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: yumingyi/poca-SoccerTwos-completed
+  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 sha256:91e82b3d67979cade64bc1140d140595082bd29ff3554ad8b7d43466d864b9e8
+size 1773174

SoccerTwos/SoccerTwos-0.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4490905a052182e4dfe5a907137049fcd1654106c435edd2ca66aee0540d07f7
+size 9490063

SoccerTwos/SoccerTwos-48499942.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86a4df1ff03ea40ffe4a5369ab195a835c3c4e75376ee83c2ce89b66701345a5
+size 1773174

SoccerTwos/SoccerTwos-48499942.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:587ebdab5478a552118e5f142a412f163ecf4fc2bff0f80cab2b6fbc41f73f5c
+size 28441601

SoccerTwos/SoccerTwos-48999991.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17f7147112d63b3a71fbabfe67b5d5519860cc471de500a2fffd76c20e16c9fa
+size 1773174

SoccerTwos/SoccerTwos-48999991.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8884f07b7f8c7961d8783748b60d3426d5c9a01aef3d8f73fbdeba8f5f2cafa7
+size 28441601

SoccerTwos/SoccerTwos-49499760.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c6d50aebabfddf01027fe2a9d694ad6685da89c0d8c562a4e68ee0c6b384a93
+size 1773174

SoccerTwos/SoccerTwos-49499760.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99657bffb24a01fc70e23f456cd09f22ccffd6512d6125e4f06c519d06b72d08
+size 28441601

SoccerTwos/SoccerTwos-49999974.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d50c5f3b13fb6c74c1b0682cdd58aa08181ce8c5159134364cabe451b4829e0f
+size 1773174

SoccerTwos/SoccerTwos-49999974.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e52e0fc9d4dc59a67eada58793c05e3e4705f0eba49778c2d68b6015451c64d1
+size 28441601

SoccerTwos/SoccerTwos-50000042.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91e82b3d67979cade64bc1140d140595082bd29ff3554ad8b7d43466d864b9e8
+size 1773174

SoccerTwos/SoccerTwos-50000042.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d5c75d5607dc2020f4f52d46863ba4f9b616c46bf4c032841c244e9eec241ae
+size 28441601

SoccerTwos/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f152a6b2f6c2f3291daaf183b30d219bd859226ab9c416496481bb344f0e5f9c
+size 28440395

SoccerTwos/events.out.tfevents.1680193582.DESKTOP-MLL8BMR.8992.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a979aa422fd8a0cc73ad9e9ef4185fed0bdab97e2f20b5da0d176158882464da
+size 1235

SoccerTwos/events.out.tfevents.1680193674.DESKTOP-MLL8BMR.27764.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41ee78a0b767790206297b4cf9b5f75db393100850af8f6e1e877d633f1156f8
+size 9914443

SoccerTwos/events.out.tfevents.1680228951.DESKTOP-MLL8BMR.21120.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ddd5a8312345adf8c02ec6991f50a90953f279997cd79f65e925633ad58efe8
+size 5139967

SoccerTwos/events.out.tfevents.1680540253.DESKTOP-MLL8BMR.32928.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a05885155b6095af0818ba29d1e0a734e654b32721c13800b18256c3b28bde88
+size 15417777

SoccerTwos/events.out.tfevents.1680621162.DESKTOP-MLL8BMR.38424.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d090983c48292c4b5fd06f6e997160b8ea44d292855c68abcb69a7557772244c
+size 20546399

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": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 500000, "network_settings": {"normalize": true, "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": 20000, "window": 10, "play_against_latest_model_ratio": 0.5, "initial_elo": 1200.0}, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/SoccerTwos.exe", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SoccerTwos", "initialize_from": null, "load_model": false, "resume": 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: linear
+      beta_schedule: linear
+      epsilon_schedule: linear
+    checkpoint_interval: 500000
+    network_settings:
+      normalize: true
+      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: 20000
+      window: 10
+      play_against_latest_model_ratio: 0.5
+      initial_elo: 1200.0
+    behavioral_cloning: null
+env_settings:
+  env_path: ./training-envs-executables/SoccerTwos.exe
+  env_args: null
+  base_port: 5005
+  num_envs: 1
+  num_areas: 1
+  seed: -1
+  max_lifetime_restarts: 10
+  restarts_rate_limit_n: 1
+  restarts_rate_limit_period_s: 60
+engine_settings:
+  width: 84
+  height: 84
+  quality_level: 5
+  time_scale: 20
+  target_frame_rate: -1
+  capture_frame_rate: 60
+  no_graphics: true
+environment_parameters: null
+checkpoint_settings:
+  run_id: SoccerTwos
+  initialize_from: null
+  load_model: false
+  resume: true
+  force: false
+  train_model: false
+  inference: false
+  results_dir: results
+torch_settings:
+  device: null
+debug: false

run_logs/Player-0.log

@@ -0,0 +1,282 @@
+Mono path[0] = 'C:/Users/zhino/Documents/ml-agents/training-envs-executables/SoccerTwos/SoccerTwos_Data/Managed'
+Mono config path = 'C:/Users/zhino/Documents/ml-agents/training-envs-executables/SoccerTwos/MonoBleedingEdge/etc'
+Initialize engine version: 2021.3.14f1 (eee1884e7226)
+[Subsystems] Discovering subsystems at path C:/Users/zhino/Documents/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  3.063 seconds
+ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+Microsoft Media Foundation video decoding to texture disabled: graphics device is Null, only Direct3D 11 and Direct3D 12 (only on desktop) are supported for hardware-accelerated video decoding.
+ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+WARNING: Shader Unsupported: 'Standard (Specular setup)' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
+ERROR: Shader Standard (Specular setup) shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+WARNING: Shader Unsupported: 'Standard (Specular setup)' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
+WARNING: Shader Unsupported: 'Autodesk Interactive' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
+ERROR: Shader Autodesk Interactive shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+WARNING: Shader Unsupported: 'Autodesk Interactive' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
+WARNING: Shader Unsupported: 'Standard' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
+ERROR: Shader Standard shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+WARNING: Shader Unsupported: 'Standard' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
+UnloadTime: 0.763300 ms
+Registered Communicator in Agent.
+ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+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]: 376680 frames, [2.0 MB-4.0 MB]: 1 frames
+      Initial Block Size 4.0 MB
+      Current Block Size 4.0 MB
+      Peak Allocated Bytes 2.0 MB
+      Overflow Count 0
+    [ALLOC_TEMP_Loading.AsyncRead]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 342 B
+      Overflow Count 0
+    [ALLOC_TEMP_Loading.PreloadManager]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 68.0 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 54 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 6]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0.8 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 54 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 54 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 54 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 54 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 54 B
+      Overflow Count 0
+    [ALLOC_TEMP_EnlightenWorker] x 4
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 54 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 54 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 54 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 54 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 54 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 54 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 54 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 54 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 54 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 54 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 54 B
+      Overflow Count 0
+    [ALLOC_TEMP_BatchDeleteObjects]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 54 B
+      Overflow Count 0
+[ALLOC_DEFAULT] Dual Thread Allocator
+  Peak main deferred allocation count 4
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 0.9 MB
+    [ALLOC_DEFAULT_MAIN]
+      Peak usage frame count: [4.0 MB-8.0 MB]: 376681 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]: 376681 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 17.4 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 0.9 MB
+    [ALLOC_GFX_MAIN]
+      Peak usage frame count: [32.0 KB-64.0 KB]: 376680 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]: 376681 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 173.6 KB
+      Peak Large allocation bytes 0 B
+[ALLOC_CACHEOBJECTS] Dual Thread Allocator
+  Peak main deferred allocation count 2
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 0.9 MB
+    [ALLOC_CACHEOBJECTS_MAIN]
+      Peak usage frame count: [0.5 MB-1.0 MB]: 376681 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]: 376680 frames, [2.0 MB-4.0 MB]: 1 frames
+      Requested Block Size 4.0 MB
+      Peak Block count 1
+      Peak Allocated memory 3.2 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 0.9 MB
+    [ALLOC_TYPETREE_MAIN]
+      Peak usage frame count: [0-1.0 KB]: 376681 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]: 376680 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": 0.7768686413764954,
+            "min": 0.745985746383667,
+            "max": 1.0701088905334473,
+            "count": 1999
+        },
+        "SoccerTwos.Policy.Entropy.sum": {
+            "value": 16382.60546875,
+            "min": 12684.986328125,
+            "max": 25907.607421875,
+            "count": 1999
+        },
+        "SoccerTwos.Environment.EpisodeLength.mean": {
+            "value": 84.76785714285714,
+            "min": 50.1958762886598,
+            "max": 112.52272727272727,
+            "count": 1999
+        },
+        "SoccerTwos.Environment.EpisodeLength.sum": {
+            "value": 18988.0,
+            "min": 17220.0,
+            "max": 21732.0,
+            "count": 1999
+        },
+        "SoccerTwos.Self-play.ELO.mean": {
+            "value": 1987.9346337444374,
+            "min": 1869.5285037041028,
+            "max": 2013.078903609272,
+            "count": 1999
+        },
+        "SoccerTwos.Self-play.ELO.sum": {
+            "value": 222648.678979377,
+            "min": 168311.66783287117,
+            "max": 374389.4863463022,
+            "count": 1999
+        },
+        "SoccerTwos.Step.mean": {
+            "value": 49999974.0,
+            "min": 30019888.0,
+            "max": 49999974.0,
+            "count": 1999
+        },
+        "SoccerTwos.Step.sum": {
+            "value": 49999974.0,
+            "min": 30019888.0,
+            "max": 49999974.0,
+            "count": 1999
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
+            "value": -0.04996594786643982,
+            "min": -0.11881507933139801,
+            "max": 0.06556014716625214,
+            "count": 1999
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
+            "value": -5.59618616104126,
+            "min": -19.30434799194336,
+            "max": 10.610092163085938,
+            "count": 1999
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
+            "value": -0.04964723438024521,
+            "min": -0.12096822261810303,
+            "max": 0.06593786925077438,
+            "count": 1999
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
+            "value": -5.560490131378174,
+            "min": -19.694625854492188,
+            "max": 10.696793556213379,
+            "count": 1999
+        },
+        "SoccerTwos.Environment.CumulativeReward.mean": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 1999
+        },
+        "SoccerTwos.Environment.CumulativeReward.sum": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 1999
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.mean": {
+            "value": 0.04753571642296655,
+            "min": -0.4648256424145821,
+            "max": 0.36228292647416027,
+            "count": 1999
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.sum": {
+            "value": 5.324000239372253,
+            "min": -54.3846001625061,
+            "max": 54.51580035686493,
+            "count": 1999
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.mean": {
+            "value": 0.04753571642296655,
+            "min": -0.4648256424145821,
+            "max": 0.36228292647416027,
+            "count": 1999
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.sum": {
+            "value": 5.324000239372253,
+            "min": -54.3846001625061,
+            "max": 54.51580035686493,
+            "count": 1999
+        },
+        "SoccerTwos.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 1999
+        },
+        "SoccerTwos.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 1999
+        },
+        "SoccerTwos.Losses.PolicyLoss.mean": {
+            "value": 0.015121188938307266,
+            "min": 0.009935286655915358,
+            "max": 0.02496404043243577,
+            "count": 969
+        },
+        "SoccerTwos.Losses.PolicyLoss.sum": {
+            "value": 0.015121188938307266,
+            "min": 0.009935286655915358,
+            "max": 0.02496404043243577,
+            "count": 969
+        },
+        "SoccerTwos.Losses.ValueLoss.mean": {
+            "value": 0.08810667023062706,
+            "min": 0.07008897066116333,
+            "max": 0.10451272428035736,
+            "count": 969
+        },
+        "SoccerTwos.Losses.ValueLoss.sum": {
+            "value": 0.08810667023062706,
+            "min": 0.07008897066116333,
+            "max": 0.10451272428035736,
+            "count": 969
+        },
+        "SoccerTwos.Losses.BaselineLoss.mean": {
+            "value": 0.08825410753488541,
+            "min": 0.0703228938082854,
+            "max": 0.10482276603579521,
+            "count": 969
+        },
+        "SoccerTwos.Losses.BaselineLoss.sum": {
+            "value": 0.08825410753488541,
+            "min": 0.0703228938082854,
+            "max": 0.10482276603579521,
+            "count": 969
+        },
+        "SoccerTwos.Policy.LearningRate.mean": {
+            "value": 5.401598202799828e-08,
+            "min": 5.401598202799828e-08,
+            "max": 0.00011981460006181996,
+            "count": 969
+        },
+        "SoccerTwos.Policy.LearningRate.sum": {
+            "value": 5.401598202799828e-08,
+            "min": 5.401598202799828e-08,
+            "max": 0.00011981460006181996,
+            "count": 969
+        },
+        "SoccerTwos.Policy.Epsilon.mean": {
+            "value": 0.10001797199999998,
+            "min": 0.10001797199999998,
+            "max": 0.13993818000000002,
+            "count": 969
+        },
+        "SoccerTwos.Policy.Epsilon.sum": {
+            "value": 0.10001797199999998,
+            "min": 0.10001797199999998,
+            "max": 0.13993818000000002,
+            "count": 969
+        },
+        "SoccerTwos.Policy.Beta.mean": {
+            "value": 1.0896802799999972e-05,
+            "min": 1.0896802799999972e-05,
+            "max": 0.0020029151820000002,
+            "count": 969
+        },
+        "SoccerTwos.Policy.Beta.sum": {
+            "value": 1.0896802799999972e-05,
+            "min": 1.0896802799999972e-05,
+            "max": 0.0020029151820000002,
+            "count": 969
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1680621154",
+        "python_version": "3.9.16 (main, Mar  8 2023, 10:39:24) [MSC v.1916 64 bit (AMD64)]",
+        "command_line_arguments": "C:\\Users\\zhino\\anaconda3\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --no-graphics --resume",
+        "mlagents_version": "0.31.0.dev0",
+        "mlagents_envs_version": "0.31.0.dev0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "2.0.0+cpu",
+        "numpy_version": "1.21.2",
+        "end_time_seconds": "1680712580"
+    },
+    "total": 91427.48632170001,
+    "count": 1,
+    "self": 4.357296700021834,
+    "children": {
+        "run_training.setup": {
+            "total": 0.18372730000000015,
+            "count": 1,
+            "self": 0.18372730000000015
+        },
+        "TrainerController.start_learning": {
+            "total": 91422.94529769999,
+            "count": 1,
+            "self": 44.078786097306875,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 10.51785440005939,
+                    "count": 101,
+                    "self": 10.51785440005939
+                },
+                "TrainerController.advance": {
+                    "total": 91367.79830890262,
+                    "count": 1362511,
+                    "self": 50.125283698624116,
+                    "children": {
+                        "env_step": {
+                            "total": 30388.00301979803,
+                            "count": 1362511,
+                            "self": 23699.272120016056,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 6660.205735787125,
+                                    "count": 1362511,
+                                    "self": 250.8423825823984,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 6409.363353204727,
+                                            "count": 2511242,
+                                            "self": 6409.363353204727
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 28.525163994850033,
+                                    "count": 1362511,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 91349.51480090125,
+                                            "count": 1362511,
+                                            "is_parallel": true,
+                                            "self": 72436.09262670328,
+                                            "children": {
+                                                "steps_from_proto": {
+                                                    "total": 0.2323070000265819,
+                                                    "count": 202,
+                                                    "is_parallel": true,
+                                                    "self": 0.04589619987165072,
+                                                    "children": {
+                                                        "_process_rank_one_or_two_observation": {
+                                                            "total": 0.18641080015493117,
+                                                            "count": 808,
+                                                            "is_parallel": true,
+                                                            "self": 0.18641080015493117
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 18913.189867197947,
+                                                    "count": 1362511,
+                                                    "is_parallel": true,
+                                                    "self": 981.7251171045536,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 771.4416957955397,
+                                                            "count": 1362511,
+                                                            "is_parallel": true,
+                                                            "self": 771.4416957955397
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 14214.444269298623,
+                                                            "count": 1362511,
+                                                            "is_parallel": true,
+                                                            "self": 14214.444269298623
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 2945.5787849992284,
+                                                            "count": 2725022,
+                                                            "is_parallel": true,
+                                                            "self": 608.6948972046598,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 2336.8838877945686,
+                                                                    "count": 10900088,
+                                                                    "is_parallel": true,
+                                                                    "self": 2336.8838877945686
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 60929.67000540597,
+                            "count": 1362511,
+                            "self": 329.38653910589346,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 7150.239786500018,
+                                    "count": 1362511,
+                                    "self": 7138.944608799997,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 11.295177700022123,
+                                            "count": 40,
+                                            "self": 11.295177700022123
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 53450.04367980006,
+                                    "count": 969,
+                                    "self": 3713.3678997005845,
+                                    "children": {
+                                        "TorchPOCAOptimizer.update": {
+                                            "total": 49736.675780099475,
+                                            "count": 29070,
+                                            "self": 49736.675780099475
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 4.4000043999403715e-06,
+                    "count": 1,
+                    "self": 4.4000043999403715e-06
+                },
+                "TrainerController._save_models": {
+                    "total": 0.550343899987638,
+                    "count": 1,
+                    "self": 0.0716307999973651,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.4787130999902729,
+                            "count": 1,
+                            "self": 0.4787130999902729
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,66 @@
+{
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "0.31.0.dev0",
+        "torch_version": "2.0.0+cpu"
+    },
+    "SoccerTwos": {
+        "elo": 1987.9346337444379,
+        "checkpoints": [
+            {
+                "steps": 48499942,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-48499942.onnx",
+                "reward": 0.0,
+                "creation_time": 1680704285.6743095,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-48499942.pt"
+                ]
+            },
+            {
+                "steps": 48999991,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-48999991.onnx",
+                "reward": 0.0,
+                "creation_time": 1680707024.7967222,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-48999991.pt"
+                ]
+            },
+            {
+                "steps": 49499760,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-49499760.onnx",
+                "reward": 0.0,
+                "creation_time": 1680709856.7630062,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-49499760.pt"
+                ]
+            },
+            {
+                "steps": 49999974,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-49999974.onnx",
+                "reward": 0.0,
+                "creation_time": 1680712575.3152504,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-49999974.pt"
+                ]
+            },
+            {
+                "steps": 50000042,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-50000042.onnx",
+                "reward": 0.0,
+                "creation_time": 1680712576.011023,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-50000042.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 50000042,
+            "file_path": "results\\SoccerTwos\\SoccerTwos.onnx",
+            "reward": 0.0,
+            "creation_time": 1680712576.011023,
+            "auxillary_file_paths": [
+                "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-50000042.pt"
+            ]
+        }
+    }
+}