524647174,
+                            "count": 17821,
+                            "self": 954.8745469633723,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 37.965532288653776,
+                                    "count": 17821,
+                                    "self": 1.1281631885794923,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 36.837369100074284,
+                                            "count": 35360,
+                                            "self": 36.837369100074284
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 0.15137321269139647,
+                                    "count": 17820,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 1231.8887167989742,
+                                            "count": 17820,
+                                            "is_parallel": true,
+                                            "self": 306.9543487156043,
+                                            "children": {
+                                                "steps_from_proto": {
+                                                    "total": 0.00428250094410032,
+                                                    "count": 4,
+                                                    "is_parallel": true,
+                                                    "self": 0.0006960829487070441,
+                                                    "children": {
+                                                        "_process_rank_one_or_two_observation": {
+                                                            "total": 0.003586417995393276,
+                                                            "count": 16,
+                                                            "is_parallel": true,
+                                                            "self": 0.003586417995393276
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 924.9300855824258,
+                                                    "count": 17820,
+                                                    "is_parallel": true,
+                                                    "self": 2.6337445022072643,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 15.928510103025474,
+                                                            "count": 17820,
+                                                            "is_parallel": true,
+                                                            "self": 15.928510103025474
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 872.163203357486,
+                                                            "count": 17820,
+                                                            "is_parallel": true,
+                                                            "self": 872.163203357486
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 34.204627619707026,
+                                                            "count": 35640,
+                                                            "is_parallel": true,
+                                                            "self": 3.7891682606423274,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 30.415459359064698,
+                                                                    "count": 142560,
+                                                                    "is_parallel": true,
+                                                                    "self": 30.415459359064698
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 237.87819131161086,
+                            "count": 17820,
+                            "self": 2.284961257711984,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 34.421652843710035,
+                                    "count": 17820,
+                                    "self": 34.421652843710035
+                                },
+                                "_update_policy": {
+                                    "total": 201.17157721018884,
+                                    "count": 12,
+                                    "self": 19.691816289327107,
+                                    "children": {
+                                        "TorchPOCAOptimizer.update": {
+                                            "total": 181.47976092086174,
+                                            "count": 360,
+                                            "self": 181.47976092086174
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 9.579816833138466e-07,
+                    "count": 1,
+                    "self": 9.579816833138466e-07
+                },
+                "TrainerController._save_models": {
+                    "total": 0.6607492910698056,
+                    "count": 1,
+                    "self": 0.0020934580825269222,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.6586558329872787,
+                            "count": 1,
+                            "self": 0.6586558329872787
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,30 @@
+{
+    "SoccerTwos": {
+        "elo": 1193.7578446427165,
+        "checkpoints": [
+            {
+                "steps": 270278,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-270278.onnx",
+                "reward": 0.0,
+                "creation_time": 1731313487.086136,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-270278.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 270278,
+            "file_path": "results/SoccerTwos/SoccerTwos.onnx",
+            "reward": 0.0,
+            "creation_time": 1731313487.086136,
+            "auxillary_file_paths": [
+                "results/SoccerTwos/SoccerTwos/SoccerTwos-270278.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "1.2.0.dev0",
+        "torch_version": "2.5.1"
+    }
+}