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: ch-bz/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:b742364eafec7d06c1205effe8a214d0e2946a363828c93c2aafce8caa04ac20
+size 1768747

SoccerTwos/SoccerTwos-3499992.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63ffec9a9e532374705169199f7f0f13d3280e5c55db5b79f107e0987a0c6049
+size 1768747

SoccerTwos/SoccerTwos-3499992.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ee59c1457c479056b0f9e253f66e566f527689538a63f18543e8cd22d2cbd2f
+size 28432022

SoccerTwos/SoccerTwos-3999903.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3ae8e0141a2e8d4a189c1f4c4f53c7d437f181afa064af3279e19d78723c1de
+size 1768747

SoccerTwos/SoccerTwos-3999903.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1c067ca8ace5dbf1732d1b48d75c36a9c410a3cbd12b0f78b4fe272abc00e60
+size 28432022

SoccerTwos/SoccerTwos-4499985.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d65a3c2b1849c29e2bc0a299ee0190012084d64bc29bd01cc4b64a466084859c
+size 1768747

SoccerTwos/SoccerTwos-4499985.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aaf4ddb7b8d61c7f1aa98d6a43fce18b94c565273195d3853003a2ce76d021ce
+size 28432022

SoccerTwos/SoccerTwos-4999963.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b742364eafec7d06c1205effe8a214d0e2946a363828c93c2aafce8caa04ac20
+size 1768747

SoccerTwos/SoccerTwos-4999963.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6da846649547966b139fa463071fc3e6274bdd3a524afdc1a91f2534ed465a49
+size 28432022

SoccerTwos/SoccerTwos-5000056.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b742364eafec7d06c1205effe8a214d0e2946a363828c93c2aafce8caa04ac20
+size 1768747

SoccerTwos/SoccerTwos-5000056.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3f366f54c464a2d712c7e16471b0a7c093655b0c2a1149a3a37ea82bae3141a
+size 28432022

SoccerTwos/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38610f73ed973d506afdd29552cd71257ed28e4d706cfbb9d4c93489eabe0bad
+size 28431030

SoccerTwos/events.out.tfevents.1732183485.Christian.22356.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79995e7ac481275ac6a815345d3561c2df69a561d61b86d72861656ef87ab978
+size 5001053

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": 5000000, "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": "./build/UnityEnvironment.exe", "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: 5000000
+    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: ./build/UnityEnvironment.exe
+  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 +1,51 @@
+Mono path[0] = 'C:/Users/songo/Documents/Python/DeepRLCourse/Unit5/ml-agents/build/UnityEnvironment_Data/Managed'
+Mono config path = 'C:/Users/songo/Documents/Python/DeepRLCourse/Unit5/ml-agents/build/MonoBleedingEdge/etc'
+[Physics::Module] Initialized fallback backend.
+[Physics::Module] Id: 0xdecafbad
+Initialize engine version: 6000.0.26f1 (ccb7c73d2c02)
+[Subsystems] Discovering subsystems at path C:/Users/songo/Documents/Python/DeepRLCourse/Unit5/ml-agents/build/UnityEnvironment_Data/UnitySubsystems
+Forcing GfxDevice: Null
+GfxDevice: creating device client; kGfxThreadingModeNonThreaded
+NullGfxDevice:
+    Version:  NULL 1.0 [1.0]
+    Renderer: Null Device
+    Vendor:   Unity Technologies
+Begin MonoManager ReloadAssembly
+- Loaded All Assemblies, in  0.101 seconds
+- Finished resetting the current domain, in  0.002 seconds
+[Physics::Module] Selected backend.
+[Physics::Module] Name: PhysX
+[Physics::Module] Id: 0xf2b8ea05
+[Physics::Module] SDK Version: 4.1.2
+[Physics::Module] Integration Version: 1.0.0
+[Physics::Module] Threading Mode: Multi-Threaded
+ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+Microsoft Media Foundation video decoding to texture disabled: graphics device is Null, only Direct3D 11 and Direct3D 12 (only on desktop) are supported for hardware-accelerated video decoding.
+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: '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?
+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?
+UnloadTime: 0.305600 ms
+Registered Communicator in Agent.
+ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+[Physics::Module] Cleanup current backned.
+[Physics::Module] Id: 0xf2b8ea05

run_logs/timers.json

@@ -0,0 +1,368 @@
+{
+    "name": "root",
+    "gauges": {
+        "SoccerTwos.Policy.Entropy.mean": {
+            "value": 1.7295876741409302,
+            "min": 1.7143337726593018,
+            "max": 3.2957329750061035,
+            "count": 500
+        },
+        "SoccerTwos.Policy.Entropy.sum": {
+            "value": 34093.6328125,
+            "min": 23113.244140625,
+            "max": 105463.453125,
+            "count": 500
+        },
+        "SoccerTwos.Environment.EpisodeLength.mean": {
+            "value": 52.18279569892473,
+            "min": 44.288288288288285,
+            "max": 999.0,
+            "count": 500
+        },
+        "SoccerTwos.Environment.EpisodeLength.sum": {
+            "value": 19412.0,
+            "min": 16708.0,
+            "max": 23952.0,
+            "count": 500
+        },
+        "SoccerTwos.Self-play.ELO.mean": {
+            "value": 1546.1747016051104,
+            "min": 1198.8230744642071,
+            "max": 1553.6576481939073,
+            "count": 495
+        },
+        "SoccerTwos.Self-play.ELO.sum": {
+            "value": 287588.49449855054,
+            "min": 2400.090268587322,
+            "max": 331281.6392627042,
+            "count": 495
+        },
+        "SoccerTwos.Step.mean": {
+            "value": 4999963.0,
+            "min": 9992.0,
+            "max": 4999963.0,
+            "count": 500
+        },
+        "SoccerTwos.Step.sum": {
+            "value": 4999963.0,
+            "min": 9992.0,
+            "max": 4999963.0,
+            "count": 500
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
+            "value": 0.003207757603377104,
+            "min": -0.10547797381877899,
+            "max": 0.23249369859695435,
+            "count": 500
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
+            "value": 0.5998506546020508,
+            "min": -19.196990966796875,
+            "max": 29.403961181640625,
+            "count": 500
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 0.002363880630582571,
+            "min": -0.1065421923995018,
+            "max": 0.22224962711334229,
+            "count": 500
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 0.4420456886291504,
+            "min": -19.39067840576172,
+            "max": 28.159595489501953,
+            "count": 500
+        },
+        "SoccerTwos.Environment.CumulativeReward.mean": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 500
+        },
+        "SoccerTwos.Environment.CumulativeReward.sum": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 500
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.mean": {
+            "value": 0.13469304789833844,
+            "min": -0.46153846153846156,
+            "max": 0.4611914855368594,
+            "count": 500
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.sum": {
+            "value": 25.18759995698929,
+            "min": -46.96580022573471,
+            "max": 51.82080054283142,
+            "count": 500
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.mean": {
+            "value": 0.13469304789833844,
+            "min": -0.46153846153846156,
+            "max": 0.4611914855368594,
+            "count": 500
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.sum": {
+            "value": 25.18759995698929,
+            "min": -46.96580022573471,
+            "max": 51.82080054283142,
+            "count": 500
+        },
+        "SoccerTwos.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 500
+        },
+        "SoccerTwos.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 500
+        },
+        "SoccerTwos.Losses.PolicyLoss.mean": {
+            "value": 0.0145405653398484,
+            "min": 0.010950432086732083,
+            "max": 0.0241118274241065,
+            "count": 241
+        },
+        "SoccerTwos.Losses.PolicyLoss.sum": {
+            "value": 0.0145405653398484,
+            "min": 0.010950432086732083,
+            "max": 0.0241118274241065,
+            "count": 241
+        },
+        "SoccerTwos.Losses.ValueLoss.mean": {
+            "value": 0.10753242050607999,
+            "min": 0.0001912354675975318,
+            "max": 0.11995167136192322,
+            "count": 241
+        },
+        "SoccerTwos.Losses.ValueLoss.sum": {
+            "value": 0.10753242050607999,
+            "min": 0.0001912354675975318,
+            "max": 0.11995167136192322,
+            "count": 241
+        },
+        "SoccerTwos.Losses.BaselineLoss.mean": {
+            "value": 0.1092821958164374,
+            "min": 0.00019016436344827526,
+            "max": 0.12219539657235146,
+            "count": 241
+        },
+        "SoccerTwos.Losses.BaselineLoss.sum": {
+            "value": 0.1092821958164374,
+            "min": 0.00019016436344827526,
+            "max": 0.12219539657235146,
+            "count": 241
+        },
+        "SoccerTwos.Policy.LearningRate.mean": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 241
+        },
+        "SoccerTwos.Policy.LearningRate.sum": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 241
+        },
+        "SoccerTwos.Policy.Epsilon.mean": {
+            "value": 0.20000000000000007,
+            "min": 0.20000000000000007,
+            "max": 0.20000000000000007,
+            "count": 241
+        },
+        "SoccerTwos.Policy.Epsilon.sum": {
+            "value": 0.20000000000000007,
+            "min": 0.20000000000000007,
+            "max": 0.20000000000000007,
+            "count": 241
+        },
+        "SoccerTwos.Policy.Beta.mean": {
+            "value": 0.005000000000000001,
+            "min": 0.005000000000000001,
+            "max": 0.005000000000000001,
+            "count": 241
+        },
+        "SoccerTwos.Policy.Beta.sum": {
+            "value": 0.005000000000000001,
+            "min": 0.005000000000000001,
+            "max": 0.005000000000000001,
+            "count": 241
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1732183482",
+        "python_version": "3.10.6 (tags/v3.10.6:9c7b4bd, Aug  1 2022, 21:53:49) [MSC v.1932 64 bit (AMD64)]",
+        "command_line_arguments": "C:\\Users\\songo\\Documents\\Python\\DeepRLCourse\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./build/UnityEnvironment.exe --run-id=SoccerTwos --no-graphics",
+        "mlagents_version": "1.1.0",
+        "mlagents_envs_version": "1.1.0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "2.5.1+cu124",
+        "numpy_version": "1.23.5",
+        "end_time_seconds": "1732191792"
+    },
+    "total": 8309.3610955,
+    "count": 1,
+    "self": 0.21610680000230786,
+    "children": {
+        "run_training.setup": {
+            "total": 0.15250379999997676,
+            "count": 1,
+            "self": 0.15250379999997676
+        },
+        "TrainerController.start_learning": {
+            "total": 8308.992484899998,
+            "count": 1,
+            "self": 5.788465800404083,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 5.170615499991982,
+                    "count": 25,
+                    "self": 5.170615499991982
+                },
+                "TrainerController.advance": {
+                    "total": 8297.868851099603,
+                    "count": 341488,
+                    "self": 4.917915998856188,
+                    "children": {
+                        "env_step": {
+                            "total": 6073.46292710023,
+                            "count": 341488,
+                            "self": 3320.8746034004544,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 2748.922556099893,
+                                    "count": 341488,
+                                    "self": 29.68259440168913,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 2719.239961698204,
+                                            "count": 630516,
+                                            "self": 2719.239961698204
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 3.665767599883111,
+                                    "count": 341488,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 8298.63097009989,
+                                            "count": 341488,
+                                            "is_parallel": true,
+                                            "self": 5606.755565901203,
+                                            "children": {
+                                                "steps_from_proto": {
+                                                    "total": 0.03797010000926093,
+                                                    "count": 50,
+                                                    "is_parallel": true,
+                                                    "self": 0.006986200001847465,
+                                                    "children": {
+                                                        "_process_rank_one_or_two_observation": {
+                                                            "total": 0.030983900007413467,
+                                                            "count": 200,
+                                                            "is_parallel": true,
+                                                            "self": 0.030983900007413467
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 2691.8374340986775,
+                                                    "count": 341488,
+                                                    "is_parallel": true,
+                                                    "self": 153.3621247981937,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 117.19420530081334,
+                                                            "count": 341488,
+                                                            "is_parallel": true,
+                                                            "self": 117.19420530081334
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 1948.330427700279,
+                                                            "count": 341488,
+                                                            "is_parallel": true,
+                                                            "self": 1948.330427700279
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 472.9506762993915,
+                                                            "count": 682976,
+                                                            "is_parallel": true,
+                                                            "self": 78.44430690255831,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 394.5063693968332,
+                                                                    "count": 2731904,
+                                                                    "is_parallel": true,
+                                                                    "self": 394.5063693968332
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 2219.488008000517,
+                            "count": 341488,
+                            "self": 42.762002600848064,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 1185.0353891996638,
+                                    "count": 341488,
+                                    "self": 1183.3512311996674,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 1.684157999996387,
+                                            "count": 10,
+                                            "self": 1.684157999996387
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 991.690616200005,
+                                    "count": 241,
+                                    "self": 555.1552949998186,
+                                    "children": {
+                                        "TorchPOCAOptimizer.update": {
+                                            "total": 436.53532120018644,
+                                            "count": 7230,
+                                            "self": 436.53532120018644
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 5.999972927384079e-07,
+                    "count": 1,
+                    "self": 5.999972927384079e-07
+                },
+                "TrainerController._save_models": {
+                    "total": 0.16455190000124276,
+                    "count": 1,
+                    "self": 0.007950800001708558,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.1566010999995342,
+                            "count": 1,
+                            "self": 0.1566010999995342
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,66 @@
+{
+    "SoccerTwos": {
+        "checkpoints": [
+            {
+                "steps": 3499992,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-3499992.onnx",
+                "reward": 0.0,
+                "creation_time": 1732189308.7448285,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-3499992.pt"
+                ]
+            },
+            {
+                "steps": 3999903,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-3999903.onnx",
+                "reward": 0.0,
+                "creation_time": 1732190120.5404708,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-3999903.pt"
+                ]
+            },
+            {
+                "steps": 4499985,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-4499985.onnx",
+                "reward": 0.0,
+                "creation_time": 1732190945.2867255,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-4499985.pt"
+                ]
+            },
+            {
+                "steps": 4999963,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-4999963.onnx",
+                "reward": 0.0,
+                "creation_time": 1732191791.635519,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-4999963.pt"
+                ]
+            },
+            {
+                "steps": 5000056,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-5000056.onnx",
+                "reward": 0.0,
+                "creation_time": 1732191791.8106294,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-5000056.pt"
+                ]
+            }
+        ],
+        "elo": 1551.556986640927,
+        "final_checkpoint": {
+            "steps": 5000056,
+            "file_path": "results\\SoccerTwos\\SoccerTwos.onnx",
+            "reward": 0.0,
+            "creation_time": 1732191791.8106294,
+            "auxillary_file_paths": [
+                "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-5000056.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "1.1.0",
+        "torch_version": "2.5.1+cu124"
+    }
+}