init

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: unlikezy/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 sha256:36d4f459d8c937c784a469c43c57456f081ab6318d1d257ee1478f35ae10e0f5
+size 1768747

SoccerTwos/SoccerTwos-1999886.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff08516a526c5e286fc7cee6bd2638173d0b6b3d0d2bb53e2895930f9b02280d
+size 1768747

SoccerTwos/SoccerTwos-1999886.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:886c21ec245bbe78f8a17a8613a1f8d3e03126d446c3ccbb7d910fbfcbc4d622
+size 28432022

SoccerTwos/SoccerTwos-2499682.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80f63d5d0096cd87a19045a79a9c2f63f6f3b8c97adfe5502a6ebc1cb73283db
+size 1768747

SoccerTwos/SoccerTwos-2499682.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92756b4e9bce1480d7f90b2810e680093a422ec6038c99f37933693a2ee738fc
+size 28432022

SoccerTwos/SoccerTwos-2999938.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd563e7ca8c18a567e01344ee9fd8b1e7224238f90242ee8a4a5fc153fabc825
+size 1768747

SoccerTwos/SoccerTwos-2999938.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1838a84758b508e6aab6b005f4749ae03a0ba41e27e6ca1bf5cece3ad42d1e97
+size 28432022

SoccerTwos/SoccerTwos-3499876.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d810e7cf17b7f43dc863bef3828cad02648b5931341ad281e0532fec95bddf24
+size 1768747

SoccerTwos/SoccerTwos-3499876.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a76ade539d2e0e8d7bddc634b565bbe56b163515cfc84038fa451e077d71668
+size 28432022

SoccerTwos/SoccerTwos-3999963.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bc37220c4e012694ca3073ad6bf29c027bf58666b157e9213d77b0499621e1a
+size 1768747

SoccerTwos/SoccerTwos-3999963.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4cab536b88aadc6a12c794ba9167a1943018d18c30966f7a9239e746b4e8fb6a
+size 28432022

SoccerTwos/SoccerTwos-48499995.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78cce40e6a143e676858634b0603db936491d284b022de7f2361d28f1cd27172
+size 1768747

SoccerTwos/SoccerTwos-48499995.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:534bb3f8fb55f073e312ee2217245616a133c746b3e07aac1106d8a009280a6e
+size 28432146

SoccerTwos/SoccerTwos-48999983.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5cd270c7e708c09ecf452a662fd4ad968e1b2f91aeb2ea01cb1b6eb267f56e53
+size 1768747

SoccerTwos/SoccerTwos-48999983.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:270dd35a9d491b74c74543c5edcdba7541079ff7e6bf0d7648a56ff395ec548a
+size 28432146

SoccerTwos/SoccerTwos-49499941.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e82691f868c0261045239b43bd2a9052401e02f406742b64fecd5d060877878
+size 1768747

SoccerTwos/SoccerTwos-49499941.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d7d22ada3203893b2b637e31826f748a04e1d901b464ab398e234899cf2dd6a
+size 28432146

SoccerTwos/SoccerTwos-49999895.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36d4f459d8c937c784a469c43c57456f081ab6318d1d257ee1478f35ae10e0f5
+size 1768747

SoccerTwos/SoccerTwos-49999895.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60d66810ebcbf63f0a45902d34e7c88db1a5e48cd3d89b591b29826812a05f23
+size 28432146

SoccerTwos/SoccerTwos-50000005.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36d4f459d8c937c784a469c43c57456f081ab6318d1d257ee1478f35ae10e0f5
+size 1768747

SoccerTwos/SoccerTwos-50000005.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2806b26c84482753fcc342e77292e06f35d65bea4fdd37dfd0d3f1377e42eca1
+size 28432146

SoccerTwos/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4d186e72ccd8ac0ae0f769813e51d17862cd3bf7fa45a4803b8884a07fd6513
+size 28431030

SoccerTwos/events.out.tfevents.1721825593.unlike-workstation.94760.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c981ea6d1ea912ca2878d6cac0e7c0503b406d5ef4db1aaa13c3a35bbda51ae2
+size 123969

SoccerTwos/events.out.tfevents.1721825752.unlike-workstation.95645.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d26bb968f52fe3117331502457c43884997ae58b448cf189d53f0f053f60b71
+size 3481167

SoccerTwos/events.out.tfevents.1721827951.unlike-workstation.106100.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4623c939a1d1588bb2755c26e5f00f2f8fa01b7e8a00f2023ce41c3c2b8cc83
+size 310194

SoccerTwos/events.out.tfevents.1721828181.unlike-workstation.107574.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2978eaa02b4f7163d925b9e7a61dd939460d38bbb1ce05f7e09e25cc27eecd30
+size 46971715

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/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": null}, "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/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: null
+debug: false

run_logs/Player-0.log

@@ -0,0 +1,404 @@
+Mono path[0] = '/home/unlike/go/src/github.com/huggingface/deep-rl-class/ml-agents/training-envs-executables/SoccerTwos/SoccerTwos_Data/Managed'
+Mono config path = '/home/unlike/go/src/github.com/huggingface/deep-rl-class/ml-agents/training-envs-executables/SoccerTwos/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 /home/unlike/go/src/github.com/huggingface/deep-rl-class/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  0.029 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: 0.335502 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 16 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]: 860056 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_Job.Worker 18]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Loading.PreloadManager]
+      Initial Block Size 256.0 KB
+      Current Block Size 300.0 KB
+      Peak Allocated Bytes 249.7 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_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_Job.Worker 16]
+      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 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 27]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 14]
+      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 17]
+      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_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_AssetGarbageCollectorHelper] x 31
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 5]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 13]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_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 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 0]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 20]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 11]
+      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 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_TEMP_Job.Worker 30]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 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_Job.Worker 21]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 26]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 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 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 25]
+      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_Job.Worker 29]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 13]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_EnlightenWorker] x 16
+      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 2]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 28]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 22]
+      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 7]
+      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_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 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 23]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 1]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 10]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 15]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 24]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 12]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 19]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Loading.AsyncRead]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 146 B
+      Overflow Count 0
+[ALLOC_DEFAULT] Dual Thread Allocator
+  Peak main deferred allocation count 5
+    [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]: 860057 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 5.0 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 860057 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 17.3 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]: 860056 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]: 860057 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]: 860057 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]: 860056 frames, [4.0 MB-8.0 MB]: 1 frames
+      Requested Block Size 4.0 MB
+      Peak Block count 2
+      Peak Allocated memory 4.5 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]: 860057 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]: 860056 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": 1.3111799955368042,
+            "min": 1.2855664491653442,
+            "max": 2.188783884048462,
+            "count": 4570
+        },
+        "SoccerTwos.Policy.Entropy.sum": {
+            "value": 23622.21875,
+            "min": 21731.388671875,
+            "max": 46860.515625,
+            "count": 4570
+        },
+        "SoccerTwos.Environment.EpisodeLength.mean": {
+            "value": 62.17948717948718,
+            "min": 38.330708661417326,
+            "max": 96.82352941176471,
+            "count": 4570
+        },
+        "SoccerTwos.Environment.EpisodeLength.sum": {
+            "value": 19400.0,
+            "min": 17644.0,
+            "max": 21636.0,
+            "count": 4570
+        },
+        "SoccerTwos.Self-play.ELO.mean": {
+            "value": 1370.5288981886865,
+            "min": 1194.9149603136586,
+            "max": 1426.1929789955975,
+            "count": 4570
+        },
+        "SoccerTwos.Self-play.ELO.sum": {
+            "value": 213802.5081174351,
+            "min": 140965.7626806283,
+            "max": 343286.631748718,
+            "count": 4570
+        },
+        "SoccerTwos.Step.mean": {
+            "value": 49999895.0,
+            "min": 4309918.0,
+            "max": 49999895.0,
+            "count": 4570
+        },
+        "SoccerTwos.Step.sum": {
+            "value": 49999895.0,
+            "min": 4309918.0,
+            "max": 49999895.0,
+            "count": 4570
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
+            "value": -0.03251473605632782,
+            "min": -0.14258797466754913,
+            "max": 0.10400567203760147,
+            "count": 4570
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
+            "value": -5.104813575744629,
+            "min": -25.951011657714844,
+            "max": 20.679386138916016,
+            "count": 4570
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
+            "value": -0.03338980674743652,
+            "min": -0.145628422498703,
+            "max": 0.10737495124340057,
+            "count": 4570
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
+            "value": -5.242199897766113,
+            "min": -26.50437355041504,
+            "max": 21.174419403076172,
+            "count": 4570
+        },
+        "SoccerTwos.Environment.CumulativeReward.mean": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 4570
+        },
+        "SoccerTwos.Environment.CumulativeReward.sum": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 4570
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.mean": {
+            "value": -0.053352865064220066,
+            "min": -0.4170310556518365,
+            "max": 0.312821740689485,
+            "count": 4570
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.sum": {
+            "value": -8.37639981508255,
+            "min": -67.14199995994568,
+            "max": 57.88719987869263,
+            "count": 4570
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.mean": {
+            "value": -0.053352865064220066,
+            "min": -0.4170310556518365,
+            "max": 0.312821740689485,
+            "count": 4570
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.sum": {
+            "value": -8.37639981508255,
+            "min": -67.14199995994568,
+            "max": 57.88719987869263,
+            "count": 4570
+        },
+        "SoccerTwos.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 4570
+        },
+        "SoccerTwos.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 4570
+        },
+        "SoccerTwos.Losses.PolicyLoss.mean": {
+            "value": 0.01991779778036289,
+            "min": 0.009833579595821599,
+            "max": 0.02802308723718549,
+            "count": 2219
+        },
+        "SoccerTwos.Losses.PolicyLoss.sum": {
+            "value": 0.01991779778036289,
+            "min": 0.009833579595821599,
+            "max": 0.02802308723718549,
+            "count": 2219
+        },
+        "SoccerTwos.Losses.ValueLoss.mean": {
+            "value": 0.10099085420370102,
+            "min": 0.07856509958704312,
+            "max": 0.13108116562167804,
+            "count": 2219
+        },
+        "SoccerTwos.Losses.ValueLoss.sum": {
+            "value": 0.10099085420370102,
+            "min": 0.07856509958704312,
+            "max": 0.13108116562167804,
+            "count": 2219
+        },
+        "SoccerTwos.Losses.BaselineLoss.mean": {
+            "value": 0.102103441208601,
+            "min": 0.07945097560683886,
+            "max": 0.13329573770364125,
+            "count": 2219
+        },
+        "SoccerTwos.Losses.BaselineLoss.sum": {
+            "value": 0.102103441208601,
+            "min": 0.07945097560683886,
+            "max": 0.13329573770364125,
+            "count": 2219
+        },
+        "SoccerTwos.Policy.LearningRate.mean": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 2219
+        },
+        "SoccerTwos.Policy.LearningRate.sum": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 2219
+        },
+        "SoccerTwos.Policy.Epsilon.mean": {
+            "value": 0.20000000000000007,
+            "min": 0.20000000000000007,
+            "max": 0.20000000000000007,
+            "count": 2219
+        },
+        "SoccerTwos.Policy.Epsilon.sum": {
+            "value": 0.20000000000000007,
+            "min": 0.20000000000000007,
+            "max": 0.20000000000000007,
+            "count": 2219
+        },
+        "SoccerTwos.Policy.Beta.mean": {
+            "value": 0.005000000000000001,
+            "min": 0.005000000000000001,
+            "max": 0.005000000000000001,
+            "count": 2219
+        },
+        "SoccerTwos.Policy.Beta.sum": {
+            "value": 0.005000000000000001,
+            "min": 0.005000000000000001,
+            "max": 0.005000000000000001,
+            "count": 2219
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1721828180",
+        "python_version": "3.10.12 | packaged by conda-forge | (main, Jun 23 2023, 22:40:32) [GCC 12.3.0]",
+        "command_line_arguments": "/home/unlike/miniconda3/envs/ml-agents/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --run-id=SoccerTwos --resume --no-graphics",
+        "mlagents_version": "1.1.0.dev0",
+        "mlagents_envs_version": "1.1.0.dev0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "2.3.1+cu121",
+        "numpy_version": "1.23.5",
+        "end_time_seconds": "1721854131"
+    },
+    "total": 25950.441492744,
+    "count": 1,
+    "self": 0.1669595460043638,
+    "children": {
+        "run_training.setup": {
+            "total": 0.005906230999244144,
+            "count": 1,
+            "self": 0.005906230999244144
+        },
+        "TrainerController.start_learning": {
+            "total": 25950.268626966998,
+            "count": 1,
+            "self": 23.044559067475348,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 2.031587658042554,
+                    "count": 230,
+                    "self": 2.031587658042554
+                },
+                "TrainerController.advance": {
+                    "total": 25925.108505157477,
+                    "count": 3174216,
+                    "self": 22.11772064798788,
+                    "children": {
+                        "env_step": {
+                            "total": 19238.14321225281,
+                            "count": 3174216,
+                            "self": 14385.698092758597,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 4837.245746559864,
+                                    "count": 3174216,
+                                    "self": 169.10663177945753,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 4668.139114780406,
+                                            "count": 5733790,
+                                            "self": 4668.139114780406
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 15.199372934348503,
+                                    "count": 3174216,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 25916.210800837714,
+                                            "count": 3174216,
+                                            "is_parallel": true,
+                                            "self": 14072.16607910991,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.0009477109997533262,
+                                                            "count": 2,
+                                                            "is_parallel": true,
+                                                            "self": 0.00022423200425691903,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.0007234789954964072,
+                                                                    "count": 8,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0007234789954964072
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.010612623002089094,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.00023258199871634133,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.00020189900169498287,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00020189900169498287
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.009530215000268072,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.009530215000268072
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.0006479270014096983,
+                                                                    "count": 2,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00012458499986678362,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.0005233420015429147,
+                                                                            "count": 8,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.0005233420015429147
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "steps_from_proto": {
+                                                    "total": 0.14035587402395322,
+                                                    "count": 458,
+                                                    "is_parallel": true,
+                                                    "self": 0.026326446979510365,
+                                                    "children": {
+                                                        "_process_rank_one_or_two_observation": {
+                                                            "total": 0.11402942704444285,
+                                                            "count": 1832,
+                                                            "is_parallel": true,
+                                                            "self": 0.11402942704444285
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 11843.904365853781,
+                                                    "count": 3174215,
+                                                    "is_parallel": true,
+                                                    "self": 658.2597974323216,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 379.51864914055113,
+                                                            "count": 3174215,
+                                                            "is_parallel": true,
+                                                            "self": 379.51864914055113
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 9059.325374901728,
+                                                            "count": 3174215,
+                                                            "is_parallel": true,
+                                                            "self": 9059.325374901728
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 1746.8005443791808,
+                                                            "count": 6348430,
+                                                            "is_parallel": true,
+                                                            "self": 318.0379855389583,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 1428.7625588402225,
+                                                                    "count": 25393720,
+                                                                    "is_parallel": true,
+                                                                    "self": 1428.7625588402225
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 6664.84757225668,
+                            "count": 3174216,
+                            "self": 175.5509459523346,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 2893.2320144626538,
+                                    "count": 3174216,
+                                    "self": 2886.7261530876494,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 6.505861375004315,
+                                            "count": 92,
+                                            "self": 6.505861375004315
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 3596.0646118416917,
+                                    "count": 2219,
+                                    "self": 2077.9340705413124,
+                                    "children": {
+                                        "TorchPOCAOptimizer.update": {
+                                            "total": 1518.1305413003793,
+                                            "count": 66570,
+                                            "self": 1518.1305413003793
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 3.349996404722333e-07,
+                    "count": 1,
+                    "self": 3.349996404722333e-07
+                },
+                "TrainerController._save_models": {
+                    "total": 0.08397474900266388,
+                    "count": 1,
+                    "self": 0.0009553830022923648,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.08301936600037152,
+                            "count": 1,
+                            "self": 0.08301936600037152
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,66 @@
+{
+    "SoccerTwos": {
+        "elo": 1369.0926472065742,
+        "checkpoints": [
+            {
+                "steps": 48499995,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-48499995.onnx",
+                "reward": 0.0,
+                "creation_time": 1721853289.3988137,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-48499995.pt"
+                ]
+            },
+            {
+                "steps": 48999983,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-48999983.onnx",
+                "reward": 0.0,
+                "creation_time": 1721853568.6667328,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-48999983.pt"
+                ]
+            },
+            {
+                "steps": 49499941,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-49499941.onnx",
+                "reward": 0.0,
+                "creation_time": 1721853850.3918188,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-49499941.pt"
+                ]
+            },
+            {
+                "steps": 49999895,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-49999895.onnx",
+                "reward": 0.0,
+                "creation_time": 1721854131.0438073,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-49999895.pt"
+                ]
+            },
+            {
+                "steps": 50000005,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-50000005.onnx",
+                "reward": 0.0,
+                "creation_time": 1721854131.1310208,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-50000005.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 50000005,
+            "file_path": "results/SoccerTwos/SoccerTwos.onnx",
+            "reward": 0.0,
+            "creation_time": 1721854131.1310208,
+            "auxillary_file_paths": [
+                "results/SoccerTwos/SoccerTwos/SoccerTwos-50000005.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "1.1.0.dev0",
+        "torch_version": "2.3.1+cu121"
+    }
+}