Guide: 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: hruslen/poca-SoccerTwos
+  3. Step 2: Select your *.nn /*.onnx file
+  4. Click on Watch the agent play 👀
+  

SoccerTwos/SoccerTwos-1499912.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e1e254b9ae24a316affb39c8ec2d274234c0ba517925dbd01cb5f9ebbf870a1
+size 1768746

SoccerTwos/SoccerTwos-1499912.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4111743cd68fb397e0bec6a8c07fe094ca5a547b1d5882b36f953f2b6d13addd
+size 28429903

SoccerTwos/SoccerTwos-1999722.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7873de4007a25e2014dbde165a837b384126c6b4a8cea54ad3702d5f694bddfe
+size 1768746

SoccerTwos/SoccerTwos-1999722.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:412d8f3beccff03d377af928120904374dd49fe8bd8799b4d37967d11d45a7d3
+size 28429903

SoccerTwos/SoccerTwos-2499793.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43196c81efd347bc4a52920a82567c2b35655eecc0b451d8dc64c01b317383bf
+size 1768746

SoccerTwos/SoccerTwos-2499793.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66dfbc275038fbeb4ed6a0c5637b1ba72b651ade163c8b7a0ab2485de788a905
+size 28429903

SoccerTwos/SoccerTwos-2999820.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af134210cbd04a15db8782ce855c074a7dfc6d39c677e890fc3e7d2ad8270706
+size 1768746

SoccerTwos/SoccerTwos-2999820.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a84cad548a094022878c79ca0a2d743301bd75294d79ad7042460dd012e215e
+size 28429903

SoccerTwos/SoccerTwos-3499876.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea18f886ce4e24021fdd7de0d2840970934dc43f95464daf87f8c655f3453a67
+size 1768746

SoccerTwos/SoccerTwos-3499876.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45da4dce278f96509f7643afe4aeea67be594b94ff7af11b289bd8c428f6b602
+size 28429903

SoccerTwos/SoccerTwos-3499993.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea18f886ce4e24021fdd7de0d2840970934dc43f95464daf87f8c655f3453a67
+size 1768746

SoccerTwos/SoccerTwos-3499993.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea29dee6756db154707190e3ae12b2de1b17685d7e920f2abd2741f401c620ef
+size 28429903

SoccerTwos/SoccerTwos-3999955.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18325c690412432dd3bab7292541347afd37ade42be12d20d1da6042780151a5
+size 1768746

SoccerTwos/SoccerTwos-3999955.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd58537b5c15683c0016eaee0ea37dc3b49144fecbec5a1d98100da5eaf67615
+size 28429903

SoccerTwos/SoccerTwos-4499976.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ec7a1fa53946d22169606d86695579504dbddaa13be44beb54a0554230765
+size 1768746

SoccerTwos/SoccerTwos-4499976.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c2f97f1f76e700e727dde9fc17ce541cad4b483daa39127ed3d4d57e7502161
+size 28429903

SoccerTwos/SoccerTwos-4499998.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ec7a1fa53946d22169606d86695579504dbddaa13be44beb54a0554230765
+size 1768746

SoccerTwos/SoccerTwos-4499998.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d86daf149be77f0b3744cc90edb3202db0a76b7d4d8e885be08f2396cfdebabe
+size 28429903

SoccerTwos/SoccerTwos-499466.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60283c0cc1f7877a16a9c930678d571becf86621c5ec48bb8eff1a12a05f55fa
+size 28429781

SoccerTwos/SoccerTwos-4999980.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f5d1532399db642070a56f82f554820157dd3bbef4a21ea9ea49128764212f0
+size 1768746

SoccerTwos/SoccerTwos-4999980.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30f1c98c55c52e3e0cbee9f39388e9fce903fa746c8bf8bafec2e32a1fefa144
+size 28429903

SoccerTwos/SoccerTwos-5499994.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b0e6f74bb9288ccf967fa6a6c7313dbc36aff1c43dac3ea06a29dd52602e8d0
+size 1768746

SoccerTwos/SoccerTwos-5499994.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75d555ff036b31335735065d80901f51055c905d1b3d38a7b0a198f1176cfab6
+size 28429903

SoccerTwos/SoccerTwos-5999990.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79bc8508d4ca095614d920739f94c93e4218d668e0a26017e90ae36a800d444c
+size 1768746

SoccerTwos/SoccerTwos-5999990.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc319e5ab244e14305591744a9288ae267595b253da234091eef1d3eeaf2683f
+size 28429903

SoccerTwos/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6fb7e1d3b585fc206cdb5cbe5548b2801b3a4ecfe3704d2670332f96efcb048
+size 28428927

SoccerTwos/events.out.tfevents.1685366793.DESKTOP-N831AT2.20188.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d7e393758b768b8cc9cc3a3ab8fa40c597c5b1e6f88fa3692567fbd92c3e0cd
+size 375015

SoccerTwos/events.out.tfevents.1685368489.DESKTOP-N831AT2.2508.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:045a5948502b731424778b1000c9b6e50183caa6b94bfd221aafdc77d0520181
+size 3030953

SoccerTwos/events.out.tfevents.1685462139.DESKTOP-N831AT2.692.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef931d7ca0b47dcac6d6dc02910fe9ff30f1faeb91b9f92a618a71500ed51bff
+size 1080091

SoccerTwos/events.out.tfevents.1685516271.DESKTOP-N831AT2.18264.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21b098946ae908c51ad98a257751d74d51c9b079df8f9f422aef22985f73f4c5
+size 1666858

config.json

@@ -0,0 +1 @@
+{"default_settings": null, "behaviors": {"SoccerTwos": {"trainer_type": "poca", "hyperparameters": {"batch_size": 2048, "buffer_size": 20480, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "learning_rate_schedule": "constant", "beta_schedule": "constant", "epsilon_schedule": "constant"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 50000000, "time_horizon": 1000, "summary_freq": 10000, "threaded": false, "self_play": {"save_steps": 50000, "team_change": 200000, "swap_steps": 2000, "window": 10, "play_against_latest_model_ratio": 0.5, "initial_elo": 1200.0}, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/SoccerTwos.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: 50000000
+    time_horizon: 1000
+    summary_freq: 10000
+    threaded: false
+    self_play:
+      save_steps: 50000
+      team_change: 200000
+      swap_steps: 2000
+      window: 10
+      play_against_latest_model_ratio: 0.5
+      initial_elo: 1200.0
+    behavioral_cloning: null
+env_settings:
+  env_path: ./training-envs-executables/SoccerTwos.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 +1,42 @@
+Mono path[0] = 'D:/OneDrive/Documents/rlhf/ml-agents/training-envs-executables/SoccerTwos/SoccerTwos_Data/Managed'
+Mono config path = 'D:/OneDrive/Documents/rlhf/ml-agents/training-envs-executables/SoccerTwos/MonoBleedingEdge/etc'
+Initialize engine version: 2021.3.14f1 (eee1884e7226)
+[Subsystems] Discovering subsystems at path D:/OneDrive/Documents/rlhf/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 11.613 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: 0.653900 ms
+Registered Communicator in Agent.
+ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+GRPC Exception: Status(StatusCode=Unknown, Detail="Stream removed"). Disconnecting from trainer.
+Setting up 4 worker threads for Enlighten.

run_logs/timers.json

@@ -0,0 +1,363 @@
+{
+    "name": "root",
+    "gauges": {
+        "SoccerTwos.Policy.Entropy.mean": {
+            "value": 3.208897352218628,
+            "min": 3.167426347732544,
+            "max": 3.295755386352539,
+            "count": 50
+        },
+        "SoccerTwos.Policy.Entropy.sum": {
+            "value": 72084.671875,
+            "min": 3157.7578125,
+            "max": 105464.1640625,
+            "count": 50
+        },
+        "SoccerTwos.Environment.EpisodeLength.mean": {
+            "value": 723.8333333333334,
+            "min": 400.5833333333333,
+            "max": 999.0,
+            "count": 50
+        },
+        "SoccerTwos.Environment.EpisodeLength.sum": {
+            "value": 17372.0,
+            "min": 12368.0,
+            "max": 28232.0,
+            "count": 50
+        },
+        "SoccerTwos.Self-play.ELO.mean": {
+            "value": 1215.3275069722,
+            "min": 1198.0140976835446,
+            "max": 1216.0444001507303,
+            "count": 46
+        },
+        "SoccerTwos.Self-play.ELO.sum": {
+            "value": 9722.6200557776,
+            "min": 2396.5239063568742,
+            "max": 19400.876835675528,
+            "count": 46
+        },
+        "SoccerTwos.Step.mean": {
+            "value": 499466.0,
+            "min": 9138.0,
+            "max": 499466.0,
+            "count": 50
+        },
+        "SoccerTwos.Step.sum": {
+            "value": 499466.0,
+            "min": 9138.0,
+            "max": 499466.0,
+            "count": 50
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
+            "value": -0.0007608662126585841,
+            "min": -0.08160314708948135,
+            "max": 0.0031201052479445934,
+            "count": 50
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
+            "value": -0.009891260415315628,
+            "min": -1.3871639966964722,
+            "max": 0.03445547819137573,
+            "count": 50
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
+            "value": -0.0007399116875603795,
+            "min": -0.08157574385404587,
+            "max": 0.0027977179270237684,
+            "count": 50
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
+            "value": -0.009618852287530899,
+            "min": -1.3866405487060547,
+            "max": 0.03021223656833172,
+            "count": 50
+        },
+        "SoccerTwos.Environment.CumulativeReward.mean": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 50
+        },
+        "SoccerTwos.Environment.CumulativeReward.sum": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 50
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.mean": {
+            "value": -0.32898461532134277,
+            "min": -0.4532631559199409,
+            "max": 0.32513333757718405,
+            "count": 50
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.sum": {
+            "value": -4.276799999177456,
+            "min": -8.611999962478876,
+            "max": 7.261200055480003,
+            "count": 50
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.mean": {
+            "value": -0.32898461532134277,
+            "min": -0.4532631559199409,
+            "max": 0.32513333757718405,
+            "count": 50
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.sum": {
+            "value": -4.276799999177456,
+            "min": -8.611999962478876,
+            "max": 7.261200055480003,
+            "count": 50
+        },
+        "SoccerTwos.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 50
+        },
+        "SoccerTwos.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 50
+        },
+        "SoccerTwos.Losses.PolicyLoss.mean": {
+            "value": 0.016160426136048046,
+            "min": 0.013953804352786392,
+            "max": 0.02250218946040453,
+            "count": 23
+        },
+        "SoccerTwos.Losses.PolicyLoss.sum": {
+            "value": 0.016160426136048046,
+            "min": 0.013953804352786392,
+            "max": 0.02250218946040453,
+            "count": 23
+        },
+        "SoccerTwos.Losses.ValueLoss.mean": {
+            "value": 0.0015458971553016453,
+            "min": 0.0005459430918563158,
+            "max": 0.007379330756763617,
+            "count": 23
+        },
+        "SoccerTwos.Losses.ValueLoss.sum": {
+            "value": 0.0015458971553016453,
+            "min": 0.0005459430918563158,
+            "max": 0.007379330756763617,
+            "count": 23
+        },
+        "SoccerTwos.Losses.BaselineLoss.mean": {
+            "value": 0.0015502585699626555,
+            "min": 0.0005527794239848542,
+            "max": 0.007383338843161861,
+            "count": 23
+        },
+        "SoccerTwos.Losses.BaselineLoss.sum": {
+            "value": 0.0015502585699626555,
+            "min": 0.0005527794239848542,
+            "max": 0.007383338843161861,
+            "count": 23
+        },
+        "SoccerTwos.Policy.LearningRate.mean": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 23
+        },
+        "SoccerTwos.Policy.LearningRate.sum": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 23
+        },
+        "SoccerTwos.Policy.Epsilon.mean": {
+            "value": 0.20000000000000007,
+            "min": 0.20000000000000007,
+            "max": 0.20000000000000007,
+            "count": 23
+        },
+        "SoccerTwos.Policy.Epsilon.sum": {
+            "value": 0.20000000000000007,
+            "min": 0.20000000000000007,
+            "max": 0.20000000000000007,
+            "count": 23
+        },
+        "SoccerTwos.Policy.Beta.mean": {
+            "value": 0.005000000000000001,
+            "min": 0.005000000000000001,
+            "max": 0.005000000000000001,
+            "count": 23
+        },
+        "SoccerTwos.Policy.Beta.sum": {
+            "value": 0.005000000000000001,
+            "min": 0.005000000000000001,
+            "max": 0.005000000000000001,
+            "count": 23
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1685366789",
+        "python_version": "3.9.16 (main, Mar  8 2023, 10:39:24) [MSC v.1916 64 bit (AMD64)]",
+        "command_line_arguments": "D:\\Anaconda3\\envs\\rl\\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": "2.0.1+cpu",
+        "numpy_version": "1.21.2",
+        "end_time_seconds": "1685368269"
+    },
+    "total": 1480.7160249,
+    "count": 1,
+    "self": 0.33426360000021305,
+    "children": {
+        "run_training.setup": {
+            "total": 0.20417030000000036,
+            "count": 1,
+            "self": 0.20417030000000036
+        },
+        "TrainerController.start_learning": {
+            "total": 1480.177591,
+            "count": 1,
+            "self": 0.7939259999991464,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 4.3953076000000495,
+                    "count": 3,
+                    "self": 4.3953076000000495
+                },
+                "TrainerController.advance": {
+                    "total": 1474.8158319000008,
+                    "count": 32685,
+                    "self": 0.8752609000316625,
+                    "children": {
+                        "env_step": {
+                            "total": 663.036887699983,
+                            "count": 32685,
+                            "self": 526.0957164999761,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 136.38368390000687,
+                                    "count": 32685,
+                                    "self": 4.607681099998558,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 131.7760028000083,
+                                            "count": 64830,
+                                            "self": 131.7760028000083
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 0.5574873000000959,
+                                    "count": 32685,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 1474.1840769999976,
+                                            "count": 32685,
+                                            "is_parallel": true,
+                                            "self": 1051.4892170999976,
+                                            "children": {
+                                                "steps_from_proto": {
+                                                    "total": 0.00575940000008579,
+                                                    "count": 6,
+                                                    "is_parallel": true,
+                                                    "self": 0.0011389000000932015,
+                                                    "children": {
+                                                        "_process_rank_one_or_two_observation": {
+                                                            "total": 0.004620499999992589,
+                                                            "count": 24,
+                                                            "is_parallel": true,
+                                                            "self": 0.004620499999992589
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 422.6891004999999,
+                                                    "count": 32685,
+                                                    "is_parallel": true,
+                                                    "self": 19.718969899969352,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 18.785363399996477,
+                                                            "count": 32685,
+                                                            "is_parallel": true,
+                                                            "self": 18.785363399996477
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 318.18374580001216,
+                                                            "count": 32685,
+                                                            "is_parallel": true,
+                                                            "self": 318.18374580001216
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 66.00102140002193,
+                                                            "count": 65370,
+                                                            "is_parallel": true,
+                                                            "self": 13.732501200086695,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 52.26852019993523,
+                                                                    "count": 261480,
+                                                                    "is_parallel": true,
+                                                                    "self": 52.26852019993523
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 810.903683299986,
+                            "count": 32685,
+                            "self": 5.57341389999317,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 111.55046469999257,
+                                    "count": 32685,
+                                    "self": 111.3059452999924,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 0.24451940000017203,
+                                            "count": 1,
+                                            "self": 0.24451940000017203
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 693.7798047000002,
+                                    "count": 23,
+                                    "self": 84.76063819999786,
+                                    "children": {
+                                        "TorchPOCAOptimizer.update": {
+                                            "total": 609.0191665000024,
+                                            "count": 690,
+                                            "self": 609.0191665000024
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "TrainerController._save_models": {
+                    "total": 0.17252549999989242,
+                    "count": 1,
+                    "self": 3.2899999951041536e-05,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.17249259999994138,
+                            "count": 1,
+                            "self": 0.17249259999994138
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,10 @@
+{
+    "SoccerTwos": {
+        "elo": 1214.1098823466716
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "0.31.0.dev0",
+        "torch_version": "2.0.1+cpu"
+    }
+}