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: Arindam75/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 sha256:4508044e01234f2106ba448159c0f72ddb661494aa8eeb857059fd4257abca5b
+size 1768746

SoccerTwos/SoccerTwos-10000138.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4508044e01234f2106ba448159c0f72ddb661494aa8eeb857059fd4257abca5b
+size 1768746

SoccerTwos/SoccerTwos-10000138.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:886ae775a7d67fb188f1c351ed898eea26c84a51c4925510ff8bf7015d17eee8
+size 28430025

SoccerTwos/SoccerTwos-499710.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a14c0c2644783e1bef1ee3cc66bca97101563b0cacb04a2e4d91b2782a8d605
+size 28429781

SoccerTwos/SoccerTwos-5999910.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aafe27bdc21f77ea5affdc19042e6c8a973d6f506fafc3bf0e5612aa3dab11d0
+size 1768746

SoccerTwos/SoccerTwos-5999910.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6faa5de49ef057e4f80b82255bcbb87d34cec72ba3f935c336b57c7264ebb960
+size 28429903

SoccerTwos/SoccerTwos-6499992.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:855f71914c244e88c7c8b584c90901248e826379fd83523f52a0054f2ae4d8f9
+size 1768746

SoccerTwos/SoccerTwos-6499992.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d4f4b9e755d610e15c4eaed80d11aa161a3b7a8bfe4b079901dcdfd49264ecd
+size 28429903

SoccerTwos/SoccerTwos-6999982.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03e2e3c6a6c674f3402f85f6a789022300c240cb83664b54282ae18da1aaca38
+size 1768746

SoccerTwos/SoccerTwos-6999982.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ea50633f3b2c62b24b59cfb269cf3605eccd3517f58e5ea497f41ad7483e15f
+size 28429903

SoccerTwos/SoccerTwos-7499989.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2a55adc984d79fa33206416136363b20dbc6946a69ed116fc36e862665c4b82
+size 1768746

SoccerTwos/SoccerTwos-7499989.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:591976c922ce5d7ab9b0654e756eefb7c5316a50a7c747d01ed092bbcbc2cae5
+size 28429903

SoccerTwos/SoccerTwos-7999964.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99dffa31d9e336d544fc85d061a95afb951785c198efe4db48778910b98baf42
+size 1768746

SoccerTwos/SoccerTwos-7999964.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7eede36eed37d0f7c2ddf7d038a0b405a6d15c5b49575d928652077989466e68
+size 28429903

SoccerTwos/SoccerTwos-8499843.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:322a20eaa1b814652c95e3cb5f407ed3bdf782bc49d61c4a90ea9a76e90a88f2
+size 1768746

SoccerTwos/SoccerTwos-8499843.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72681aa6ea0774d9640cd99d2be0145e5b31a0a452afbe44acad943d0f26fc13
+size 28429903

SoccerTwos/SoccerTwos-8999963.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a95e1c8746c2cb6d034127e8aa369b7817d5077e70186f3815e7ab2bd3d1bc7
+size 1768746

SoccerTwos/SoccerTwos-8999963.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:072c8f2bae61be120fdf37f79b63189b5bea63b6130fdfd4fab22d6df508c3cd
+size 28429903

SoccerTwos/SoccerTwos-9499969.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6f5763a0cb5ef86b4245c5c4b4cd2e6a5bdb3815e0d555cc5a8af31060d75d0
+size 1768746

SoccerTwos/SoccerTwos-9499969.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4e613e730888576773b81a3f2138e031d5df6fa8a3744c8cbc03d38efaa86ac
+size 28429903

SoccerTwos/SoccerTwos-9999880.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4508044e01234f2106ba448159c0f72ddb661494aa8eeb857059fd4257abca5b
+size 1768746

SoccerTwos/SoccerTwos-9999880.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef79da60e34c406b005e6e1f319bc38d8427a12f43eb4d95ea08b90f2db45f42
+size 28429903

SoccerTwos/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e393557e86c2231cd0b8e09ba2fcbbd7bb6bc67acdaf8cb56f6869e0f5b3360
+size 28428927

SoccerTwos/events.out.tfevents.1692035221.ANDY.4420.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:504a23d12a93a0d32e5efac49a6145f0d2f83dbe47da9a988fcf49476037a096
+size 305489

SoccerTwos/events.out.tfevents.1692038079.ANDY.21608.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97b6fbb24587c8558ea243ba0927f0d2be20170c93317b65b2bde490aa9f7dc6
+size 1414

SoccerTwos/events.out.tfevents.1692038265.ANDY.12908.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a95bc778ea050962895ba7f9808f14ad1fe38fb32c6ddfe92fdb248dcca6dcb
+size 2040

SoccerTwos/events.out.tfevents.1692038710.ANDY.13780.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e27f61b911a114ad8f5cf9891f25caaca332a5ee2e12dc62629c7bedd8914cc5
+size 7065886

SoccerTwos/events.out.tfevents.1692072367.ANDY.16352.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ebc0c6c277c6ed2f032152e25eae1badb5f3fb25042801136eb95a39af11336
+size 2057612

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": 10000000, "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.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: 5
+    even_checkpoints: false
+    max_steps: 10000000
+    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.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 +1,322 @@
+Mono path[0] = 'C:/Users/arind/Documents/ml-agents/training-envs-executables/SoccerTwos/SoccerTwos_Data/Managed'
+Mono config path = 'C:/Users/arind/Documents/ml-agents/training-envs-executables/SoccerTwos/MonoBleedingEdge/etc'
+Initialize engine version: 2021.3.14f1 (eee1884e7226)
+[Subsystems] Discovering subsystems at path C:/Users/arind/Documents/ml-agents/training-envs-executables/SoccerTwos/SoccerTwos_Data/UnitySubsystems
+Forcing GfxDevice: Null
+GfxDevice: creating device client; threaded=0; jobified=0
+NullGfxDevice:
+    Version:  NULL 1.0 [1.0]
+    Renderer: Null Device
+    Vendor:   Unity Technologies
+Begin MonoManager ReloadAssembly
+- Completed reload, in  0.148 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: 0.575700 ms
+Registered Communicator in Agent.
+ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+Setting up 8 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]: 37632 frames, [2.0 MB-4.0 MB]: 1 frames
+      Initial Block Size 4.0 MB
+      Current Block Size 4.0 MB
+      Peak Allocated Bytes 2.0 MB
+      Overflow Count 0
+    [ALLOC_TEMP_Loading.AsyncRead]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 342 B
+      Overflow Count 0
+    [ALLOC_TEMP_Loading.PreloadManager]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 67.1 KB
+      Overflow Count 4
+    [ALLOC_TEMP_Background Job.Worker 8]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 54 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 6]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 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 54 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 9]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 54 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 5]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 14]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 54 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 6]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 54 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 4]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 14]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 54 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_Job.Worker 13]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 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 8
+      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 15
+      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_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 54 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 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_Job.Worker 10]
+      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 0]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 54 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 11]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 54 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 12]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 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 3
+    [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]: 37633 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 4.9 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 37633 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 17.4 MB
+      Peak Large allocation bytes 16.0 MB
+[ALLOC_TEMP_JOB_1_FRAME]
+  Initial Block Size 2.0 MB
+  Used Block Count 1
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_TEMP_JOB_2_FRAMES]
+  Initial Block Size 2.0 MB
+  Used Block Count 1
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_TEMP_JOB_4_FRAMES (JobTemp)]
+  Initial Block Size 2.0 MB
+  Used Block Count 2
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_TEMP_JOB_ASYNC (Background)]
+  Initial Block Size 1.0 MB
+  Used Block Count 3
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_GFX] Dual Thread Allocator
+  Peak main deferred allocation count 0
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 0.9 MB
+    [ALLOC_GFX_MAIN]
+      Peak usage frame count: [32.0 KB-64.0 KB]: 37632 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]: 37633 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]: 37633 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]: 37632 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]: 37633 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]: 37632 frames, [2.0 KB-4.0 KB]: 1 frames
+      Requested Block Size 2.0 MB
+      Peak Block count 1
+      Peak Allocated memory 2.2 KB
+      Peak Large allocation bytes 0 B

run_logs/timers.json

@@ -0,0 +1,368 @@
+{
+    "name": "root",
+    "gauges": {
+        "SoccerTwos.Policy.Entropy.mean": {
+            "value": 1.732181429862976,
+            "min": 1.6721676588058472,
+            "max": 1.7746363878250122,
+            "count": 201
+        },
+        "SoccerTwos.Policy.Entropy.sum": {
+            "value": 33036.1640625,
+            "min": 1314.3040771484375,
+            "max": 39203.53125,
+            "count": 201
+        },
+        "SoccerTwos.Environment.EpisodeLength.mean": {
+            "value": 59.154761904761905,
+            "min": 22.0,
+            "max": 85.08620689655173,
+            "count": 201
+        },
+        "SoccerTwos.Environment.EpisodeLength.sum": {
+            "value": 19876.0,
+            "min": 88.0,
+            "max": 20684.0,
+            "count": 201
+        },
+        "SoccerTwos.Self-play.ELO.mean": {
+            "value": 1184.1481187834331,
+            "min": 1179.3808442439704,
+            "max": 1245.1211576021508,
+            "count": 201
+        },
+        "SoccerTwos.Self-play.ELO.sum": {
+            "value": 198936.88395561677,
+            "min": 2408.3848347360704,
+            "max": 275078.6501338947,
+            "count": 201
+        },
+        "SoccerTwos.Step.mean": {
+            "value": 9999880.0,
+            "min": 7999987.0,
+            "max": 9999880.0,
+            "count": 201
+        },
+        "SoccerTwos.Step.sum": {
+            "value": 9999880.0,
+            "min": 7999987.0,
+            "max": 9999880.0,
+            "count": 201
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
+            "value": -0.047952137887477875,
+            "min": -0.3794843554496765,
+            "max": 0.06930270045995712,
+            "count": 201
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
+            "value": -8.008007049560547,
+            "min": -17.206485748291016,
+            "max": 9.979588508605957,
+            "count": 201
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
+            "value": -0.04520222172141075,
+            "min": -0.3782753646373749,
+            "max": 0.0739375427365303,
+            "count": 201
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
+            "value": -7.548770904541016,
+            "min": -18.65555191040039,
+            "max": 10.647006034851074,
+            "count": 201
+        },
+        "SoccerTwos.Environment.CumulativeReward.mean": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 201
+        },
+        "SoccerTwos.Environment.CumulativeReward.sum": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 201
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.mean": {
+            "value": -0.03427784492869577,
+            "min": -1.0,
+            "max": 0.27126915023681963,
+            "count": 201
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.sum": {
+            "value": -5.724400103092194,
+            "min": -60.165599942207336,
+            "max": 50.998600244522095,
+            "count": 201
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.mean": {
+            "value": -0.03427784492869577,
+            "min": -1.0,
+            "max": 0.27126915023681963,
+            "count": 201
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.sum": {
+            "value": -5.724400103092194,
+            "min": -60.165599942207336,
+            "max": 50.998600244522095,
+            "count": 201
+        },
+        "SoccerTwos.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 201
+        },
+        "SoccerTwos.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 201
+        },
+        "SoccerTwos.Losses.PolicyLoss.mean": {
+            "value": 0.015484807884786279,
+            "min": 0.010712086466567902,
+            "max": 0.02184484260311971,
+            "count": 97
+        },
+        "SoccerTwos.Losses.PolicyLoss.sum": {
+            "value": 0.015484807884786279,
+            "min": 0.010712086466567902,
+            "max": 0.02184484260311971,
+            "count": 97
+        },
+        "SoccerTwos.Losses.ValueLoss.mean": {
+            "value": 0.10931220576167107,
+            "min": 0.09008215417464574,
+            "max": 0.11983859514196714,
+            "count": 97
+        },
+        "SoccerTwos.Losses.ValueLoss.sum": {
+            "value": 0.10931220576167107,
+            "min": 0.09008215417464574,
+            "max": 0.11983859514196714,
+            "count": 97
+        },
+        "SoccerTwos.Losses.BaselineLoss.mean": {
+            "value": 0.11182896370689074,
+            "min": 0.0918625886241595,
+            "max": 0.12305790483951569,
+            "count": 97
+        },
+        "SoccerTwos.Losses.BaselineLoss.sum": {
+            "value": 0.11182896370689074,
+            "min": 0.0918625886241595,
+            "max": 0.12305790483951569,
+            "count": 97
+        },
+        "SoccerTwos.Policy.LearningRate.mean": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 97
+        },
+        "SoccerTwos.Policy.LearningRate.sum": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 97
+        },
+        "SoccerTwos.Policy.Epsilon.mean": {
+            "value": 0.20000000000000007,
+            "min": 0.20000000000000007,
+            "max": 0.20000000000000007,
+            "count": 97
+        },
+        "SoccerTwos.Policy.Epsilon.sum": {
+            "value": 0.20000000000000007,
+            "min": 0.20000000000000007,
+            "max": 0.20000000000000007,
+            "count": 97
+        },
+        "SoccerTwos.Policy.Beta.mean": {
+            "value": 0.005000000000000001,
+            "min": 0.005000000000000001,
+            "max": 0.005000000000000001,
+            "count": 97
+        },
+        "SoccerTwos.Policy.Beta.sum": {
+            "value": 0.005000000000000001,
+            "min": 0.005000000000000001,
+            "max": 0.005000000000000001,
+            "count": 97
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1692072363",
+        "python_version": "3.9.17 (main, Jul  5 2023, 20:47:11) [MSC v.1916 64 bit (AMD64)]",
+        "command_line_arguments": "\\\\?\\C:\\Users\\arind\\anaconda3\\envs\\rl\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --no-graphics --resume",
+        "mlagents_version": "0.31.0.dev0",
+        "mlagents_envs_version": "0.31.0.dev0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "2.0.1+cpu",
+        "numpy_version": "1.21.2",
+        "end_time_seconds": "1692080634"
+    },
+    "total": 8271.546342399999,
+    "count": 1,
+    "self": 0.34422339999946416,
+    "children": {
+        "run_training.setup": {
+            "total": 0.13060319999999992,
+            "count": 1,
+            "self": 0.13060319999999992
+        },
+        "TrainerController.start_learning": {
+            "total": 8271.0715158,
+            "count": 1,
+            "self": 3.870866999952341,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 4.523448899999807,
+                    "count": 11,
+                    "self": 4.523448899999807
+                },
+                "TrainerController.advance": {
+                    "total": 8262.54827700005,
+                    "count": 139226,
+                    "self": 3.62916780008527,
+                    "children": {
+                        "env_step": {
+                            "total": 2431.2926128999343,
+                            "count": 139226,
+                            "self": 1897.7927180996112,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 531.2760609002432,
+                                    "count": 139226,
+                                    "self": 20.32213670011913,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 510.9539242001241,
+                                            "count": 250890,
+                                            "self": 510.9539242001241
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 2.22383390007973,
+                                    "count": 139226,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 8260.908639200072,
+                                            "count": 139226,
+                                            "is_parallel": true,
+                                            "self": 6760.666442999948,
+                                            "children": {
+                                                "steps_from_proto": {
+                                                    "total": 0.02259929999895327,
+                                                    "count": 22,
+                                                    "is_parallel": true,
+                                                    "self": 0.004516000000016618,
+                                                    "children": {
+                                                        "_process_rank_one_or_two_observation": {
+                                                            "total": 0.018083299998936653,
+                                                            "count": 88,
+                                                            "is_parallel": true,
+                                                            "self": 0.018083299998936653
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 1500.2195969001245,
+                                                    "count": 139226,
+                                                    "is_parallel": true,
+                                                    "self": 86.47876889976465,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 75.80817220008848,
+                                                            "count": 139226,
+                                                            "is_parallel": true,
+                                                            "self": 75.80817220008848
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 1074.4842978001786,
+                                                            "count": 139226,
+                                                            "is_parallel": true,
+                                                            "self": 1074.4842978001786
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 263.4483580000929,
+                                                            "count": 278452,
+                                                            "is_parallel": true,
+                                                            "self": 54.522942300503445,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 208.92541569958948,
+                                                                    "count": 1113808,
+                                                                    "is_parallel": true,
+                                                                    "self": 208.92541569958948
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 5827.626496300031,
+                            "count": 139226,
+                            "self": 29.34687570002734,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 849.6915618000047,
+                                    "count": 139226,
+                                    "self": 848.9329515000044,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 0.758610300000381,
+                                            "count": 5,
+                                            "self": 0.758610300000381
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 4948.588058799999,
+                                    "count": 97,
+                                    "self": 334.6716963999934,
+                                    "children": {
+                                        "TorchPOCAOptimizer.update": {
+                                            "total": 4613.916362400006,
+                                            "count": 2910,
+                                            "self": 4613.916362400006
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 7.999988156370819e-07,
+                    "count": 1,
+                    "self": 7.999988156370819e-07
+                },
+                "TrainerController._save_models": {
+                    "total": 0.12892209999881743,
+                    "count": 1,
+                    "self": 0.003294999998615822,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.1256271000002016,
+                            "count": 1,
+                            "self": 0.1256271000002016
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,66 @@
+{
+    "SoccerTwos": {
+        "elo": 1187.2017962014856,
+        "checkpoints": [
+            {
+                "steps": 8499843,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-8499843.onnx",
+                "reward": 0.0,
+                "creation_time": 1692074472.6173906,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-8499843.pt"
+                ]
+            },
+            {
+                "steps": 8999963,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-8999963.onnx",
+                "reward": 0.0,
+                "creation_time": 1692076608.945494,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-8999963.pt"
+                ]
+            },
+            {
+                "steps": 9499969,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-9499969.onnx",
+                "reward": 0.0,
+                "creation_time": 1692078625.5683866,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-9499969.pt"
+                ]
+            },
+            {
+                "steps": 9999880,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-9999880.onnx",
+                "reward": 0.0,
+                "creation_time": 1692080634.421705,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-9999880.pt"
+                ]
+            },
+            {
+                "steps": 10000138,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-10000138.onnx",
+                "reward": 0.0,
+                "creation_time": 1692080634.6281087,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-10000138.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 10000138,
+            "file_path": "results\\SoccerTwos\\SoccerTwos.onnx",
+            "reward": 0.0,
+            "creation_time": 1692080634.6281087,
+            "auxillary_file_paths": [
+                "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-10000138.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "0.31.0.dev0",
+        "torch_version": "2.0.1+cpu"
+    }
+}