First Push

README.md

@@ -0,0 +1,31 @@
+
+---
+      tags:
+      - unity-ml-agents
+      - ml-agents
+      - deep-reinforcement-learning
+      - reinforcement-learning
+      - ML-Agents-SoccerTwos
+      library_name: ml-agents
+---
+    
+  # **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://github.com/huggingface/ml-agents#get-started
+  We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
+
+
+  ### Resume the training
+  ```
+  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. Go to https://huggingface.co/spaces/unity/ML-Agents-SoccerTwos
+  2. Step 1: Write your model_id: Art-phys/poca-SoccerTwos_420M
+  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 sha256:7eabdcb6674d24b5193f942de2714005c8283f46066e7e27f15b524c7eb61765
+size 1768747

SoccerTwos/SoccerTwos-423999940.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a189b2386f1f7cf57c418212e0b8b99387e4e95cf1056a4cccc6fe4b1baf024d
+size 1768746

SoccerTwos/SoccerTwos-423999940.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a76a7cb76b16634c616778b6f0c154eee14133af63b3d0a66edf325771cab6b2
+size 28430147

SoccerTwos/SoccerTwos-424999984.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0222125f3066fbeb9cc8c9b0ad0b9d044a36be2c6be6ef6ac445ece23898ad17
+size 1768746

SoccerTwos/SoccerTwos-424999984.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97e103f63ad7de55d48fd1a5c311962db0621b9130d4c1fbf731e8b597eed72e
+size 28430147

SoccerTwos/SoccerTwos-425999927.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:476a403e9d1d599dcbe8979d30ecb29eec2ca83e8aa94f7a22e05ce7b5e0c83c
+size 1768746

SoccerTwos/SoccerTwos-425999927.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:473284e040815ae6dd8aa74d746fedc51097bf2a5e313d738dac4ac3bbedc7b6
+size 28430147

SoccerTwos/SoccerTwos-426999958.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0daa69ea9496bd0c848b9f5120959e632688602132b89cc0b5fd81b496619255
+size 1768746

SoccerTwos/SoccerTwos-426999958.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4ceba20d6cf32e67082bc3a2d74ec4d213dc5cea918c2ae24349345b39d5388
+size 28430147

SoccerTwos/SoccerTwos-427999965.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28179fa6268e2fe2a46051d91601b551530f5096a08e1497423f54b642af7475
+size 1768746

SoccerTwos/SoccerTwos-427999965.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7b2cc65c81b0da0ab30531897b60536f076d1cb6ce1ef5e819382724078fada
+size 28430147

SoccerTwos/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b66ac45b76080314ee19f1879476dcc955fbb86da304293a8c453a5fef463b6
+size 28428927

SoccerTwos/events.out.tfevents.1678891688.DESKTOP-HNML991.12128.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:380eec32a3116687fd7139b9553c16655b9061d0414258ecb4e8474982111251
+size 36908537

SoccerTwos/events.out.tfevents.1678958177.DESKTOP-HNML991.4920.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3aabf39ca94d0eafcbc24c91ae616493c9c318a03d86191d48059f767070edf2
+size 403120100

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": 100000000, "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.exe", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "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}, "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 +1,82 @@
+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: 100000000
+    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.exe
+  env_args: null
+  base_port: 5005
+  num_envs: 1
+  num_areas: 1
+  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
+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 +1,40 @@
+Mono path[0] = 'L:/!!!AI/Curs huggingface RL/Unit_7_v1/ml-agents/training-envs-executables/SoccerTwos/SoccerTwos_Data/Managed'
+Mono config path = 'L:/!!!AI/Curs huggingface RL/Unit_7_v1/ml-agents/training-envs-executables/SoccerTwos/MonoBleedingEdge/etc'
+Initialize engine version: 2021.3.14f1 (eee1884e7226)
+[Subsystems] Discovering subsystems at path L:/!!!AI/Curs huggingface RL/Unit_7_v1/ml-agents/training-envs-executables/SoccerTwos/SoccerTwos_Data/UnitySubsystems
+Forcing GfxDevice: Null
+GfxDevice: creating device client; threaded=0; jobified=0
+NullGfxDevice:
+    Version:  NULL 1.0 [1.0]
+    Renderer: Null Device
+    Vendor:   Unity Technologies
+Begin MonoManager ReloadAssembly
+- Completed reload, in  0.066 seconds
+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: '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: 0.529000 ms
+Registered Communicator in Agent.
+ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)

run_logs/timers.json

@@ -0,0 +1,368 @@
+{
+    "name": "root",
+    "gauges": {
+        "SoccerTwos.Policy.Entropy.mean": {
+            "value": 1.3613641262054443,
+            "min": 1.3411742448806763,
+            "max": 3.2956974506378174,
+            "count": 3602
+        },
+        "SoccerTwos.Policy.Entropy.sum": {
+            "value": 26965.900390625,
+            "min": 20730.64453125,
+            "max": 113570.3515625,
+            "count": 3602
+        },
+        "SoccerTwos.Environment.EpisodeLength.mean": {
+            "value": 60.25925925925926,
+            "min": 37.152671755725194,
+            "max": 999.0,
+            "count": 3602
+        },
+        "SoccerTwos.Environment.EpisodeLength.sum": {
+            "value": 19524.0,
+            "min": 14780.0,
+            "max": 26264.0,
+            "count": 3602
+        },
+        "SoccerTwos.Self-play.ELO.mean": {
+            "value": 1657.6884764709157,
+            "min": 1196.935184936025,
+            "max": 1693.6010200992766,
+            "count": 3598
+        },
+        "SoccerTwos.Self-play.ELO.sum": {
+            "value": 268545.53318828833,
+            "min": 2395.503742810388,
+            "max": 395426.28455575136,
+            "count": 3598
+        },
+        "SoccerTwos.Step.mean": {
+            "value": 36019996.0,
+            "min": 9152.0,
+            "max": 36019996.0,
+            "count": 3602
+        },
+        "SoccerTwos.Step.sum": {
+            "value": 36019996.0,
+            "min": 9152.0,
+            "max": 36019996.0,
+            "count": 3602
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
+            "value": -0.02646617218852043,
+            "min": -0.12825043499469757,
+            "max": 0.16259294748306274,
+            "count": 3602
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
+            "value": -4.287519931793213,
+            "min": -23.33773422241211,
+            "max": 29.429323196411133,
+            "count": 3602
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
+            "value": -0.02755160629749298,
+            "min": -0.12929044663906097,
+            "max": 0.16035780310630798,
+            "count": 3602
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
+            "value": -4.46336030960083,
+            "min": -23.126182556152344,
+            "max": 29.145509719848633,
+            "count": 3602
+        },
+        "SoccerTwos.Environment.CumulativeReward.mean": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 3602
+        },
+        "SoccerTwos.Environment.CumulativeReward.sum": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 3602
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.mean": {
+            "value": -0.06300493817270537,
+            "min": -0.5118799969553948,
+            "max": 0.38358182121406903,
+            "count": 3602
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.sum": {
+            "value": -10.206799983978271,
+            "min": -75.341000020504,
+            "max": 65.22119987010956,
+            "count": 3602
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.mean": {
+            "value": -0.06300493817270537,
+            "min": -0.5118799969553948,
+            "max": 0.38358182121406903,
+            "count": 3602
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.sum": {
+            "value": -10.206799983978271,
+            "min": -75.341000020504,
+            "max": 65.22119987010956,
+            "count": 3602
+        },
+        "SoccerTwos.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 3602
+        },
+        "SoccerTwos.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 3602
+        },
+        "SoccerTwos.Losses.PolicyLoss.mean": {
+            "value": 0.024208955618087204,
+            "min": 0.010381613879386957,
+            "max": 0.02644906841839353,
+            "count": 1747
+        },
+        "SoccerTwos.Losses.PolicyLoss.sum": {
+            "value": 0.024208955618087204,
+            "min": 0.010381613879386957,
+            "max": 0.02644906841839353,
+            "count": 1747
+        },
+        "SoccerTwos.Losses.ValueLoss.mean": {
+            "value": 0.09502252489328385,
+            "min": 0.0008015644780243747,
+            "max": 0.12794513031840324,
+            "count": 1747
+        },
+        "SoccerTwos.Losses.ValueLoss.sum": {
+            "value": 0.09502252489328385,
+            "min": 0.0008015644780243747,
+            "max": 0.12794513031840324,
+            "count": 1747
+        },
+        "SoccerTwos.Losses.BaselineLoss.mean": {
+            "value": 0.09575181355079015,
+            "min": 0.0008083683215469743,
+            "max": 0.13082094714045525,
+            "count": 1747
+        },
+        "SoccerTwos.Losses.BaselineLoss.sum": {
+            "value": 0.09575181355079015,
+            "min": 0.0008083683215469743,
+            "max": 0.13082094714045525,
+            "count": 1747
+        },
+        "SoccerTwos.Policy.LearningRate.mean": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 1747
+        },
+        "SoccerTwos.Policy.LearningRate.sum": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 1747
+        },
+        "SoccerTwos.Policy.Epsilon.mean": {
+            "value": 0.20000000000000007,
+            "min": 0.20000000000000007,
+            "max": 0.20000000000000007,
+            "count": 1747
+        },
+        "SoccerTwos.Policy.Epsilon.sum": {
+            "value": 0.20000000000000007,
+            "min": 0.20000000000000007,
+            "max": 0.20000000000000007,
+            "count": 1747
+        },
+        "SoccerTwos.Policy.Beta.mean": {
+            "value": 0.005000000000000001,
+            "min": 0.005000000000000001,
+            "max": 0.005000000000000001,
+            "count": 1747
+        },
+        "SoccerTwos.Policy.Beta.sum": {
+            "value": 0.005000000000000001,
+            "min": 0.005000000000000001,
+            "max": 0.005000000000000001,
+            "count": 1747
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1678891687",
+        "python_version": "3.9.16 (main, Mar  8 2023, 10:39:24) [MSC v.1916 64 bit (AMD64)]",
+        "command_line_arguments": "C:\\ProgramData\\Anaconda3\\envs\\Unit_7_v1\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --no-graphics",
+        "mlagents_version": "0.31.0.dev0",
+        "mlagents_envs_version": "0.31.0.dev0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "1.13.1+cpu",
+        "numpy_version": "1.21.2",
+        "end_time_seconds": "1678947339"
+    },
+    "total": 55652.2723445,
+    "count": 1,
+    "self": 4.1539450000054785,
+    "children": {
+        "run_training.setup": {
+            "total": 0.04273440000000006,
+            "count": 1,
+            "self": 0.04273440000000006
+        },
+        "TrainerController.start_learning": {
+            "total": 55648.0756651,
+            "count": 1,
+            "self": 31.595731998357223,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 2.9493974999899493,
+                    "count": 181,
+                    "self": 2.9493974999899493
+                },
+                "TrainerController.advance": {
+                    "total": 55613.45954870164,
+                    "count": 2494971,
+                    "self": 29.06726641154819,
+                    "children": {
+                        "env_step": {
+                            "total": 20888.51379739436,
+                            "count": 2494971,
+                            "self": 16634.13684089223,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 4238.250976899165,
+                                    "count": 2494971,
+                                    "self": 167.79678639648273,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 4070.454190502682,
+                                            "count": 4523328,
+                                            "self": 4070.454190502682
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 16.12597960296451,
+                                    "count": 2494970,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 55605.35222459717,
+                                            "count": 2494970,
+                                            "is_parallel": true,
+                                            "self": 41758.270943694755,
+                                            "children": {
+                                                "steps_from_proto": {
+                                                    "total": 0.16569109998207066,
+                                                    "count": 362,
+                                                    "is_parallel": true,
+                                                    "self": 0.03305700008893364,
+                                                    "children": {
+                                                        "_process_rank_one_or_two_observation": {
+                                                            "total": 0.13263409989313701,
+                                                            "count": 1448,
+                                                            "is_parallel": true,
+                                                            "self": 0.13263409989313701
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 13846.91558980243,
+                                                    "count": 2494970,
+                                                    "is_parallel": true,
+                                                    "self": 665.5670276068831,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 446.81969479831116,
+                                                            "count": 2494970,
+                                                            "is_parallel": true,
+                                                            "self": 446.81969479831116
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 10669.060154700657,
+                                                            "count": 2494970,
+                                                            "is_parallel": true,
+                                                            "self": 10669.060154700657
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 2065.4687126965787,
+                                                            "count": 4989940,
+                                                            "is_parallel": true,
+                                                            "self": 405.50216390756873,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 1659.96654878901,
+                                                                    "count": 19959760,
+                                                                    "is_parallel": true,
+                                                                    "self": 1659.96654878901
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 34695.87848489574,
+                            "count": 2494970,
+                            "self": 206.65146769313287,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 6583.591829502495,
+                                    "count": 2494970,
+                                    "self": 6578.748415902507,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 4.843413599987798,
+                                            "count": 72,
+                                            "self": 4.843413599987798
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 27905.635187700107,
+                                    "count": 1748,
+                                    "self": 2748.502520400274,
+                                    "children": {
+                                        "TorchPOCAOptimizer.update": {
+                                            "total": 25157.132667299833,
+                                            "count": 52440,
+                                            "self": 25157.132667299833
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 1.700005668681115e-06,
+                    "count": 1,
+                    "self": 1.700005668681115e-06
+                },
+                "TrainerController._save_models": {
+                    "total": 0.07098519999999553,
+                    "count": 1,
+                    "self": 0.0037606999976560473,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.06722450000233948,
+                            "count": 1,
+                            "self": 0.06722450000233948
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,66 @@
+{
+    "SoccerTwos": {
+        "checkpoints": [
+            {
+                "steps": 34499942,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-34499942.onnx",
+                "reward": 0.0,
+                "creation_time": 1678944493.3304255,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-34499942.pt"
+                ]
+            },
+            {
+                "steps": 34999990,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-34999990.onnx",
+                "reward": 0.0,
+                "creation_time": 1678945440.9990487,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-34999990.pt"
+                ]
+            },
+            {
+                "steps": 35499956,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-35499956.onnx",
+                "reward": 0.0,
+                "creation_time": 1678946364.6768358,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-35499956.pt"
+                ]
+            },
+            {
+                "steps": 35999970,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-35999970.onnx",
+                "reward": 0.0,
+                "creation_time": 1678947273.3443823,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-35999970.pt"
+                ]
+            },
+            {
+                "steps": 36027514,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-36027514.onnx",
+                "reward": 0.0,
+                "creation_time": 1678947335.2909179,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-36027514.pt"
+                ]
+            }
+        ],
+        "elo": 1656.3287287055173,
+        "final_checkpoint": {
+            "steps": 36027514,
+            "file_path": "results\\SoccerTwos\\SoccerTwos.onnx",
+            "reward": 0.0,
+            "creation_time": 1678947335.2909179,
+            "auxillary_file_paths": [
+                "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-36027514.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "0.31.0.dev0",
+        "torch_version": "1.13.1+cpu"
+    }
+}