First Push

README.md

@@ -0,0 +1,35 @@
+---
+library_name: ml-agents
+tags:
+- SoccerTwos
+- deep-reinforcement-learning
+- reinforcement-learning
+- ML-Agents-SoccerTwos
+---
+
+  # **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://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/
+
+  We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
+  - A *short tutorial* where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your
+  browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction
+  - A *longer tutorial* to understand how works ML-Agents:
+  https://huggingface.co/learn/deep-rl-course/unit5/introduction
+
+  ### Resume the training
+  ```bash
+  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. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity
+  2. Step 1: Find your model_id: samilcoban/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 sha256:7379b74d4f142f6db7af39b5bb07c57820c9fb8fcc2d891e95fa28d04baf5999
+size 1768747

SoccerTwos/SoccerTwos-16499998.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32c8ccac4ead4126db38896d5189d0fbcb1ac82ee2d229c0cb0298e6c6e44ac6
+size 1768747

SoccerTwos/SoccerTwos-16499998.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28fcff08eb19a5f4b56d229058463f23b5219e8fd286d3eb1996b2a9a197f6ee
+size 28432146

SoccerTwos/SoccerTwos-16999938.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:577b3fc4e9cf099189c3b85c9598641064a0cf7f58dbe702410bb53a90ad48b9
+size 1768747

SoccerTwos/SoccerTwos-16999938.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79cef6226ca6053d902d4c1ba12494697ca1f5fd47a317728c309374b1f24114
+size 28432146

SoccerTwos/SoccerTwos-17499789.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e903e375cd64721d11737d37a8c92303554c374f2961d00f2a5123e80b32e381
+size 1768747

SoccerTwos/SoccerTwos-17499789.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd767001954deccbbe7e423c7502118793387d74c4e7290efb3675c3112ed326
+size 28432146

SoccerTwos/SoccerTwos-17999964.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd599797d80b858cd0853678a2c9b69e53ea6d394eb2fc30c320a30ab075aaee
+size 1768747

SoccerTwos/SoccerTwos-17999964.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3d3797e3aaf5690dee0dca2d1390b491db56b8834c7ad33ab243911c9a089b2
+size 28432146

SoccerTwos/SoccerTwos-18094866.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7379b74d4f142f6db7af39b5bb07c57820c9fb8fcc2d891e95fa28d04baf5999
+size 1768747

SoccerTwos/SoccerTwos-18094866.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2007680dc5fc25c7aae1e7a32420fe2b8b3a3fc43291f72fa4a9880cec62d3d2
+size 28432146

SoccerTwos/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a7a69748d6355ff9a19e02a328007eb62c41f26e07d284c71fd7bf1753f709e
+size 28431030

SoccerTwos/events.out.tfevents.1702575307.Computer.9554.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39d479ff08813c5ef8fb3d68b49edd025df96e0619d10fca89bdbd10d1772799
+size 2429781

SoccerTwos/events.out.tfevents.1702580223.Computer.21339.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b39195680e7e4dda66630eec093948fcac39f36996e55237e75b6bf679fb9d7f
+size 9456757

SoccerTwos/events.out.tfevents.1702612958.Computer.6016.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a7919df1ad6b7387485ce36383d97db05d048527eccaf9544e5e2cd672115e0
+size 1974193

SoccerTwos/events.out.tfevents.1702620134.Computer.5011.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84c69472cd67c0d70fcfb713acf26bc962a8db268cfc20aa01a29cf2bb8d08b4
+size 4492317

config.json

@@ -0,0 +1 @@
+{"default_settings": null, "behaviors": {"SoccerTwos": {"trainer_type": "poca", "hyperparameters": {"batch_size": 2048, "buffer_size": 20480, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "learning_rate_schedule": "constant", "beta_schedule": "constant", "epsilon_schedule": "constant"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 50000000, "time_horizon": 1000, "summary_freq": 10000, "threaded": false, "self_play": {"save_steps": 50000, "team_change": 200000, "swap_steps": 2000, "window": 10, "play_against_latest_model_ratio": 0.5, "initial_elo": 1200.0}, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/SoccerTwos.x86_64", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "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, "no_graphics_monitor": false}, "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": "cuda"}, "debug": false}

configuration.yaml

@@ -0,0 +1,84 @@
+default_settings: null
+behaviors:
+  SoccerTwos:
+    trainer_type: poca
+    hyperparameters:
+      batch_size: 2048
+      buffer_size: 20480
+      learning_rate: 0.0003
+      beta: 0.005
+      epsilon: 0.2
+      lambd: 0.95
+      num_epoch: 3
+      learning_rate_schedule: constant
+      beta_schedule: constant
+      epsilon_schedule: constant
+    checkpoint_interval: 500000
+    network_settings:
+      normalize: false
+      hidden_units: 512
+      num_layers: 2
+      vis_encode_type: simple
+      memory: null
+      goal_conditioning_type: hyper
+      deterministic: false
+    reward_signals:
+      extrinsic:
+        gamma: 0.99
+        strength: 1.0
+        network_settings:
+          normalize: false
+          hidden_units: 128
+          num_layers: 2
+          vis_encode_type: simple
+          memory: null
+          goal_conditioning_type: hyper
+          deterministic: false
+    init_path: null
+    keep_checkpoints: 5
+    even_checkpoints: false
+    max_steps: 50000000
+    time_horizon: 1000
+    summary_freq: 10000
+    threaded: false
+    self_play:
+      save_steps: 50000
+      team_change: 200000
+      swap_steps: 2000
+      window: 10
+      play_against_latest_model_ratio: 0.5
+      initial_elo: 1200.0
+    behavioral_cloning: null
+env_settings:
+  env_path: ./training-envs-executables/SoccerTwos.x86_64
+  env_args: null
+  base_port: 5005
+  num_envs: 1
+  num_areas: 1
+  timeout_wait: 60
+  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
+  no_graphics_monitor: false
+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: cuda
+debug: false

run_logs/Player-0.log

@@ -0,0 +1,304 @@
+Mono path[0] = '/media/samil/hdd/pythonfiles/learn_pytorch/torchRL/ml-agents/training-envs-executables/SoccerTwos_Data/Managed'
+Mono config path = '/media/samil/hdd/pythonfiles/learn_pytorch/torchRL/ml-agents/training-envs-executables/SoccerTwos_Data/MonoBleedingEdge/etc'
+Preloaded 'lib_burst_generated.so'
+Preloaded 'libgrpc_csharp_ext.x64.so'
+Initialize engine version: 2021.3.14f1 (eee1884e7226)
+[Subsystems] Discovering subsystems at path /media/samil/hdd/pythonfiles/learn_pytorch/torchRL/ml-agents/training-envs-executables/SoccerTwos_Data/UnitySubsystems
+Forcing GfxDevice: Null
+GfxDevice: creating device client; threaded=0; jobified=0
+NullGfxDevice:
+    Version:  NULL 1.0 [1.0]
+    Renderer: Null Device
+    Vendor:   Unity Technologies
+Begin MonoManager ReloadAssembly
+- Completed reload, in  0.634 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: 0.565836 ms
+Registered Communicator in Agent.
+ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+requesting resize 84 x 84
+Setting up 6 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]: 82221 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 129 B
+      Overflow Count 0
+    [ALLOC_TEMP_Loading.PreloadManager]
+      Initial Block Size 256.0 KB
+      Current Block Size 300.0 KB
+      Peak Allocated Bytes 249.6 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 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 6
+      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 11
+      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_Job.Worker 9]
+      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 13]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 8]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 7]
+      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 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_Job.Worker 10]
+      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 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]: 82222 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 4.7 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 82222 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]: 82221 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]: 82222 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]: 82222 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]: 82221 frames, [4.0 MB-8.0 MB]: 1 frames
+      Requested Block Size 4.0 MB
+      Peak Block count 2
+      Peak Allocated memory 5.4 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]: 82222 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]: 82221 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 +1,424 @@
+{
+    "name": "root",
+    "gauges": {
+        "SoccerTwos.Policy.Entropy.mean": {
+            "value": 1.5289312601089478,
+            "min": 1.4429744482040405,
+            "max": 1.6524065732955933,
+            "count": 437
+        },
+        "SoccerTwos.Policy.Entropy.sum": {
+            "value": 31508.21484375,
+            "min": 10421.470703125,
+            "max": 36688.703125,
+            "count": 437
+        },
+        "SoccerTwos.Environment.EpisodeLength.mean": {
+            "value": 65.6103896103896,
+            "min": 48.48979591836735,
+            "max": 114.5111111111111,
+            "count": 437
+        },
+        "SoccerTwos.Environment.EpisodeLength.sum": {
+            "value": 20208.0,
+            "min": 4812.0,
+            "max": 21704.0,
+            "count": 437
+        },
+        "SoccerTwos.Self-play.ELO.mean": {
+            "value": 1591.266926676015,
+            "min": 1525.7500144565668,
+            "max": 1634.7649431157508,
+            "count": 437
+        },
+        "SoccerTwos.Self-play.ELO.sum": {
+            "value": 245055.1067081063,
+            "min": 60774.17314216623,
+            "max": 313938.9115618683,
+            "count": 437
+        },
+        "SoccerTwos.Step.mean": {
+            "value": 18089958.0,
+            "min": 13729936.0,
+            "max": 18089958.0,
+            "count": 437
+        },
+        "SoccerTwos.Step.sum": {
+            "value": 18089958.0,
+            "min": 13729936.0,
+            "max": 18089958.0,
+            "count": 437
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
+            "value": 0.007700234651565552,
+            "min": -0.13673512637615204,
+            "max": 0.07944316416978836,
+            "count": 437
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
+            "value": 1.178135871887207,
+            "min": -18.185771942138672,
+            "max": 12.552020072937012,
+            "count": 437
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 0.007211917545646429,
+            "min": -0.13792335987091064,
+            "max": 0.081109918653965,
+            "count": 437
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 1.1034233570098877,
+            "min": -18.343807220458984,
+            "max": 12.815367698669434,
+            "count": 437
+        },
+        "SoccerTwos.Environment.CumulativeReward.mean": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 437
+        },
+        "SoccerTwos.Environment.CumulativeReward.sum": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 437
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.mean": {
+            "value": -0.03309281277500726,
+            "min": -0.3374048784011748,
+            "max": 0.32358507300490763,
+            "count": 437
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.sum": {
+            "value": -5.063200354576111,
+            "min": -55.334400057792664,
+            "max": 43.36039978265762,
+            "count": 437
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.mean": {
+            "value": -0.03309281277500726,
+            "min": -0.3374048784011748,
+            "max": 0.32358507300490763,
+            "count": 437
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.sum": {
+            "value": -5.063200354576111,
+            "min": -55.334400057792664,
+            "max": 43.36039978265762,
+            "count": 437
+        },
+        "SoccerTwos.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 437
+        },
+        "SoccerTwos.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 437
+        },
+        "SoccerTwos.Losses.PolicyLoss.mean": {
+            "value": 0.019048793388841054,
+            "min": 0.01202231189866628,
+            "max": 0.023315804599163433,
+            "count": 211
+        },
+        "SoccerTwos.Losses.PolicyLoss.sum": {
+            "value": 0.019048793388841054,
+            "min": 0.01202231189866628,
+            "max": 0.023315804599163433,
+            "count": 211
+        },
+        "SoccerTwos.Losses.ValueLoss.mean": {
+            "value": 0.10422521059711774,
+            "min": 0.07008710379401843,
+            "max": 0.10756902545690536,
+            "count": 211
+        },
+        "SoccerTwos.Losses.ValueLoss.sum": {
+            "value": 0.10422521059711774,
+            "min": 0.07008710379401843,
+            "max": 0.10756902545690536,
+            "count": 211
+        },
+        "SoccerTwos.Losses.BaselineLoss.mean": {
+            "value": 0.10599818527698517,
+            "min": 0.07135874889791012,
+            "max": 0.10912942091623942,
+            "count": 211
+        },
+        "SoccerTwos.Losses.BaselineLoss.sum": {
+            "value": 0.10599818527698517,
+            "min": 0.07135874889791012,
+            "max": 0.10912942091623942,
+            "count": 211
+        },
+        "SoccerTwos.Policy.LearningRate.mean": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 211
+        },
+        "SoccerTwos.Policy.LearningRate.sum": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 211
+        },
+        "SoccerTwos.Policy.Epsilon.mean": {
+            "value": 0.20000000000000007,
+            "min": 0.20000000000000007,
+            "max": 0.20000000000000007,
+            "count": 211
+        },
+        "SoccerTwos.Policy.Epsilon.sum": {
+            "value": 0.20000000000000007,
+            "min": 0.20000000000000007,
+            "max": 0.20000000000000007,
+            "count": 211
+        },
+        "SoccerTwos.Policy.Beta.mean": {
+            "value": 0.005000000000000001,
+            "min": 0.005000000000000001,
+            "max": 0.005000000000000001,
+            "count": 211
+        },
+        "SoccerTwos.Policy.Beta.sum": {
+            "value": 0.005000000000000001,
+            "min": 0.005000000000000001,
+            "max": 0.005000000000000001,
+            "count": 211
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1702620132",
+        "python_version": "3.10.12 (main, Jul  5 2023, 18:54:27) [GCC 11.2.0]",
+        "command_line_arguments": "/home/samil/anaconda3/envs/unity/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --resume --torch-device cuda",
+        "mlagents_version": "1.1.0.dev0",
+        "mlagents_envs_version": "1.1.0.dev0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "2.1.1+cu121",
+        "numpy_version": "1.23.5",
+        "end_time_seconds": "1702627737"
+    },
+    "total": 7605.147426823,
+    "count": 1,
+    "self": 0.42629649300033634,
+    "children": {
+        "run_training.setup": {
+            "total": 0.044025450999995996,
+            "count": 1,
+            "self": 0.044025450999995996
+        },
+        "TrainerController.start_learning": {
+            "total": 7604.677104879,
+            "count": 1,
+            "self": 6.384801841059016,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 3.543140044001973,
+                    "count": 23,
+                    "self": 3.543140044001973
+                },
+                "TrainerController.advance": {
+                    "total": 7594.35423294594,
+                    "count": 299615,
+                    "self": 6.412759897923934,
+                    "children": {
+                        "env_step": {
+                            "total": 5653.755548863008,
+                            "count": 299615,
+                            "self": 4278.739194771819,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 1370.8643595179715,
+                                    "count": 299615,
+                                    "self": 35.6024519718776,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 1335.2619075460939,
+                                            "count": 548149,
+                                            "self": 1335.2619075460939
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 4.151994573217664,
+                                    "count": 299614,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 7596.223032310018,
+                                            "count": 299614,
+                                            "is_parallel": true,
+                                            "self": 4014.40834585581,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.0025739310000005844,
+                                                            "count": 2,
+                                                            "is_parallel": true,
+                                                            "self": 0.001017920999998978,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.0015560100000016064,
+                                                                    "count": 8,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0015560100000016064
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.02281602400000793,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0005066710000249941,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.0003378149999946345,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0003378149999946345
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.02049500199998988,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.02049500199998988
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.0014765359999984184,
+                                                                    "count": 2,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0002987140000243471,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.0011778219999740713,
+                                                                            "count": 8,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.0011778219999740713
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "steps_from_proto": {
+                                                    "total": 0.03414245899863033,
+                                                    "count": 44,
+                                                    "is_parallel": true,
+                                                    "self": 0.006506948000961188,
+                                                    "children": {
+                                                        "_process_rank_one_or_two_observation": {
+                                                            "total": 0.027635510997669144,
+                                                            "count": 176,
+                                                            "is_parallel": true,
+                                                            "self": 0.027635510997669144
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 3581.78054399521,
+                                                    "count": 299613,
+                                                    "is_parallel": true,
+                                                    "self": 196.83538217598698,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 106.80310568586641,
+                                                            "count": 299613,
+                                                            "is_parallel": true,
+                                                            "self": 106.80310568586641
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 2738.338005463118,
+                                                            "count": 299613,
+                                                            "is_parallel": true,
+                                                            "self": 2738.338005463118
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 539.8040506702387,
+                                                            "count": 599226,
+                                                            "is_parallel": true,
+                                                            "self": 100.28991740625202,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 439.51413326398665,
+                                                                    "count": 2396904,
+                                                                    "is_parallel": true,
+                                                                    "self": 439.51413326398665
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 1934.1859241850077,
+                            "count": 299614,
+                            "self": 41.93469052002342,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 736.4015649759863,
+                                    "count": 299614,
+                                    "self": 733.8347796079853,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 2.5667853680009785,
+                                            "count": 9,
+                                            "self": 2.5667853680009785
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 1155.849668688998,
+                                    "count": 211,
+                                    "self": 526.311828841966,
+                                    "children": {
+                                        "TorchPOCAOptimizer.update": {
+                                            "total": 629.537839847032,
+                                            "count": 6330,
+                                            "self": 629.537839847032
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 1.3119997674948536e-06,
+                    "count": 1,
+                    "self": 1.3119997674948536e-06
+                },
+                "TrainerController._save_models": {
+                    "total": 0.3949287359992013,
+                    "count": 1,
+                    "self": 0.0016341169994120719,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.39329461899978924,
+                            "count": 1,
+                            "self": 0.39329461899978924
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,66 @@
+{
+    "SoccerTwos": {
+        "checkpoints": [
+            {
+                "steps": 16499998,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-16499998.onnx",
+                "reward": 0.0,
+                "creation_time": 1702624881.5673628,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-16499998.pt"
+                ]
+            },
+            {
+                "steps": 16999938,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-16999938.onnx",
+                "reward": 0.0,
+                "creation_time": 1702625722.539582,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-16999938.pt"
+                ]
+            },
+            {
+                "steps": 17499789,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-17499789.onnx",
+                "reward": 0.0,
+                "creation_time": 1702626647.25588,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-17499789.pt"
+                ]
+            },
+            {
+                "steps": 17999964,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-17999964.onnx",
+                "reward": 0.0,
+                "creation_time": 1702627571.440824,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-17999964.pt"
+                ]
+            },
+            {
+                "steps": 18094866,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-18094866.onnx",
+                "reward": 0.0,
+                "creation_time": 1702627736.9685683,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-18094866.pt"
+                ]
+            }
+        ],
+        "elo": 1581.3620390143442,
+        "final_checkpoint": {
+            "steps": 18094866,
+            "file_path": "results/SoccerTwos/SoccerTwos.onnx",
+            "reward": 0.0,
+            "creation_time": 1702627736.9685683,
+            "auxillary_file_paths": [
+                "results/SoccerTwos/SoccerTwos/SoccerTwos-18094866.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "1.1.0.dev0",
+        "torch_version": "2.1.1+cu121"
+    }
+}