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: brettgoehre/poca-SoccerTwosMemory
+  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 sha256:382fa58a72199d6dd58f6869e3c1f4b5c0353f94cbfd731a4da94792bbed3b65
+size 2351062

SoccerTwos/SoccerTwos-1499394.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b402ac2672cff38dc844051a6d73e465d3dd949b401c61d19952131be72cbed
+size 2351062

SoccerTwos/SoccerTwos-1499394.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c7629c8bcfd53335d927f2f115d449c19062a9151c10b41fdd0b77b57c32279
+size 36302950

SoccerTwos/SoccerTwos-999356.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ad1afecace049c7dbb1837f6c37b4f33aed734d733e82f7c3e099cca9f2b49f
+size 2351062

SoccerTwos/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2252c8e3bdc2c4ab2c4dc3266a3ae51e88ff1886224bdc9f6de3441664eb90b5
+size 36301318

SoccerTwos/events.out.tfevents.1725478844.Bretts-MacBook-Pro.local.72766.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50e21b67fe74f262ba283401a667969191f6f2bf26c97580c35179f80946c513
+size 279640

SoccerTwos/events.out.tfevents.1725486116.Bretts-MacBook-Pro.local.3446.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11f398e3557dd9aa0ebc01b8423fcdae2d887d248b0e6499ec45afde51f1b484
+size 424931

SoccerTwos/events.out.tfevents.1725499029.Bretts-MBP.home.48420.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ed43ddcae413951fa86b3bc4f134069b0c69bf306a74a9ad8e8832b54a4c791
+size 874936

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": 0.01, "epsilon": 0.2, "lambd": 0.9, "num_epoch": 3, "learning_rate_schedule": "constant", "beta_schedule": "linear", "epsilon_schedule": "constant"}, "checkpoint_interval": 500000, "network_settings": {"normalize": true, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple", "memory": {"sequence_length": 16, "memory_size": 128}, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.995, "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}}, "curiosity": {"gamma": 0.9, "strength": 0.05, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0003, "encoding_size": 512}, "rnd": {"gamma": 0.9, "strength": 0.01, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0001, "encoding_size": null}}, "init_path": null, "keep_checkpoints": 1, "even_checkpoints": false, "max_steps": 80000000, "time_horizon": 1000, "summary_freq": 10000, "threaded": false, "self_play": {"save_steps": 100000, "team_change": 400000, "swap_steps": 2000, "window": 30, "play_against_latest_model_ratio": 0.9, "initial_elo": 1.0}, "behavioral_cloning": null}}, "env_settings": {"env_path": "./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": "sept-run-01", "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 +1,112 @@
+default_settings: null
+behaviors:
+  SoccerTwos:
+    trainer_type: poca
+    hyperparameters:
+      batch_size: 2048
+      buffer_size: 20480
+      learning_rate: 0.0003
+      beta: 0.01
+      epsilon: 0.2
+      lambd: 0.9
+      num_epoch: 3
+      learning_rate_schedule: constant
+      beta_schedule: linear
+      epsilon_schedule: constant
+    checkpoint_interval: 500000
+    network_settings:
+      normalize: true
+      hidden_units: 512
+      num_layers: 2
+      vis_encode_type: simple
+      memory:
+        sequence_length: 16
+        memory_size: 128
+      goal_conditioning_type: hyper
+      deterministic: false
+    reward_signals:
+      extrinsic:
+        gamma: 0.995
+        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
+      curiosity:
+        gamma: 0.9
+        strength: 0.05
+        network_settings:
+          normalize: false
+          hidden_units: 512
+          num_layers: 2
+          vis_encode_type: simple
+          memory: null
+          goal_conditioning_type: hyper
+          deterministic: false
+        learning_rate: 0.0003
+        encoding_size: 512
+      rnd:
+        gamma: 0.9
+        strength: 0.01
+        network_settings:
+          normalize: false
+          hidden_units: 128
+          num_layers: 2
+          vis_encode_type: simple
+          memory: null
+          goal_conditioning_type: hyper
+          deterministic: false
+        learning_rate: 0.0001
+        encoding_size: null
+    init_path: null
+    keep_checkpoints: 1
+    even_checkpoints: false
+    max_steps: 80000000
+    time_horizon: 1000
+    summary_freq: 10000
+    threaded: false
+    self_play:
+      save_steps: 100000
+      team_change: 400000
+      swap_steps: 2000
+      window: 30
+      play_against_latest_model_ratio: 0.9
+      initial_elo: 1.0
+    behavioral_cloning: null
+env_settings:
+  env_path: ./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: sept-run-01
+  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 +1,342 @@
+Mono path[0] = '/Users/brettgohre/Desktop/huggingface/ml-agents/SoccerTwos/SoccerTwos.app/Contents/Resources/Data/Managed'
+Mono config path = '/Users/brettgohre/Desktop/huggingface/ml-agents/SoccerTwos/SoccerTwos.app/Contents/MonoBleedingEdge/etc'
+New input system (experimental) initialized
+Initialize engine version: 2021.3.17f1 (3e8111cac19d)
+[Subsystems] Discovering subsystems at path /Users/brettgohre/Desktop/huggingface/ml-agents/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  0.046 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: 0.207292 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
+Default audio device was changed, but the audio system failed to initialize it. Attempting to reset sound system.
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+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 +1,476 @@
+{
+    "name": "root",
+    "gauges": {
+        "SoccerTwos.Policy.Entropy.mean": {
+            "value": 2.9194252490997314,
+            "min": 2.7066967487335205,
+            "max": 2.94661283493042,
+            "count": 64
+        },
+        "SoccerTwos.Policy.Entropy.sum": {
+            "value": 57547.7109375,
+            "min": 4742.3798828125,
+            "max": 93634.375,
+            "count": 64
+        },
+        "SoccerTwos.Environment.EpisodeLength.mean": {
+            "value": 604.875,
+            "min": 322.6923076923077,
+            "max": 999.0,
+            "count": 64
+        },
+        "SoccerTwos.Environment.EpisodeLength.sum": {
+            "value": 19356.0,
+            "min": 3972.0,
+            "max": 31968.0,
+            "count": 64
+        },
+        "SoccerTwos.Self-play.ELO.mean": {
+            "value": 4.928913831525834,
+            "min": -2.9657419777902905,
+            "max": 4.928913831525834,
+            "count": 50
+        },
+        "SoccerTwos.Self-play.ELO.sum": {
+            "value": 39.43131065220667,
+            "min": -23.725935822322324,
+            "max": 98.57827663051667,
+            "count": 50
+        },
+        "SoccerTwos.Step.mean": {
+            "value": 1069432.0,
+            "min": 439134.0,
+            "max": 1069432.0,
+            "count": 64
+        },
+        "SoccerTwos.Step.sum": {
+            "value": 1069432.0,
+            "min": 439134.0,
+            "max": 1069432.0,
+            "count": 64
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
+            "value": -0.07731862366199493,
+            "min": -0.17547613382339478,
+            "max": -0.012409262359142303,
+            "count": 64
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
+            "value": -1.237097978591919,
+            "min": -2.31373929977417,
+            "max": -0.21196956932544708,
+            "count": 64
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
+            "value": -0.10046061873435974,
+            "min": -0.17158803343772888,
+            "max": -0.011743116192519665,
+            "count": 64
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
+            "value": -1.6073698997497559,
+            "min": -2.326843738555908,
+            "max": -0.18669486045837402,
+            "count": 64
+        },
+        "SoccerTwos.Policy.CuriosityBaselineEstimate.mean": {
+            "value": 0.04025515913963318,
+            "min": 0.03323616459965706,
+            "max": 0.061155594885349274,
+            "count": 64
+        },
+        "SoccerTwos.Policy.CuriosityBaselineEstimate.sum": {
+            "value": 0.6440825462341309,
+            "min": 0.2457103729248047,
+            "max": 1.2533018589019775,
+            "count": 64
+        },
+        "SoccerTwos.Policy.CuriosityValueEstimate.mean": {
+            "value": 0.03912646323442459,
+            "min": 0.032525066286325455,
+            "max": 0.06183749437332153,
+            "count": 64
+        },
+        "SoccerTwos.Policy.CuriosityValueEstimate.sum": {
+            "value": 0.6260234117507935,
+            "min": 0.24073556065559387,
+            "max": 1.2407689094543457,
+            "count": 64
+        },
+        "SoccerTwos.Policy.RndBaselineEstimate.mean": {
+            "value": 0.0281881932169199,
+            "min": -0.0028001777827739716,
+            "max": 0.044277217239141464,
+            "count": 64
+        },
+        "SoccerTwos.Policy.RndBaselineEstimate.sum": {
+            "value": 0.4510110914707184,
+            "min": -0.03360213339328766,
+            "max": 0.6157264113426208,
+            "count": 64
+        },
+        "SoccerTwos.Policy.RndValueEstimate.mean": {
+            "value": 0.035632044076919556,
+            "min": -0.003357115900143981,
+            "max": 0.0452946312725544,
+            "count": 64
+        },
+        "SoccerTwos.Policy.RndValueEstimate.sum": {
+            "value": 0.5701127052307129,
+            "min": -0.0402853898704052,
+            "max": 0.6341248154640198,
+            "count": 64
+        },
+        "SoccerTwos.Environment.CumulativeReward.mean": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 64
+        },
+        "SoccerTwos.Environment.CumulativeReward.sum": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 64
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.mean": {
+            "value": -0.29100000113248825,
+            "min": -0.5357724140430319,
+            "max": 0.2798571416309902,
+            "count": 64
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.sum": {
+            "value": -4.656000018119812,
+            "min": -15.537400007247925,
+            "max": 3.9179999828338623,
+            "count": 64
+        },
+        "SoccerTwos.Policy.CuriosityReward.mean": {
+            "value": 2.320769681595266,
+            "min": 0.0,
+            "max": 5.748547983169556,
+            "count": 64
+        },
+        "SoccerTwos.Policy.CuriosityReward.sum": {
+            "value": 37.132314905524254,
+            "min": 0.0,
+            "max": 61.15827703475952,
+            "count": 64
+        },
+        "SoccerTwos.Policy.RndReward.mean": {
+            "value": 0.5761634132359177,
+            "min": 0.31020875843562956,
+            "max": 4.226163029670715,
+            "count": 64
+        },
+        "SoccerTwos.Policy.RndReward.sum": {
+            "value": 9.218614611774683,
+            "min": 5.0982994213700294,
+            "max": 45.86141597852111,
+            "count": 64
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.mean": {
+            "value": -0.29100000113248825,
+            "min": -0.5357724140430319,
+            "max": 0.2798571416309902,
+            "count": 64
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.sum": {
+            "value": -4.656000018119812,
+            "min": -15.537400007247925,
+            "max": 3.9179999828338623,
+            "count": 64
+        },
+        "SoccerTwos.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 64
+        },
+        "SoccerTwos.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 64
+        },
+        "SoccerTwos.Losses.PolicyLoss.mean": {
+            "value": 0.05118437986044834,
+            "min": 0.034444741702949006,
+            "max": 0.07191514666968336,
+            "count": 28
+        },
+        "SoccerTwos.Losses.PolicyLoss.sum": {
+            "value": 0.05118437986044834,
+            "min": 0.034444741702949006,
+            "max": 0.07191514666968336,
+            "count": 28
+        },
+        "SoccerTwos.Losses.ValueLoss.mean": {
+            "value": 0.0020198069929998987,
+            "min": 2.9689358901426505e-05,
+            "max": 0.0020198069929998987,
+            "count": 28
+        },
+        "SoccerTwos.Losses.ValueLoss.sum": {
+            "value": 0.0020198069929998987,
+            "min": 2.9689358901426505e-05,
+            "max": 0.0020198069929998987,
+            "count": 28
+        },
+        "SoccerTwos.Losses.BaselineLoss.mean": {
+            "value": 0.0020883430406684056,
+            "min": 2.673255736832895e-05,
+            "max": 0.0020883430406684056,
+            "count": 28
+        },
+        "SoccerTwos.Losses.BaselineLoss.sum": {
+            "value": 0.0020883430406684056,
+            "min": 2.673255736832895e-05,
+            "max": 0.0020883430406684056,
+            "count": 28
+        },
+        "SoccerTwos.Policy.LearningRate.mean": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 28
+        },
+        "SoccerTwos.Policy.LearningRate.sum": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 28
+        },
+        "SoccerTwos.Policy.Epsilon.mean": {
+            "value": 0.20000000000000007,
+            "min": 0.19999999999999996,
+            "max": 0.20000000000000007,
+            "count": 28
+        },
+        "SoccerTwos.Policy.Epsilon.sum": {
+            "value": 0.20000000000000007,
+            "min": 0.19999999999999996,
+            "max": 0.20000000000000007,
+            "count": 28
+        },
+        "SoccerTwos.Policy.Beta.mean": {
+            "value": 0.009868430950750002,
+            "min": 0.009868430950750002,
+            "max": 0.009941550008500001,
+            "count": 28
+        },
+        "SoccerTwos.Policy.Beta.sum": {
+            "value": 0.009868430950750002,
+            "min": 0.009868430950750002,
+            "max": 0.009941550008500001,
+            "count": 28
+        },
+        "SoccerTwos.Losses.CuriosityForwardLoss.mean": {
+            "value": 0.07661932905515036,
+            "min": 0.07661932905515036,
+            "max": 0.12366530618497304,
+            "count": 28
+        },
+        "SoccerTwos.Losses.CuriosityForwardLoss.sum": {
+            "value": 0.07661932905515036,
+            "min": 0.07661932905515036,
+            "max": 0.12366530618497304,
+            "count": 28
+        },
+        "SoccerTwos.Losses.CuriosityInverseLoss.mean": {
+            "value": 2.333798543612162,
+            "min": 2.103957215944926,
+            "max": 2.3597320238749186,
+            "count": 28
+        },
+        "SoccerTwos.Losses.CuriosityInverseLoss.sum": {
+            "value": 2.333798543612162,
+            "min": 2.103957215944926,
+            "max": 2.3597320238749186,
+            "count": 28
+        },
+        "SoccerTwos.Losses.RNDLoss.mean": {
+            "value": 0.09128604084253311,
+            "min": 0.09128604084253311,
+            "max": 0.4021055996417999,
+            "count": 28
+        },
+        "SoccerTwos.Losses.RNDLoss.sum": {
+            "value": 0.09128604084253311,
+            "min": 0.09128604084253311,
+            "max": 0.4021055996417999,
+            "count": 28
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1725486114",
+        "python_version": "3.10.12 (main, Aug 23 2024, 16:29:11) [Clang 15.0.0 (clang-1500.3.9.4)]",
+        "command_line_arguments": "/Users/brettgohre/Desktop/huggingface/ml-agents/games/bin/mlagents-learn ./config/poca/sept/one.yaml --env=./SoccerTwos/SoccerTwos.app --run-id=sept-run-01 --no-graphics --resume",
+        "mlagents_version": "1.1.0.dev0",
+        "mlagents_envs_version": "1.1.0.dev0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "2.4.0",
+        "numpy_version": "1.23.5",
+        "end_time_seconds": "1725488336"
+    },
+    "total": 2222.1776464590075,
+    "count": 1,
+    "self": 0.0701700420177076,
+    "children": {
+        "run_training.setup": {
+            "total": 0.013670291999005713,
+            "count": 1,
+            "self": 0.013670291999005713
+        },
+        "TrainerController.start_learning": {
+            "total": 2222.093806124991,
+            "count": 1,
+            "self": 0.3377753770328127,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 1.7997647919983137,
+                    "count": 3,
+                    "self": 1.7997647919983137
+                },
+                "TrainerController.advance": {
+                    "total": 2219.8443342889514,
+                    "count": 40646,
+                    "self": 0.3316819507308537,
+                    "children": {
+                        "env_step": {
+                            "total": 1791.3922533830773,
+                            "count": 40646,
+                            "self": 1712.9993363862886,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 78.15483157281415,
+                                    "count": 40646,
+                                    "self": 2.5638017278397456,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 75.5910298449744,
+                                            "count": 80638,
+                                            "self": 75.5910298449744
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 0.23808542397455312,
+                                    "count": 40645,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 2220.0730693208898,
+                                            "count": 40645,
+                                            "is_parallel": true,
+                                            "self": 554.5647922483477,
+                                            "children": {
+                                                "steps_from_proto": {
+                                                    "total": 0.004229875979945064,
+                                                    "count": 6,
+                                                    "is_parallel": true,
+                                                    "self": 0.0005952939682174474,
+                                                    "children": {
+                                                        "_process_rank_one_or_two_observation": {
+                                                            "total": 0.003634582011727616,
+                                                            "count": 24,
+                                                            "is_parallel": true,
+                                                            "self": 0.003634582011727616
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 1665.5040471965622,
+                                                    "count": 40645,
+                                                    "is_parallel": true,
+                                                    "self": 4.165579487016657,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 29.249617290261085,
+                                                            "count": 40645,
+                                                            "is_parallel": true,
+                                                            "self": 29.249617290261085
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 1578.8149416175438,
+                                                            "count": 40645,
+                                                            "is_parallel": true,
+                                                            "self": 1578.8149416175438
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 53.27390880174062,
+                                                            "count": 81290,
+                                                            "is_parallel": true,
+                                                            "self": 6.224019605710055,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 47.04988919603056,
+                                                                    "count": 325160,
+                                                                    "is_parallel": true,
+                                                                    "self": 47.04988919603056
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 428.1203989551432,
+                            "count": 40645,
+                            "self": 3.3293685391981853,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 138.76527908295975,
+                                    "count": 40645,
+                                    "self": 138.53822916596255,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 0.22704991699720267,
+                                            "count": 2,
+                                            "self": 0.22704991699720267
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 286.02575133298524,
+                                    "count": 28,
+                                    "self": 58.20280640778947,
+                                    "children": {
+                                        "TorchPOCAOptimizer.update": {
+                                            "total": 227.82294492519577,
+                                            "count": 858,
+                                            "self": 227.82294492519577
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 4.169996827840805e-07,
+                    "count": 1,
+                    "self": 4.169996827840805e-07
+                },
+                "TrainerController._save_models": {
+                    "total": 0.11193125000863802,
+                    "count": 1,
+                    "self": 0.001827208005124703,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.11010404200351331,
+                            "count": 1,
+                            "self": 0.11010404200351331
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,30 @@
+{
+    "SoccerTwos": {
+        "elo": 4.928913831525834,
+        "checkpoints": [
+            {
+                "steps": 1070432,
+                "file_path": "results/sept-run-01/SoccerTwos/SoccerTwos-1070432.onnx",
+                "reward": 0.0,
+                "creation_time": 1725488336.925156,
+                "auxillary_file_paths": [
+                    "results/sept-run-01/SoccerTwos/SoccerTwos-1070432.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 1070432,
+            "file_path": "results/sept-run-01/SoccerTwos.onnx",
+            "reward": 0.0,
+            "creation_time": 1725488336.925156,
+            "auxillary_file_paths": [
+                "results/sept-run-01/SoccerTwos/SoccerTwos-1070432.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "1.1.0.dev0",
+        "torch_version": "2.4.0"
+    }
+}