First Push

.DS_Store

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36d0efa8d6459a6e00ef8a50f78591e8ffbe66144d9c3d70d1cc9d5b1ada01de
+size 6148

.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: jinhu2659/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:eefa81fce578cf490cab4e6d3daf2f4ea1fc8ff7bbbeade4b69c0a9e776d18c5
+size 1764633

SoccerTwos/SoccerTwos-19988.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f24fe4715ee6e2e7bb454ab5fca8aa27e6223f597a13fd90a040f5a5400c5cfc
+size 1764633

SoccerTwos/SoccerTwos-19988.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a0fa6dd5a3fb7d18732649d0ef0a0b31571db4875b78a37b1e3953a07b60b08
+size 28421201

SoccerTwos/SoccerTwos-39922.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c63356a2fa2188e17c8f95f1e85aab5cd88481cb9210d911603985547b29d50
+size 1764633

SoccerTwos/SoccerTwos-39922.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42b67ecd3ca7a54cb4aed4db18e8a90b6c5607df4774a4c43fc4d3629ef6a771
+size 28421201

SoccerTwos/SoccerTwos-59889.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89c5d95a4c8c924da214475bbc957cf3a760e75eeaa855852f68c6a9e297a04d
+size 1764633

SoccerTwos/SoccerTwos-59889.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb18a374d902feeac1270586ee7fc2a23c96fe3f6fca18e4d6d7b83639e12c6e
+size 28421201

SoccerTwos/SoccerTwos-79694.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eefa81fce578cf490cab4e6d3daf2f4ea1fc8ff7bbbeade4b69c0a9e776d18c5
+size 1764633

SoccerTwos/SoccerTwos-79694.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6dd434577c43bb560a5d109a7ba7d850ec9f0aade6f2c869864620bca85f7093
+size 28421201

SoccerTwos/SoccerTwos-90250.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58beea8bcd0ab5dd95948b5575a9d6344f287b72167ec8bff92e1adce6aded1f
+size 1764633

SoccerTwos/SoccerTwos-90250.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59feb3ce44283a6c49d9d11823fd33573567cd66f32d09564202a172e3a363c1
+size 28421201

SoccerTwos/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59feb3ce44283a6c49d9d11823fd33573567cd66f32d09564202a172e3a363c1
+size 28421201

SoccerTwos/events.out.tfevents.1678028980.Mac-mini.lan.26782.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56438fcea6859cc5f05bf125238e640d8926531aafccc51229d9a4701e82dc3a
+size 94874

config.json

@@ -0,0 +1 @@
+{"default_settings": null, "behaviors": {"SoccerTwos": {"trainer_type": "poca", "hyperparameters": {"batch_size": 1024, "buffer_size": 10240, "learning_rate": 3e-05, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "learning_rate_schedule": "constant", "beta_schedule": "constant", "epsilon_schedule": "constant"}, "checkpoint_interval": 20000, "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": "./trainedAgent/checkpoint.pt", "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 90000, "time_horizon": 1000, "summary_freq": 10000, "threaded": false, "self_play": {"save_steps": 200000, "team_change": 200000, "swap_steps": 200000, "window": 3, "play_against_latest_model_ratio": 0.001, "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": -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: 1024
+      buffer_size: 10240
+      learning_rate: 3.0e-05
+      beta: 0.005
+      epsilon: 0.2
+      lambd: 0.95
+      num_epoch: 3
+      learning_rate_schedule: constant
+      beta_schedule: constant
+      epsilon_schedule: constant
+    checkpoint_interval: 20000
+    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: ./trainedAgent/checkpoint.pt
+    keep_checkpoints: 5
+    even_checkpoints: false
+    max_steps: 90000
+    time_horizon: 1000
+    summary_freq: 10000
+    threaded: false
+    self_play:
+      save_steps: 200000
+      team_change: 200000
+      swap_steps: 200000
+      window: 3
+      play_against_latest_model_ratio: 0.001
+      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: -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 +1,288 @@
+Mono path[0] = '/Users/jinn/Downloads/tmpEnv/ml-agents/training-envs-executables/SoccerTwos/SoccerTwos.app/Contents/Resources/Data/Managed'
+Mono config path = '/Users/jinn/Downloads/tmpEnv/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/jinn/Downloads/tmpEnv/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  0.067 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: 1.072875 ms
+Registered Communicator in Agent.
+ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+Thread 0x16ce37000 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]: 1706 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 141 B
+      Overflow Count 0
+    [ALLOC_TEMP_Loading.PreloadManager]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 78.8 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 0.7 KB
+      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 B
+      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 2
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 1.1 MB
+    [ALLOC_DEFAULT_MAIN]
+      Peak usage frame count: [4.0 MB-8.0 MB]: 1707 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]: 1707 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 1.1 MB
+    [ALLOC_GFX_MAIN]
+      Peak usage frame count: [32.0 KB-64.0 KB]: 1706 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]: 1707 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 1.1 MB
+    [ALLOC_CACHEOBJECTS_MAIN]
+      Peak usage frame count: [0.5 MB-1.0 MB]: 1707 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]: 1706 frames, [2.0 MB-4.0 MB]: 1 frames
+      Requested Block Size 4.0 MB
+      Peak Block count 1
+      Peak Allocated memory 3.0 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 1.1 MB
+    [ALLOC_TYPETREE_MAIN]
+      Peak usage frame count: [0-1.0 KB]: 1707 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]: 1706 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": 0.39695820212364197,
+            "min": 0.38180339336395264,
+            "max": 0.39923664927482605,
+            "count": 9
+        },
+        "SoccerTwos.Policy.Entropy.sum": {
+            "value": 8332.9462890625,
+            "min": 7154.32080078125,
+            "max": 8454.654296875,
+            "count": 9
+        },
+        "SoccerTwos.Environment.EpisodeLength.mean": {
+            "value": 62.27160493827161,
+            "min": 49.888888888888886,
+            "max": 69.35211267605634,
+            "count": 9
+        },
+        "SoccerTwos.Environment.EpisodeLength.sum": {
+            "value": 20176.0,
+            "min": 19224.0,
+            "max": 20176.0,
+            "count": 9
+        },
+        "SoccerTwos.Self-play.ELO.mean": {
+            "value": 1218.9244261022736,
+            "min": 1198.1883022708387,
+            "max": 1219.3393362294287,
+            "count": 9
+        },
+        "SoccerTwos.Self-play.ELO.sum": {
+            "value": 197465.75702856833,
+            "min": 170382.24554465187,
+            "max": 237282.94107725695,
+            "count": 9
+        },
+        "SoccerTwos.Step.mean": {
+            "value": 89976.0,
+            "min": 9972.0,
+            "max": 89976.0,
+            "count": 9
+        },
+        "SoccerTwos.Step.sum": {
+            "value": 89976.0,
+            "min": 9972.0,
+            "max": 89976.0,
+            "count": 9
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
+            "value": 0.043504662811756134,
+            "min": -0.046195726841688156,
+            "max": 0.052038975059986115,
+            "count": 9
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
+            "value": 7.004250526428223,
+            "min": -9.054362297058105,
+            "max": 8.378274917602539,
+            "count": 9
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 0.04345454275608063,
+            "min": -0.04577525705099106,
+            "max": 0.05204879492521286,
+            "count": 9
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 6.996181488037109,
+            "min": -8.97195053100586,
+            "max": 8.37985610961914,
+            "count": 9
+        },
+        "SoccerTwos.Environment.CumulativeReward.mean": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 9
+        },
+        "SoccerTwos.Environment.CumulativeReward.sum": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 9
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.mean": {
+            "value": -0.05065590291289809,
+            "min": -0.17446944531467226,
+            "max": 0.16435032498602772,
+            "count": 9
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.sum": {
+            "value": -8.155600368976593,
+            "min": -25.123600125312805,
+            "max": 25.145599722862244,
+            "count": 9
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.mean": {
+            "value": -0.05065590291289809,
+            "min": -0.17446944531467226,
+            "max": 0.16435032498602772,
+            "count": 9
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.sum": {
+            "value": -8.155600368976593,
+            "min": -25.123600125312805,
+            "max": 25.145599722862244,
+            "count": 9
+        },
+        "SoccerTwos.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 9
+        },
+        "SoccerTwos.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 9
+        },
+        "SoccerTwos.Losses.PolicyLoss.mean": {
+            "value": 0.020864922987918057,
+            "min": 0.019463621099324275,
+            "max": 0.03482574524435525,
+            "count": 8
+        },
+        "SoccerTwos.Losses.PolicyLoss.sum": {
+            "value": 0.020864922987918057,
+            "min": 0.019463621099324275,
+            "max": 0.03482574524435525,
+            "count": 8
+        },
+        "SoccerTwos.Losses.ValueLoss.mean": {
+            "value": 0.0992392435669899,
+            "min": 0.09508605897426606,
+            "max": 0.11328349038958549,
+            "count": 8
+        },
+        "SoccerTwos.Losses.ValueLoss.sum": {
+            "value": 0.0992392435669899,
+            "min": 0.09508605897426606,
+            "max": 0.11328349038958549,
+            "count": 8
+        },
+        "SoccerTwos.Losses.BaselineLoss.mean": {
+            "value": 0.09958985447883606,
+            "min": 0.09513062909245491,
+            "max": 0.11373425051569938,
+            "count": 8
+        },
+        "SoccerTwos.Losses.BaselineLoss.sum": {
+            "value": 0.09958985447883606,
+            "min": 0.09513062909245491,
+            "max": 0.11373425051569938,
+            "count": 8
+        },
+        "SoccerTwos.Policy.LearningRate.mean": {
+            "value": 2.9999999999999994e-05,
+            "min": 2.9999999999999994e-05,
+            "max": 2.9999999999999994e-05,
+            "count": 8
+        },
+        "SoccerTwos.Policy.LearningRate.sum": {
+            "value": 2.9999999999999994e-05,
+            "min": 2.9999999999999994e-05,
+            "max": 2.9999999999999994e-05,
+            "count": 8
+        },
+        "SoccerTwos.Policy.Epsilon.mean": {
+            "value": 0.20000000000000007,
+            "min": 0.20000000000000007,
+            "max": 0.20000000000000007,
+            "count": 8
+        },
+        "SoccerTwos.Policy.Epsilon.sum": {
+            "value": 0.20000000000000007,
+            "min": 0.20000000000000007,
+            "max": 0.20000000000000007,
+            "count": 8
+        },
+        "SoccerTwos.Policy.Beta.mean": {
+            "value": 0.005000000000000001,
+            "min": 0.005000000000000001,
+            "max": 0.005000000000000001,
+            "count": 8
+        },
+        "SoccerTwos.Policy.Beta.sum": {
+            "value": 0.005000000000000001,
+            "min": 0.005000000000000001,
+            "max": 0.005000000000000001,
+            "count": 8
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1678028979",
+        "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/jinn/Downloads/tmpEnv/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.app --run-id=SoccerTwos --no-graphics",
+        "mlagents_version": "0.31.0.dev0",
+        "mlagents_envs_version": "0.31.0.dev0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "1.11.0",
+        "numpy_version": "1.21.2",
+        "end_time_seconds": "1678029371"
+    },
+    "total": 392.011704375,
+    "count": 1,
+    "self": 0.28511587400004146,
+    "children": {
+        "run_training.setup": {
+            "total": 0.02166145899999994,
+            "count": 1,
+            "self": 0.02166145899999994
+        },
+        "TrainerController.start_learning": {
+            "total": 391.704927042,
+            "count": 1,
+            "self": 0.06890854200003105,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 1.6307198749999998,
+                    "count": 1,
+                    "self": 1.6307198749999998
+                },
+                "TrainerController.advance": {
+                    "total": 389.9199078329999,
+                    "count": 6286,
+                    "self": 0.05976889300086441,
+                    "children": {
+                        "env_step": {
+                            "total": 325.5466283379995,
+                            "count": 6286,
+                            "self": 316.52240444800134,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 8.977451871001685,
+                                    "count": 6286,
+                                    "self": 0.26497939800278125,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 8.712472472998904,
+                                            "count": 11376,
+                                            "self": 8.712472472998904
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 0.04677201899644334,
+                                    "count": 6286,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 389.89252504699834,
+                                            "count": 6286,
+                                            "is_parallel": true,
+                                            "self": 81.06308022499769,
+                                            "children": {
+                                                "steps_from_proto": {
+                                                    "total": 0.001763792999999847,
+                                                    "count": 2,
+                                                    "is_parallel": true,
+                                                    "self": 0.00022829299999926889,
+                                                    "children": {
+                                                        "_process_rank_one_or_two_observation": {
+                                                            "total": 0.001535500000000578,
+                                                            "count": 8,
+                                                            "is_parallel": true,
+                                                            "self": 0.001535500000000578
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 308.82768102900064,
+                                                    "count": 6286,
+                                                    "is_parallel": true,
+                                                    "self": 0.799413659006575,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 5.497644032997364,
+                                                            "count": 6286,
+                                                            "is_parallel": true,
+                                                            "self": 5.497644032997364
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 291.60044107100003,
+                                                            "count": 6286,
+                                                            "is_parallel": true,
+                                                            "self": 291.60044107100003
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 10.93018226599666,
+                                                            "count": 12572,
+                                                            "is_parallel": true,
+                                                            "self": 1.2131422579930025,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 9.717040008003657,
+                                                                    "count": 50288,
+                                                                    "is_parallel": true,
+                                                                    "self": 9.717040008003657
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 64.31351060199952,
+                            "count": 6286,
+                            "self": 0.5570712559996878,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 13.264635177999853,
+                                    "count": 6286,
+                                    "self": 12.853939261999873,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 0.41069591599998034,
+                                            "count": 4,
+                                            "self": 0.41069591599998034
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 50.49180416799998,
+                                    "count": 8,
+                                    "self": 7.260425048999686,
+                                    "children": {
+                                        "TorchPOCAOptimizer.update": {
+                                            "total": 43.231379119000295,
+                                            "count": 240,
+                                            "self": 43.231379119000295
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 3.7500001326407073e-07,
+                    "count": 1,
+                    "self": 3.7500001326407073e-07
+                },
+                "TrainerController._save_models": {
+                    "total": 0.08539041700004191,
+                    "count": 1,
+                    "self": 0.0007179590000419012,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.084672458,
+                            "count": 1,
+                            "self": 0.084672458
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,66 @@
+{
+    "SoccerTwos": {
+        "checkpoints": [
+            {
+                "steps": 19988,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-19988.onnx",
+                "reward": 0.0,
+                "creation_time": 1678029068.479626,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-19988.pt"
+                ]
+            },
+            {
+                "steps": 39922,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-39922.onnx",
+                "reward": 0.0,
+                "creation_time": 1678029151.815783,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-39922.pt"
+                ]
+            },
+            {
+                "steps": 59889,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-59889.onnx",
+                "reward": 0.0,
+                "creation_time": 1678029239.8125849,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-59889.pt"
+                ]
+            },
+            {
+                "steps": 79694,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-79694.onnx",
+                "reward": 0.0,
+                "creation_time": 1678029325.522742,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-79694.pt"
+                ]
+            },
+            {
+                "steps": 90250,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-90250.onnx",
+                "reward": 0.0,
+                "creation_time": 1678029370.8789802,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-90250.pt"
+                ]
+            }
+        ],
+        "elo": 1210.7361763741353,
+        "final_checkpoint": {
+            "steps": 90250,
+            "file_path": "results/SoccerTwos/SoccerTwos.onnx",
+            "reward": 0.0,
+            "creation_time": 1678029370.8789802,
+            "auxillary_file_paths": [
+                "results/SoccerTwos/SoccerTwos/SoccerTwos-90250.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "0.31.0.dev0",
+        "torch_version": "1.11.0"
+    }
+}