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: peterdamn/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:fb33dfca35dcc3a57edd20b33302a39b72e0d2db47847b12df641bca86cccf68
+size 1764633

SoccerTwos/SoccerTwos-258900.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb33dfca35dcc3a57edd20b33302a39b72e0d2db47847b12df641bca86cccf68
+size 1764633

SoccerTwos/SoccerTwos-258900.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:755a0493fac90b954b0d38e17b549123ec7984838ad96d0abd27b86d8d3e3f6d
+size 28422481

SoccerTwos/SoccerTwos-37999902.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e0657b9aa498ec6910addaca2a748460c27d03cce2c3122cda8cd69f530f06f
+size 1764633

SoccerTwos/SoccerTwos-37999902.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b6f6b70b60060e02dca0ec445798bd4771d00896e34f52110d7ae61e9428478
+size 28422481

SoccerTwos/SoccerTwos-38499992.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5982c1b1a14bbe766c973726f252481aed71fa8a8fc2e692696599363c76bcb7
+size 1764633

SoccerTwos/SoccerTwos-38499992.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb2548ed2c23280e135e1af3dc90e0a485bc64f3d5ade9889c6bf200e59947ca
+size 28422481

SoccerTwos/SoccerTwos-38999882.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34758402b3144ea71f0aa5346c774493ceb8727eb3b2697f1e16cd1bd5ee6f0a
+size 1764633

SoccerTwos/SoccerTwos-38999882.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97a876bedbb8e0b2bab4bfe4ef2c0b0674d685a02a15dd0b16ad059130047408
+size 28422481

SoccerTwos/SoccerTwos-39499852.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3bc67d4ed7702f4198cd2f8a2f28087c9f468ff23d304d3017557454f734f405
+size 1764633

SoccerTwos/SoccerTwos-39499852.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0f7a9f2c45b132599a7674dc4d8a89a4c8f991b306d96d8c2670525215e2702
+size 28422481

SoccerTwos/SoccerTwos-39999997.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9b63c5791c25c5f1986d21070362fc348c8ec55e7bb9df6367c6a8eddd52f27
+size 1764633

SoccerTwos/SoccerTwos-39999997.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8d4aed0c998c17df81bf4ce74ed2b6ac17cf75efcf6eb8708b00edd97b4f42b
+size 28422481

SoccerTwos/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8d4aed0c998c17df81bf4ce74ed2b6ac17cf75efcf6eb8708b00edd97b4f42b
+size 28422481

SoccerTwos/events.out.tfevents.1678898596.monitor-staging.493909.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:750bed3b700d0ef74ce9a5dece17d50e351760a1bee933eb87cdccb9245effae
+size 41003858

config.json

@@ -0,0 +1 @@
+{"default_settings": null, "behaviors": {"SoccerTwos": {"trainer_type": "poca", "hyperparameters": {"batch_size": 2048, "buffer_size": 20480, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "learning_rate_schedule": "constant", "beta_schedule": "constant", "epsilon_schedule": "constant"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 50000000, "time_horizon": 1000, "summary_freq": 10000, "threaded": false, "self_play": {"save_steps": 50000, "team_change": 200000, "swap_steps": 2000, "window": 10, "play_against_latest_model_ratio": 0.5, "initial_elo": 1200.0}, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/SoccerTwos/SoccerTwos.x86_64", "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": true, "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/SoccerTwos.x86_64
+  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: true
+  train_model: false
+  inference: false
+  results_dir: results
+torch_settings:
+  device: null
+debug: false

run_logs/Player-0.log

@@ -0,0 +1,393 @@
+Mono path[0] = '/home/kuan-fu/ml-agents/training-envs-executables/SoccerTwos/SoccerTwos_Data/Managed'
+Mono config path = '/home/kuan-fu/ml-agents/training-envs-executables/SoccerTwos/SoccerTwos_Data/MonoBleedingEdge/etc'
+Preloaded 'lib_burst_generated.so'
+Preloaded 'libgrpc_csharp_ext.x64.so'
+Initialize engine version: 2021.3.14f1 (eee1884e7226)
+[Subsystems] Discovering subsystems at path /home/kuan-fu/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  0.053 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: 0.438518 ms
+Registered Communicator in Agent.
+ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+requesting resize 84 x 84
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+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 +1,417 @@
+{
+    "name": "root",
+    "gauges": {
+        "SoccerTwos.Policy.Entropy.mean": {
+            "value": 3.2042267322540283,
+            "min": 3.196126937866211,
+            "max": 3.29575777053833,
+            "count": 25
+        },
+        "SoccerTwos.Policy.Entropy.sum": {
+            "value": 70954.3984375,
+            "min": 35282.03515625,
+            "max": 105464.25,
+            "count": 25
+        },
+        "SoccerTwos.Environment.EpisodeLength.mean": {
+            "value": 796.3333333333334,
+            "min": 545.3,
+            "max": 999.0,
+            "count": 25
+        },
+        "SoccerTwos.Environment.EpisodeLength.sum": {
+            "value": 19112.0,
+            "min": 14892.0,
+            "max": 26160.0,
+            "count": 25
+        },
+        "SoccerTwos.Self-play.ELO.mean": {
+            "value": 1199.5249689281682,
+            "min": 1197.0046718880833,
+            "max": 1201.9851297759408,
+            "count": 22
+        },
+        "SoccerTwos.Self-play.ELO.sum": {
+            "value": 7197.149813569009,
+            "min": 2394.0093437761666,
+            "max": 14411.90727018202,
+            "count": 22
+        },
+        "SoccerTwos.Step.mean": {
+            "value": 249366.0,
+            "min": 9096.0,
+            "max": 249366.0,
+            "count": 25
+        },
+        "SoccerTwos.Step.sum": {
+            "value": 249366.0,
+            "min": 9096.0,
+            "max": 249366.0,
+            "count": 25
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
+            "value": 0.013986501842737198,
+            "min": 0.009657038375735283,
+            "max": 0.06453952938318253,
+            "count": 25
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
+            "value": 0.16783802211284637,
+            "min": 0.1158844605088234,
+            "max": 0.9675376415252686,
+            "count": 25
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 0.014087402261793613,
+            "min": 0.008834817446768284,
+            "max": 0.06278619915246964,
+            "count": 25
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 0.16904883086681366,
+            "min": 0.1060178130865097,
+            "max": 0.9417929649353027,
+            "count": 25
+        },
+        "SoccerTwos.Environment.CumulativeReward.mean": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 25
+        },
+        "SoccerTwos.Environment.CumulativeReward.sum": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 25
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.mean": {
+            "value": 0.202633336186409,
+            "min": -0.3333333333333333,
+            "max": 0.28265714219638277,
+            "count": 25
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.sum": {
+            "value": 2.431600034236908,
+            "min": -4.0,
+            "max": 3.957199990749359,
+            "count": 25
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.mean": {
+            "value": 0.202633336186409,
+            "min": -0.3333333333333333,
+            "max": 0.28265714219638277,
+            "count": 25
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.sum": {
+            "value": 2.431600034236908,
+            "min": -4.0,
+            "max": 3.957199990749359,
+            "count": 25
+        },
+        "SoccerTwos.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 25
+        },
+        "SoccerTwos.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 25
+        },
+        "SoccerTwos.Losses.PolicyLoss.mean": {
+            "value": 0.018186002262518743,
+            "min": 0.012218670298170763,
+            "max": 0.01822557576621572,
+            "count": 11
+        },
+        "SoccerTwos.Losses.PolicyLoss.sum": {
+            "value": 0.018186002262518743,
+            "min": 0.012218670298170763,
+            "max": 0.01822557576621572,
+            "count": 11
+        },
+        "SoccerTwos.Losses.ValueLoss.mean": {
+            "value": 0.001264232094399631,
+            "min": 0.0008625649594857047,
+            "max": 0.005156221093299488,
+            "count": 11
+        },
+        "SoccerTwos.Losses.ValueLoss.sum": {
+            "value": 0.001264232094399631,
+            "min": 0.0008625649594857047,
+            "max": 0.005156221093299488,
+            "count": 11
+        },
+        "SoccerTwos.Losses.BaselineLoss.mean": {
+            "value": 0.0012761966761900112,
+            "min": 0.0008756408002227545,
+            "max": 0.004928033861021201,
+            "count": 11
+        },
+        "SoccerTwos.Losses.BaselineLoss.sum": {
+            "value": 0.0012761966761900112,
+            "min": 0.0008756408002227545,
+            "max": 0.004928033861021201,
+            "count": 11
+        },
+        "SoccerTwos.Policy.LearningRate.mean": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 11
+        },
+        "SoccerTwos.Policy.LearningRate.sum": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 11
+        },
+        "SoccerTwos.Policy.Epsilon.mean": {
+            "value": 0.20000000000000007,
+            "min": 0.20000000000000007,
+            "max": 0.20000000000000007,
+            "count": 11
+        },
+        "SoccerTwos.Policy.Epsilon.sum": {
+            "value": 0.20000000000000007,
+            "min": 0.20000000000000007,
+            "max": 0.20000000000000007,
+            "count": 11
+        },
+        "SoccerTwos.Policy.Beta.mean": {
+            "value": 0.005000000000000001,
+            "min": 0.005000000000000001,
+            "max": 0.005000000000000001,
+            "count": 11
+        },
+        "SoccerTwos.Policy.Beta.sum": {
+            "value": 0.005000000000000001,
+            "min": 0.005000000000000001,
+            "max": 0.005000000000000001,
+            "count": 11
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1678898257",
+        "python_version": "3.9.16 (main, Mar  8 2023, 14:00:05) \n[GCC 11.2.0]",
+        "command_line_arguments": "/home/kuan-fu/anaconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --force",
+        "mlagents_version": "0.31.0.dev0",
+        "mlagents_envs_version": "0.31.0.dev0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "1.11.0+cu102",
+        "numpy_version": "1.21.2",
+        "end_time_seconds": "1678898561"
+    },
+    "total": 304.3988052122295,
+    "count": 1,
+    "self": 0.10091473907232285,
+    "children": {
+        "run_training.setup": {
+            "total": 0.006784338504076004,
+            "count": 1,
+            "self": 0.006784338504076004
+        },
+        "TrainerController.start_learning": {
+            "total": 304.2911061346531,
+            "count": 1,
+            "self": 0.3095868192613125,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 1.953086320310831,
+                    "count": 2,
+                    "self": 1.953086320310831
+                },
+                "TrainerController.advance": {
+                    "total": 301.86365178599954,
+                    "count": 17044,
+                    "self": 0.295504592359066,
+                    "children": {
+                        "env_step": {
+                            "total": 235.74011680856347,
+                            "count": 17044,
+                            "self": 177.63760925456882,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 57.91266277059913,
+                                    "count": 17044,
+                                    "self": 1.7453923672437668,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 56.16727040335536,
+                                            "count": 33846,
+                                            "self": 56.16727040335536
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 0.1898447833955288,
+                                    "count": 17044,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 301.5095813497901,
+                                            "count": 17044,
+                                            "is_parallel": true,
+                                            "self": 156.7658403813839,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.0018038563430309296,
+                                                            "count": 2,
+                                                            "is_parallel": true,
+                                                            "self": 0.00040678679943084717,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.0013970695436000824,
+                                                                    "count": 8,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0013970695436000824
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.018284153193235397,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.000433310866355896,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.00036272406578063965,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00036272406578063965
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.016151074320077896,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.016151074320077896
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.0013370439410209656,
+                                                                    "count": 2,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00028074905276298523,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.0010562948882579803,
+                                                                            "count": 8,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.0010562948882579803
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 144.74243408814073,
+                                                    "count": 17043,
+                                                    "is_parallel": true,
+                                                    "self": 7.4984940476715565,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 5.627955291420221,
+                                                            "count": 17043,
+                                                            "is_parallel": true,
+                                                            "self": 5.627955291420221
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 108.85295943170786,
+                                                            "count": 17043,
+                                                            "is_parallel": true,
+                                                            "self": 108.85295943170786
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 22.76302531734109,
+                                                            "count": 34086,
+                                                            "is_parallel": true,
+                                                            "self": 4.588412620127201,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 18.174612697213888,
+                                                                    "count": 136344,
+                                                                    "is_parallel": true,
+                                                                    "self": 18.174612697213888
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "steps_from_proto": {
+                                                    "total": 0.0013068802654743195,
+                                                    "count": 2,
+                                                    "is_parallel": true,
+                                                    "self": 0.0002643764019012451,
+                                                    "children": {
+                                                        "_process_rank_one_or_two_observation": {
+                                                            "total": 0.0010425038635730743,
+                                                            "count": 8,
+                                                            "is_parallel": true,
+                                                            "self": 0.0010425038635730743
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 65.828030385077,
+                            "count": 17044,
+                            "self": 2.3353971764445305,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 15.534990962594748,
+                                    "count": 17044,
+                                    "self": 15.534990962594748
+                                },
+                                "_update_policy": {
+                                    "total": 47.95764224603772,
+                                    "count": 12,
+                                    "self": 28.350088000297546,
+                                    "children": {
+                                        "TorchPOCAOptimizer.update": {
+                                            "total": 19.607554245740175,
+                                            "count": 341,
+                                            "self": 19.607554245740175
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 9.94652509689331e-07,
+                    "count": 1,
+                    "self": 9.94652509689331e-07
+                },
+                "TrainerController._save_models": {
+                    "total": 0.16478021442890167,
+                    "count": 1,
+                    "self": 0.0010590888559818268,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.16372112557291985,
+                            "count": 1,
+                            "self": 0.16372112557291985
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,30 @@
+{
+    "SoccerTwos": {
+        "elo": 1199.0327940079324,
+        "checkpoints": [
+            {
+                "steps": 258900,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-258900.onnx",
+                "reward": null,
+                "creation_time": 1678898561.4964812,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-258900.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 258900,
+            "file_path": "results/SoccerTwos/SoccerTwos.onnx",
+            "reward": null,
+            "creation_time": 1678898561.4964812,
+            "auxillary_file_paths": [
+                "results/SoccerTwos/SoccerTwos/SoccerTwos-258900.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "0.31.0.dev0",
+        "torch_version": "1.11.0+cu102"
+    }
+}