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: CzarnyRycerz/poca-SoccerTwos-2
+  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:d3d273c516e886eed753310e73141a6259753744fc510e11bad0c13646b7a4ed
+size 1768746

SoccerTwos/SoccerTwos-1499947.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3548c8ea9104d6a18bcd046914894ba531923e5b0478b5b809d90eda4d4c027a
+size 1768746

SoccerTwos/SoccerTwos-1499947.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:029bccdfefde0fe5bed57fda0c8332a74935650e3db332f2375118e15da20410
+size 28429903

SoccerTwos/SoccerTwos-1999978.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed96e3a230892b9aa0bdb7486167f6262025dc423449584c3106495b8376931b
+size 1768746

SoccerTwos/SoccerTwos-1999978.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83249f0b9216988e8b38e6c624e889ab7ae540a543e78f3283b7fdfd729cd10f
+size 28429903

SoccerTwos/SoccerTwos-2499892.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06523302727c1ffea5a6ab0d2d8789a1ca2c137a865840158cf33822bdb96093
+size 1768746

SoccerTwos/SoccerTwos-2499892.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2f7c2e89d45f995ae973aa9feffb91d4edc20cb9431b62c1ee0a9a9c6925a6a
+size 28429903

SoccerTwos/SoccerTwos-2999941.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3926ea872a431711dc88bbaf54d6c2cd5dc95a0d74d94e4f7c638500ffa58a7f
+size 1768746

SoccerTwos/SoccerTwos-2999941.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b2aa99708fac6cd299f263356c505079b5037af8a8540060df1ee5b43638db1
+size 28429903

SoccerTwos/SoccerTwos-3499956.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f99a9753ed210a63f2803871d97fb017055e1383ffdbe893a9ba59ff039f175
+size 1768746

SoccerTwos/SoccerTwos-3499956.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c12fe98a326b6cbb0c252dac418c7df4590455a8d30f47287e70fc8a053311e0
+size 28429903

SoccerTwos/SoccerTwos-3999986.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:506676d2993fd41f7497cd91fb9fdfb9f0b0fdf09e57016ce5df69e48bd1b4e2
+size 1768746

SoccerTwos/SoccerTwos-3999986.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1dcf8f1906fa9177000136fabd89e20a6a80aabe63e859ed2987d8399498b5f0
+size 28429903

SoccerTwos/SoccerTwos-4499978.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ddcffd7e78913be1040a99f6d7ec8f5942dbb23a8782174696b6f3f6c17e844
+size 1768746

SoccerTwos/SoccerTwos-4499978.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e59bfefffb1c707103fd0eeff5ac4fa0308a8e1e8f303ef7eda89b9233c3697
+size 28429903

SoccerTwos/SoccerTwos-4999868.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b663c6e873b2d410a68548f94ee9c81404b42830e491b75306a4f648114206c4
+size 1768746

SoccerTwos/SoccerTwos-4999868.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9897fc934b37e187c0f6af55bae1109ee1792f4a18463939903a5873cac2d57
+size 28429903

SoccerTwos/SoccerTwos-5000142.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b663c6e873b2d410a68548f94ee9c81404b42830e491b75306a4f648114206c4
+size 1768746

SoccerTwos/SoccerTwos-5000142.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04bbef41cc444d756c66f75da8b714bd9f122c861fa858d3bb97c69c8f721295
+size 28429903

SoccerTwos/SoccerTwos-5062052.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3d273c516e886eed753310e73141a6259753744fc510e11bad0c13646b7a4ed
+size 1768746

SoccerTwos/SoccerTwos-5062052.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be78572496bacf88433dcf973652f2d6da2581c350408e7f9accfa31eeb99bed
+size 28429903

SoccerTwos/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:959e0199e662a2cbfa0f80095d3161f2db0e1e6b3c7a5a5243a6582f503c3b4e
+size 28428927

SoccerTwos/events.out.tfevents.1694245807.DESKTOP-L0G93AV.4372.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86a525ea560d51b726e3eb7a10b472d319a1b88407e0afd85d8c9727b9c43c04
+size 16717

SoccerTwos/events.out.tfevents.1694245960.DESKTOP-L0G93AV.15744.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:680e0ce06682d3ca950092974b1a04aa4b0c65287c16306f9160c94c43bf6f55
+size 873576

SoccerTwos/events.out.tfevents.1694249046.DESKTOP-L0G93AV.11292.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53b17d0c9242b9d40d2c998d543e4102ae0a089b282e68e167c336a6ba9cb249
+size 449732

SoccerTwos/events.out.tfevents.1694251246.DESKTOP-L0G93AV.14016.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e967cc52bb524992378ac478acb5cea0c9cd6fcaa588757076fbe5d40c3ffd6b
+size 8703644

SoccerTwos/events.out.tfevents.1694288077.DESKTOP-L0G93AV.7076.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cca95309c3472f1c2f44339b2355a9c1fcf26511a9bf229e2753cce785416650
+size 123252

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": 10, "even_checkpoints": false, "max_steps": 6000000, "time_horizon": 1000, "summary_freq": 5000, "threaded": false, "self_play": {"save_steps": 50000, "team_change": 200000, "swap_steps": 2000, "window": 10, "play_against_latest_model_ratio": 0.5, "initial_elo": 1200.0}, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/SoccerTwos/SoccerTwos.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: 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: 10
+    even_checkpoints: false
+    max_steps: 6000000
+    time_horizon: 1000
+    summary_freq: 5000
+    threaded: false
+    self_play:
+      save_steps: 50000
+      team_change: 200000
+      swap_steps: 2000
+      window: 10
+      play_against_latest_model_ratio: 0.5
+      initial_elo: 1200.0
+    behavioral_cloning: null
+env_settings:
+  env_path: ./training-envs-executables/SoccerTwos/SoccerTwos.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 +1,262 @@
+Mono path[0] = 'C:/ml-agents-2/training-envs-executables/SoccerTwos/SoccerTwos_Data/Managed'
+Mono config path = 'C:/ml-agents-2/training-envs-executables/SoccerTwos/MonoBleedingEdge/etc'
+Initialize engine version: 2021.3.14f1 (eee1884e7226)
+[Subsystems] Discovering subsystems at path C:/ml-agents-2/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  5.082 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: 0.878600 ms
+Registered Communicator in Agent.
+ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+Setting up 2 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]: 1170 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 282 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_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 0]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0.8 KB
+      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 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_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 2
+      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 3
+      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]: 1171 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 5.1 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 1171 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 17.2 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]: 1170 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]: 1171 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]: 1171 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]: 1170 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]: 1171 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]: 1170 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 +1,361 @@
+{
+    "name": "root",
+    "gauges": {
+        "SoccerTwos.Policy.Entropy.mean": {
+            "value": 1.8755611181259155,
+            "min": 1.8755611181259155,
+            "max": 1.9629061222076416,
+            "count": 12
+        },
+        "SoccerTwos.Policy.Entropy.sum": {
+            "value": 17645.279296875,
+            "min": 15431.09375,
+            "max": 22579.794921875,
+            "count": 12
+        },
+        "SoccerTwos.Environment.EpisodeLength.mean": {
+            "value": 56.372093023255815,
+            "min": 44.236363636363635,
+            "max": 92.18518518518519,
+            "count": 12
+        },
+        "SoccerTwos.Environment.EpisodeLength.sum": {
+            "value": 9696.0,
+            "min": 9384.0,
+            "max": 10228.0,
+            "count": 12
+        },
+        "SoccerTwos.Self-play.ELO.mean": {
+            "value": 1471.2420747520032,
+            "min": 1467.0113626709385,
+            "max": 1472.3702846188985,
+            "count": 12
+        },
+        "SoccerTwos.Self-play.ELO.sum": {
+            "value": 126526.81842867227,
+            "min": 79494.11829521183,
+            "max": 161960.73130807883,
+            "count": 12
+        },
+        "SoccerTwos.Step.mean": {
+            "value": 5059976.0,
+            "min": 5004977.0,
+            "max": 5059976.0,
+            "count": 12
+        },
+        "SoccerTwos.Step.sum": {
+            "value": 5059976.0,
+            "min": 5004977.0,
+            "max": 5059976.0,
+            "count": 12
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
+            "value": -0.03155245631933212,
+            "min": -0.07364168018102646,
+            "max": 0.05369749665260315,
+            "count": 12
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
+            "value": -2.7135112285614014,
+            "min": -6.333184719085693,
+            "max": 4.510589599609375,
+            "count": 12
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
+            "value": -0.028821786865592003,
+            "min": -0.07633186876773834,
+            "max": 0.054833486676216125,
+            "count": 12
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
+            "value": -2.4786736965179443,
+            "min": -6.564540863037109,
+            "max": 4.60601282119751,
+            "count": 12
+        },
+        "SoccerTwos.Environment.CumulativeReward.mean": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 12
+        },
+        "SoccerTwos.Environment.CumulativeReward.sum": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 12
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.mean": {
+            "value": 0.05773721254149149,
+            "min": -0.2546205123265584,
+            "max": 0.29172856892858234,
+            "count": 12
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.sum": {
+            "value": 4.965400278568268,
+            "min": -23.05839991569519,
+            "max": 24.505199790000916,
+            "count": 12
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.mean": {
+            "value": 0.05773721254149149,
+            "min": -0.2546205123265584,
+            "max": 0.29172856892858234,
+            "count": 12
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.sum": {
+            "value": 4.965400278568268,
+            "min": -23.05839991569519,
+            "max": 24.505199790000916,
+            "count": 12
+        },
+        "SoccerTwos.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 12
+        },
+        "SoccerTwos.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 12
+        },
+        "SoccerTwos.Losses.PolicyLoss.mean": {
+            "value": 0.018866196391172707,
+            "min": 0.018561844217280545,
+            "max": 0.018866196391172707,
+            "count": 2
+        },
+        "SoccerTwos.Losses.PolicyLoss.sum": {
+            "value": 0.018866196391172707,
+            "min": 0.018561844217280545,
+            "max": 0.018866196391172707,
+            "count": 2
+        },
+        "SoccerTwos.Losses.ValueLoss.mean": {
+            "value": 0.1034101811548074,
+            "min": 0.1034101811548074,
+            "max": 0.10705579469601313,
+            "count": 2
+        },
+        "SoccerTwos.Losses.ValueLoss.sum": {
+            "value": 0.1034101811548074,
+            "min": 0.1034101811548074,
+            "max": 0.10705579469601313,
+            "count": 2
+        },
+        "SoccerTwos.Losses.BaselineLoss.mean": {
+            "value": 0.10521998926997185,
+            "min": 0.10521998926997185,
+            "max": 0.10900999580820402,
+            "count": 2
+        },
+        "SoccerTwos.Losses.BaselineLoss.sum": {
+            "value": 0.10521998926997185,
+            "min": 0.10521998926997185,
+            "max": 0.10900999580820402,
+            "count": 2
+        },
+        "SoccerTwos.Policy.LearningRate.mean": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 2
+        },
+        "SoccerTwos.Policy.LearningRate.sum": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 2
+        },
+        "SoccerTwos.Policy.Epsilon.mean": {
+            "value": 0.20000000000000007,
+            "min": 0.20000000000000007,
+            "max": 0.20000000000000007,
+            "count": 2
+        },
+        "SoccerTwos.Policy.Epsilon.sum": {
+            "value": 0.20000000000000007,
+            "min": 0.20000000000000007,
+            "max": 0.20000000000000007,
+            "count": 2
+        },
+        "SoccerTwos.Policy.Beta.mean": {
+            "value": 0.005000000000000001,
+            "min": 0.005000000000000001,
+            "max": 0.005000000000000001,
+            "count": 2
+        },
+        "SoccerTwos.Policy.Beta.sum": {
+            "value": 0.005000000000000001,
+            "min": 0.005000000000000001,
+            "max": 0.005000000000000001,
+            "count": 2
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1694288067",
+        "python_version": "3.9.17 (main, Jul  5 2023, 20:47:11) [MSC v.1916 64 bit (AMD64)]",
+        "command_line_arguments": "\\\\?\\F:\\ProgramData\\anaconda3\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/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": "2.0.1+cpu",
+        "numpy_version": "1.21.2",
+        "end_time_seconds": "1694288370"
+    },
+    "total": 302.9526163,
+    "count": 1,
+    "self": 0.1316006999999786,
+    "children": {
+        "run_training.setup": {
+            "total": 0.14559349999999993,
+            "count": 1,
+            "self": 0.14559349999999993
+        },
+        "TrainerController.start_learning": {
+            "total": 302.6754221,
+            "count": 1,
+            "self": 0.13936549999971248,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 10.2101864,
+                    "count": 2,
+                    "self": 10.2101864
+                },
+                "TrainerController.advance": {
+                    "total": 292.07503860000025,
+                    "count": 4316,
+                    "self": 0.13155329999949572,
+                    "children": {
+                        "env_step": {
+                            "total": 96.87484390000049,
+                            "count": 4316,
+                            "self": 70.49217279999837,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 26.30355280000162,
+                                    "count": 4316,
+                                    "self": 1.0515914000035202,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 25.2519613999981,
+                                            "count": 7804,
+                                            "self": 25.2519613999981
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 0.0791183000005038,
+                                    "count": 4316,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 255.5749684000001,
+                                            "count": 4316,
+                                            "is_parallel": true,
+                                            "self": 200.75236169999954,
+                                            "children": {
+                                                "steps_from_proto": {
+                                                    "total": 0.0049770999999996235,
+                                                    "count": 4,
+                                                    "is_parallel": true,
+                                                    "self": 0.0010962999999986067,
+                                                    "children": {
+                                                        "_process_rank_one_or_two_observation": {
+                                                            "total": 0.0038808000000010168,
+                                                            "count": 16,
+                                                            "is_parallel": true,
+                                                            "self": 0.0038808000000010168
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 54.817629600000565,
+                                                    "count": 4316,
+                                                    "is_parallel": true,
+                                                    "self": 2.907856100001787,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 3.0367378000002354,
+                                                            "count": 4316,
+                                                            "is_parallel": true,
+                                                            "self": 3.0367378000002354
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 39.23678789999935,
+                                                            "count": 4316,
+                                                            "is_parallel": true,
+                                                            "self": 39.23678789999935
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 9.636247799999198,
+                                                            "count": 8632,
+                                                            "is_parallel": true,
+                                                            "self": 2.1300928000013375,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 7.506154999997861,
+                                                                    "count": 34528,
+                                                                    "is_parallel": true,
+                                                                    "self": 7.506154999997861
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 195.06864140000027,
+                            "count": 4316,
+                            "self": 0.8827934999994227,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 34.76580950000083,
+                                    "count": 4316,
+                                    "self": 34.76580950000083
+                                },
+                                "_update_policy": {
+                                    "total": 159.4200384,
+                                    "count": 3,
+                                    "self": 14.080173999999772,
+                                    "children": {
+                                        "TorchPOCAOptimizer.update": {
+                                            "total": 145.33986440000024,
+                                            "count": 77,
+                                            "self": 145.33986440000024
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 1.499999996212864e-06,
+                    "count": 1,
+                    "self": 1.499999996212864e-06
+                },
+                "TrainerController._save_models": {
+                    "total": 0.25083010000003014,
+                    "count": 1,
+                    "self": 0.010249900000019352,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.2405802000000108,
+                            "count": 1,
+                            "self": 0.2405802000000108
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,111 @@
+{
+    "SoccerTwos": {
+        "elo": 1470.634980277678,
+        "checkpoints": [
+            {
+                "steps": 1499947,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-1499947.onnx",
+                "reward": 0.0,
+                "creation_time": 1694255651.8499525,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-1499947.pt"
+                ]
+            },
+            {
+                "steps": 1999978,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-1999978.onnx",
+                "reward": 0.0,
+                "creation_time": 1694258174.1589022,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-1999978.pt"
+                ]
+            },
+            {
+                "steps": 2499892,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-2499892.onnx",
+                "reward": 0.0,
+                "creation_time": 1694260708.7348855,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-2499892.pt"
+                ]
+            },
+            {
+                "steps": 2999941,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-2999941.onnx",
+                "reward": 0.0,
+                "creation_time": 1694263272.796274,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-2999941.pt"
+                ]
+            },
+            {
+                "steps": 3499956,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-3499956.onnx",
+                "reward": 0.0,
+                "creation_time": 1694265776.804768,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-3499956.pt"
+                ]
+            },
+            {
+                "steps": 3999986,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-3999986.onnx",
+                "reward": 0.0,
+                "creation_time": 1694268278.668395,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-3999986.pt"
+                ]
+            },
+            {
+                "steps": 4499978,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-4499978.onnx",
+                "reward": 0.0,
+                "creation_time": 1694270779.62449,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-4499978.pt"
+                ]
+            },
+            {
+                "steps": 4999868,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-4999868.onnx",
+                "reward": 0.0,
+                "creation_time": 1694273335.165618,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-4999868.pt"
+                ]
+            },
+            {
+                "steps": 5000142,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-5000142.onnx",
+                "reward": 0.0,
+                "creation_time": 1694273335.4434474,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-5000142.pt"
+                ]
+            },
+            {
+                "steps": 5062052,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-5062052.onnx",
+                "reward": null,
+                "creation_time": 1694288369.90915,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-5062052.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 5062052,
+            "file_path": "results\\SoccerTwos\\SoccerTwos.onnx",
+            "reward": null,
+            "creation_time": 1694288369.90915,
+            "auxillary_file_paths": [
+                "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-5062052.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "0.31.0.dev0",
+        "torch_version": "2.0.1+cpu"
+    }
+}