10M

.DS_Store

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a456159a20ff6fdeee7d7f29208d78be256b9f4e32ceafbd951a279a981b6f95
+size 10244

.gitattributes

@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+.DS_Store filter=lfs diff=lfs merge=lfs -text

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: Nelsonlin0321/poca-SoccerTwos-v4
+  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 sha256:1c53aa38bc707f00a503967470c84ab29826cc48ee25b2ad6582ecb3dc0ede3f
+size 1764633

SoccerTwos/.DS_Store

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb3dfe81d2c0f35e201e4ac3e57d69e106e9b953372190be4d9492c02aac6c91
+size 6148

SoccerTwos/SoccerTwos-109999992.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb0626960d53ef953e8b2779f33c2322fecdcdb2bdf11873ddf41c7393637d9d
+size 1764633

SoccerTwos/SoccerTwos-109999992.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e992efbb4c1c04b92abbf3b6344efb1c87bf0687fd0561d2528eb6015c156444
+size 28421201

SoccerTwos/SoccerTwos-110499995.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:885d61f2932077aa2a8fb3f765139d2f764fc6b3f62d1af771432aee7ec08e07
+size 1764633

SoccerTwos/SoccerTwos-110499995.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:382d54203d079541ce895a0301ac2e74be4955996c8f1228124b12cc212e5c97
+size 28421201

SoccerTwos/SoccerTwos-110524644.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c53aa38bc707f00a503967470c84ab29826cc48ee25b2ad6582ecb3dc0ede3f
+size 1764633

SoccerTwos/SoccerTwos-110524644.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd6772974ba66f4330475aba076419da2d31b21086c18a6b6687b40cf19bd5ac
+size 28421201

SoccerTwos/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd6772974ba66f4330475aba076419da2d31b21086c18a6b6687b40cf19bd5ac
+size 28421201

SoccerTwos/events.out.tfevents.1678709433.Nelsons-Mac-mini.local.91266.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5a9c6837c8c26154396e883f5f453a90de414b575ebd86f1cf7e23a6b4e9f29
+size 20567781

SoccerTwos/events.out.tfevents.1678796733.Nelsons-Mac-mini.local.11611.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be3b65a847ee09b86891835ef20e331b84ea1b0ccc0fc32ba6a90ec7a59bd880
+size 1038960

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": 0.8, "initial_elo": 1200.0}, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/SoccerTwos/SoccerTwos.app", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "seed": 33, "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": true, "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: 0.8
+      initial_elo: 1200.0
+    behavioral_cloning: null
+env_settings:
+  env_path: ./training-envs-executables/SoccerTwos/SoccerTwos.app
+  env_args: null
+  base_port: 5005
+  num_envs: 1
+  num_areas: 1
+  seed: 33
+  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: true
+  force: false
+  train_model: false
+  inference: false
+  results_dir: results
+torch_settings:
+  device: null
+debug: false

run_logs/Player-0.log

@@ -0,0 +1,288 @@
+Mono path[0] = '/Users/nelsonlin/Desktop/WorkSpace/Projects/reinforcement-learning-AIvsAI-SoccerTwos/ml-agents/training-envs-executables/SoccerTwos/SoccerTwos.app/Contents/Resources/Data/Managed'
+Mono config path = '/Users/nelsonlin/Desktop/WorkSpace/Projects/reinforcement-learning-AIvsAI-SoccerTwos/ml-agents/training-envs-executables/SoccerTwos/SoccerTwos.app/Contents/MonoBleedingEdge/etc'
+New input system (experimental) initialized
+Initialize engine version: 2021.3.17f1 (3e8111cac19d)
+[Subsystems] Discovering subsystems at path /Users/nelsonlin/Desktop/WorkSpace/Projects/reinforcement-learning-AIvsAI-SoccerTwos/ml-agents/training-envs-executables/SoccerTwos/SoccerTwos.app/Contents/Resources/Data/UnitySubsystems
+Forcing GfxDevice: Null
+GfxDevice: creating device client; threaded=0; jobified=0
+NullGfxDevice:
+    Version:  NULL 1.0 [1.0]
+    Renderer: Null Device
+    Vendor:   Unity Technologies
+Begin MonoManager ReloadAssembly
+- Completed reload, in  0.057 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: 0.247666 ms
+Registered Communicator in Agent.
+ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+Thread 0x16d177000 may have been prematurely finalized
+Setting up 4 worker threads for Enlighten.
+Memory Statistics:
+[ALLOC_TEMP_TLS] TLS Allocator
+  StackAllocators : 
+    [ALLOC_TEMP_MAIN]
+      Peak usage frame count: [8.0 KB-16.0 KB]: 19073 frames, [2.0 MB-4.0 MB]: 1 frames
+      Initial Block Size 4.0 MB
+      Current Block Size 4.0 MB
+      Peak Allocated Bytes 2.1 MB
+      Overflow Count 0
+    [ALLOC_TEMP_Loading.AsyncRead]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 197 B
+      Overflow Count 0
+    [ALLOC_TEMP_Loading.PreloadManager]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 78.9 KB
+      Overflow Count 4
+    [ALLOC_TEMP_Background Job.Worker 8]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 6]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 0]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 10]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 9]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 5]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 14]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 6]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 4]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0.7 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 3]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 12]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_EnlightenWorker] x 4
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 15]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 1]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 2]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 7]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_AssetGarbageCollectorHelper] x 7
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 5]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 13]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_OSX HID Input]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 1]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 2]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 3]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 11]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 0]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 4]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_BatchDeleteObjects]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+[ALLOC_DEFAULT] Dual Thread Allocator
+  Peak main deferred allocation count 3
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 1.0 MB
+    [ALLOC_DEFAULT_MAIN]
+      Peak usage frame count: [4.0 MB-8.0 MB]: 19074 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 4.9 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 19074 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 17.5 MB
+      Peak Large allocation bytes 16.0 MB
+[ALLOC_TEMP_JOB_1_FRAME]
+  Initial Block Size 2.0 MB
+  Used Block Count 1
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_TEMP_JOB_2_FRAMES]
+  Initial Block Size 2.0 MB
+  Used Block Count 1
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_TEMP_JOB_4_FRAMES (JobTemp)]
+  Initial Block Size 2.0 MB
+  Used Block Count 2
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_TEMP_JOB_ASYNC (Background)]
+  Initial Block Size 1.0 MB
+  Used Block Count 3
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_GFX] Dual Thread Allocator
+  Peak main deferred allocation count 0
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 1.0 MB
+    [ALLOC_GFX_MAIN]
+      Peak usage frame count: [32.0 KB-64.0 KB]: 19073 frames, [64.0 KB-128.0 KB]: 1 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 65.6 KB
+      Peak Large allocation bytes 0 B
+    [ALLOC_GFX_THREAD]
+      Peak usage frame count: [128.0 KB-256.0 KB]: 19074 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 173.5 KB
+      Peak Large allocation bytes 0 B
+[ALLOC_CACHEOBJECTS] Dual Thread Allocator
+  Peak main deferred allocation count 0
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 1.0 MB
+    [ALLOC_CACHEOBJECTS_MAIN]
+      Peak usage frame count: [0.5 MB-1.0 MB]: 19074 frames
+      Requested Block Size 4.0 MB
+      Peak Block count 1
+      Peak Allocated memory 0.6 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_CACHEOBJECTS_THREAD]
+      Peak usage frame count: [0.5 MB-1.0 MB]: 19073 frames, [2.0 MB-4.0 MB]: 1 frames
+      Requested Block Size 4.0 MB
+      Peak Block count 1
+      Peak Allocated memory 3.4 MB
+      Peak Large allocation bytes 0 B
+[ALLOC_TYPETREE] Dual Thread Allocator
+  Peak main deferred allocation count 0
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 1.0 MB
+    [ALLOC_TYPETREE_MAIN]
+      Peak usage frame count: [0-1.0 KB]: 19074 frames
+      Requested Block Size 2.0 MB
+      Peak Block count 1
+      Peak Allocated memory 1.0 KB
+      Peak Large allocation bytes 0 B
+    [ALLOC_TYPETREE_THREAD]
+      Peak usage frame count: [1.0 KB-2.0 KB]: 19073 frames, [2.0 KB-4.0 KB]: 1 frames
+      Requested Block Size 2.0 MB
+      Peak Block count 1
+      Peak Allocated memory 2.2 KB
+      Peak Large allocation bytes 0 B

run_logs/timers.json

@@ -0,0 +1,368 @@
+{
+    "name": "root",
+    "gauges": {
+        "SoccerTwos.Policy.Entropy.mean": {
+            "value": 1.238175868988037,
+            "min": 1.2183680534362793,
+            "max": 1.2994136810302734,
+            "count": 101
+        },
+        "SoccerTwos.Policy.Entropy.sum": {
+            "value": 28606.814453125,
+            "min": 18521.25390625,
+            "max": 29463.525390625,
+            "count": 101
+        },
+        "SoccerTwos.Environment.EpisodeLength.mean": {
+            "value": 64.10126582278481,
+            "min": 47.205882352941174,
+            "max": 97.05660377358491,
+            "count": 101
+        },
+        "SoccerTwos.Environment.EpisodeLength.sum": {
+            "value": 20256.0,
+            "min": 12840.0,
+            "max": 20596.0,
+            "count": 101
+        },
+        "SoccerTwos.Self-play.ELO.mean": {
+            "value": 1383.9251066506235,
+            "min": 1358.2550725855904,
+            "max": 1404.797734279851,
+            "count": 101
+        },
+        "SoccerTwos.Self-play.ELO.sum": {
+            "value": 218660.16685079853,
+            "min": 147654.71552795975,
+            "max": 261406.6746122921,
+            "count": 101
+        },
+        "SoccerTwos.Step.mean": {
+            "value": 110519926.0,
+            "min": 109519968.0,
+            "max": 110519926.0,
+            "count": 101
+        },
+        "SoccerTwos.Step.sum": {
+            "value": 110519926.0,
+            "min": 109519968.0,
+            "max": 110519926.0,
+            "count": 101
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
+            "value": -0.06276094168424606,
+            "min": -0.10081424564123154,
+            "max": 0.07244554162025452,
+            "count": 101
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
+            "value": -9.85346794128418,
+            "min": -15.122137069702148,
+            "max": 10.359712600708008,
+            "count": 101
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
+            "value": -0.06429271399974823,
+            "min": -0.10031350702047348,
+            "max": 0.07440705597400665,
+            "count": 101
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
+            "value": -10.093955993652344,
+            "min": -15.047025680541992,
+            "max": 10.640209197998047,
+            "count": 101
+        },
+        "SoccerTwos.Environment.CumulativeReward.mean": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 101
+        },
+        "SoccerTwos.Environment.CumulativeReward.sum": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 101
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.mean": {
+            "value": -0.12160381921537362,
+            "min": -0.2928708088323937,
+            "max": 0.24230461854201096,
+            "count": 101
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.sum": {
+            "value": -19.09179961681366,
+            "min": -47.15220022201538,
+            "max": 34.4439994096756,
+            "count": 101
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.mean": {
+            "value": -0.12160381921537362,
+            "min": -0.2928708088323937,
+            "max": 0.24230461854201096,
+            "count": 101
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.sum": {
+            "value": -19.09179961681366,
+            "min": -47.15220022201538,
+            "max": 34.4439994096756,
+            "count": 101
+        },
+        "SoccerTwos.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 101
+        },
+        "SoccerTwos.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 101
+        },
+        "SoccerTwos.Losses.PolicyLoss.mean": {
+            "value": 0.018505743145942687,
+            "min": 0.01337819177036484,
+            "max": 0.02388267353720342,
+            "count": 48
+        },
+        "SoccerTwos.Losses.PolicyLoss.sum": {
+            "value": 0.018505743145942687,
+            "min": 0.01337819177036484,
+            "max": 0.02388267353720342,
+            "count": 48
+        },
+        "SoccerTwos.Losses.ValueLoss.mean": {
+            "value": 0.09639366020758947,
+            "min": 0.08254250039656957,
+            "max": 0.10760453740755717,
+            "count": 48
+        },
+        "SoccerTwos.Losses.ValueLoss.sum": {
+            "value": 0.09639366020758947,
+            "min": 0.08254250039656957,
+            "max": 0.10760453740755717,
+            "count": 48
+        },
+        "SoccerTwos.Losses.BaselineLoss.mean": {
+            "value": 0.09725053906440735,
+            "min": 0.08359315171837807,
+            "max": 0.10865442578991254,
+            "count": 48
+        },
+        "SoccerTwos.Losses.BaselineLoss.sum": {
+            "value": 0.09725053906440735,
+            "min": 0.08359315171837807,
+            "max": 0.10865442578991254,
+            "count": 48
+        },
+        "SoccerTwos.Policy.LearningRate.mean": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 48
+        },
+        "SoccerTwos.Policy.LearningRate.sum": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 48
+        },
+        "SoccerTwos.Policy.Epsilon.mean": {
+            "value": 0.20000000000000007,
+            "min": 0.20000000000000007,
+            "max": 0.20000000000000007,
+            "count": 48
+        },
+        "SoccerTwos.Policy.Epsilon.sum": {
+            "value": 0.20000000000000007,
+            "min": 0.20000000000000007,
+            "max": 0.20000000000000007,
+            "count": 48
+        },
+        "SoccerTwos.Policy.Beta.mean": {
+            "value": 0.005000000000000001,
+            "min": 0.005000000000000001,
+            "max": 0.005000000000000001,
+            "count": 48
+        },
+        "SoccerTwos.Policy.Beta.sum": {
+            "value": 0.005000000000000001,
+            "min": 0.005000000000000001,
+            "max": 0.005000000000000001,
+            "count": 48
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1678796732",
+        "python_version": "3.9.6 (default, Oct 18 2022, 12:41:40) \n[Clang 14.0.0 (clang-1400.0.29.202)]",
+        "command_line_arguments": "/Users/nelsonlin/Library/Python/3.9/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.app --run-id=SoccerTwos --no-graphics --seed 33 --resume",
+        "mlagents_version": "0.31.0.dev0",
+        "mlagents_envs_version": "0.31.0.dev0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "1.11.0",
+        "numpy_version": "1.21.2",
+        "end_time_seconds": "1678801203"
+    },
+    "total": 4470.538652374999,
+    "count": 1,
+    "self": 0.15183437499945285,
+    "children": {
+        "run_training.setup": {
+            "total": 0.036698125000000026,
+            "count": 1,
+            "self": 0.036698125000000026
+        },
+        "TrainerController.start_learning": {
+            "total": 4470.350119875,
+            "count": 1,
+            "self": 0.6606429559606113,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 1.5348900419998799,
+                    "count": 7,
+                    "self": 1.5348900419998799
+                },
+                "TrainerController.advance": {
+                    "total": 4468.071898126041,
+                    "count": 69491,
+                    "self": 0.5945881060242755,
+                    "children": {
+                        "env_step": {
+                            "total": 3737.4008349549913,
+                            "count": 69491,
+                            "self": 3644.466079133961,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 92.43297455104795,
+                                    "count": 69491,
+                                    "self": 2.994801659105306,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 89.43817289194264,
+                                            "count": 127162,
+                                            "self": 89.43817289194264
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 0.5017812699820254,
+                                    "count": 69490,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 4467.599752941986,
+                                            "count": 69490,
+                                            "is_parallel": true,
+                                            "self": 910.873527853073,
+                                            "children": {
+                                                "steps_from_proto": {
+                                                    "total": 0.010324335000786666,
+                                                    "count": 14,
+                                                    "is_parallel": true,
+                                                    "self": 0.0012625440006204247,
+                                                    "children": {
+                                                        "_process_rank_one_or_two_observation": {
+                                                            "total": 0.009061791000166242,
+                                                            "count": 56,
+                                                            "is_parallel": true,
+                                                            "self": 0.009061791000166242
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 3556.7159007539117,
+                                                    "count": 69490,
+                                                    "is_parallel": true,
+                                                    "self": 8.655802357777702,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 62.56810803897854,
+                                                            "count": 69490,
+                                                            "is_parallel": true,
+                                                            "self": 62.56810803897854
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 3364.0867828420182,
+                                                            "count": 69490,
+                                                            "is_parallel": true,
+                                                            "self": 3364.0867828420182
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 121.40520751513708,
+                                                            "count": 138980,
+                                                            "is_parallel": true,
+                                                            "self": 13.667138762174588,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 107.73806875296249,
+                                                                    "count": 555920,
+                                                                    "is_parallel": true,
+                                                                    "self": 107.73806875296249
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 730.0764750650255,
+                            "count": 69490,
+                            "self": 5.646705462999307,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 148.00438756002427,
+                                    "count": 69490,
+                                    "self": 147.8085534770246,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 0.1958340829996814,
+                                            "count": 2,
+                                            "self": 0.1958340829996814
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 576.425382042002,
+                                    "count": 49,
+                                    "self": 80.2756632939957,
+                                    "children": {
+                                        "TorchPOCAOptimizer.update": {
+                                            "total": 496.14971874800625,
+                                            "count": 1470,
+                                            "self": 496.14971874800625
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 8.33999365568161e-07,
+                    "count": 1,
+                    "self": 8.33999365568161e-07
+                },
+                "TrainerController._save_models": {
+                    "total": 0.08268791699993017,
+                    "count": 1,
+                    "self": 0.002931125999566575,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.07975679100036359,
+                            "count": 1,
+                            "self": 0.07975679100036359
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,66 @@
+{
+    "SoccerTwos": {
+        "elo": 1380.422555546809,
+        "checkpoints": [
+            {
+                "steps": 50000068,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-50000068.onnx",
+                "reward": 0.0,
+                "creation_time": 1678418882.2481952,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-50000068.pt"
+                ]
+            },
+            {
+                "steps": 50463940,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-50463940.onnx",
+                "reward": 0.0,
+                "creation_time": 1678455667.82228,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-50463940.pt"
+                ]
+            },
+            {
+                "steps": 109999992,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-109999992.onnx",
+                "reward": 0.0,
+                "creation_time": 1678798845.8822742,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-109999992.pt"
+                ]
+            },
+            {
+                "steps": 110499995,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-110499995.onnx",
+                "reward": 0.0,
+                "creation_time": 1678801085.3221078,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-110499995.pt"
+                ]
+            },
+            {
+                "steps": 110524644,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-110524644.onnx",
+                "reward": 0.0,
+                "creation_time": 1678801202.982322,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-110524644.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 110524644,
+            "file_path": "results/SoccerTwos/SoccerTwos.onnx",
+            "reward": 0.0,
+            "creation_time": 1678801202.982322,
+            "auxillary_file_paths": [
+                "results/SoccerTwos/SoccerTwos/SoccerTwos-110524644.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "0.31.0.dev0",
+        "torch_version": "1.11.0"
+    }
+}