First Push

README.md

@@ -0,0 +1,31 @@
+
+---
+      tags:
+      - unity-ml-agents
+      - ml-agents
+      - deep-reinforcement-learning
+      - reinforcement-learning
+      - ML-Agents-SoccerTwos
+      library_name: ml-agents
+---
+    
+  # **poca** Agent playing **SoccerTwos**
+  This is a trained model of a **poca** agent playing **SoccerTwos** using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
+  
+  ## Usage (with ML-Agents)
+  The Documentation: https://github.com/huggingface/ml-agents#get-started
+  We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
+
+
+  ### Resume the training
+  ```
+  mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume
+  ```
+  ### Watch your Agent play
+  You can watch your agent **playing directly in your browser:**.
+  
+  1. Go to https://huggingface.co/spaces/unity/ML-Agents-SoccerTwos
+  2. Step 1: Write your model_id: keshan/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 sha256:58c8775acc174fd7d7b4486a8e3f42b17bb2eb55b4e0f77a411328647e59b2c8
+size 2814192

SoccerTwos/SoccerTwos-18499990.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32381b335f1627ea700233cec95deaa1db3e1a38b7346252e695e2d2d3e9b714
+size 1763220

SoccerTwos/SoccerTwos-18499990.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa66bb3f008196c949144c08dd5aee89d9aa7eface7c63b4d02e48961f9f84a4
+size 28424375

SoccerTwos/SoccerTwos-18999996.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29b24657f9c1058888b7297bdbcbc417cbb182a350c6c1199399fe2e834e93df
+size 1763220

SoccerTwos/SoccerTwos-18999996.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0bdb50c223dbfd6db371c22f36d843af11483eb372b25587f5a949a7f3cd0071
+size 28424375

SoccerTwos/SoccerTwos-19363512.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6bf61ba31d983f420e620d5332c944644b820a400716312611e1658c7fdff02c
+size 1763220

SoccerTwos/SoccerTwos-19363512.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21b838724eefc61a2e7efbb56654e12d077748a3c799f4cb468cd930d929d9fc
+size 28424375

SoccerTwos/SoccerTwos-19499134.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58c8775acc174fd7d7b4486a8e3f42b17bb2eb55b4e0f77a411328647e59b2c8
+size 2814192

SoccerTwos/SoccerTwos-19499134.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49473026b0d031807839a43a78819c7ddb24060ef3b58851586db899e81adb41
+size 34732213

SoccerTwos/SoccerTwos-19501134.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58c8775acc174fd7d7b4486a8e3f42b17bb2eb55b4e0f77a411328647e59b2c8
+size 2814192

SoccerTwos/SoccerTwos-19501134.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0bcd5bfadc78007b9d60558bd237b5a4d5db1c9c9e70031704c579889c6c17c4
+size 34732213

SoccerTwos/SoccerTwos-499859.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb91ef23837bb746f9f437d9046ca896b78cc2083850dc7c6832014b3f5a22d6
+size 1763220

SoccerTwos/SoccerTwos-499859.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1560e165371c3311332cc48cd4406b9f99a1e95d652cb9e134ae3e8dae188579
+size 28424369

SoccerTwos/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0bcd5bfadc78007b9d60558bd237b5a4d5db1c9c9e70031704c579889c6c17c4
+size 34732213

SoccerTwos/events.out.tfevents.1675391398.workstation.13444.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d5e6bd7d843173a4eff12a498fc3db4057a98c43af059237beec3cc33cb259b
+size 806547

SoccerTwos/events.out.tfevents.1675393190.workstation.6284.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3b2c80bc445563f8caf6ed7716fa69221783d75f5a6792d1be4e4fa2ae3f641
+size 18722597

SoccerTwos/events.out.tfevents.1675418918.workstation.25068.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b037b58fe5768163bbb1174265212f8ab9d0f25430f4dd1418ef29df2284a278
+size 130382

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": 3, "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": 19500000, "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, "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: 3
+      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: 19500000
+    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
+  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 +1,345 @@
+Mono path[0] = '/home/keshan/workspace/RL/ml-agents/training-envs-executables/SoccerTwos/SoccerTwos_Data/Managed'
+Mono config path = '/home/keshan/workspace/RL/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/keshan/workspace/RL/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  0.088 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: 0.458294 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
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+Setting up 6 worker threads for Enlighten.
+Memory Statistics:
+[ALLOC_TEMP_TLS] TLS Allocator
+  StackAllocators : 
+    [ALLOC_TEMP_MAIN]
+      Peak usage frame count: [8.0 KB-16.0 KB]: 2673 frames, [2.0 MB-4.0 MB]: 1 frames
+      Initial Block Size 4.0 MB
+      Current Block Size 4.0 MB
+      Peak Allocated Bytes 2.1 MB
+      Overflow Count 0
+    [ALLOC_TEMP_Loading.AsyncRead]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 128 B
+      Overflow Count 0
+    [ALLOC_TEMP_Loading.PreloadManager]
+      Initial Block Size 256.0 KB
+      Current Block Size 300.0 KB
+      Peak Allocated Bytes 249.6 KB
+      Overflow Count 4
+    [ALLOC_TEMP_Background Job.Worker 8]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 6]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 0]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0.7 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 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 9]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 5]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 14]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 6]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 4]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 3]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 12]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_EnlightenWorker] x 6
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 15]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 1]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 2]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 7]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_AssetGarbageCollectorHelper] x 11
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 5]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 9]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 13]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 8]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 7]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 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 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 11]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 10]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 0]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 4]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_BatchDeleteObjects]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+[ALLOC_DEFAULT] Dual Thread Allocator
+  Peak main deferred allocation count 4
+    [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]: 2674 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]: 2674 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]: 2673 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]: 2674 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]: 2674 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]: 2673 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]: 2674 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]: 2673 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": 3.043471574783325,
+            "min": 3.037630796432495,
+            "max": 3.0692951679229736,
+            "count": 14
+        },
+        "SoccerTwos.Policy.Entropy.sum": {
+            "value": 50935.5390625,
+            "min": 38177.2421875,
+            "max": 97204.1875,
+            "count": 14
+        },
+        "SoccerTwos.Environment.EpisodeLength.mean": {
+            "value": 702.1428571428571,
+            "min": 496.22222222222223,
+            "max": 918.5,
+            "count": 14
+        },
+        "SoccerTwos.Environment.EpisodeLength.sum": {
+            "value": 19660.0,
+            "min": 9068.0,
+            "max": 25108.0,
+            "count": 14
+        },
+        "SoccerTwos.Self-play.ELO.mean": {
+            "value": 1618.8131689785366,
+            "min": 1618.8131689785366,
+            "max": 1629.3202806478475,
+            "count": 14
+        },
+        "SoccerTwos.Self-play.ELO.sum": {
+            "value": 12950.505351828293,
+            "min": 3242.0698683381665,
+            "max": 26052.765819372493,
+            "count": 14
+        },
+        "SoccerTwos.Step.mean": {
+            "value": 19499134.0,
+            "min": 19369091.0,
+            "max": 19499134.0,
+            "count": 14
+        },
+        "SoccerTwos.Step.sum": {
+            "value": 19499134.0,
+            "min": 19369091.0,
+            "max": 19499134.0,
+            "count": 14
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
+            "value": -0.04292716458439827,
+            "min": -0.08585584908723831,
+            "max": -0.04292716458439827,
+            "count": 14
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
+            "value": -0.600980281829834,
+            "min": -1.2457462549209595,
+            "max": -0.5130867958068848,
+            "count": 14
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
+            "value": -0.042994700372219086,
+            "min": -0.08585096895694733,
+            "max": -0.042994700372219086,
+            "count": 14
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
+            "value": -0.601925790309906,
+            "min": -1.2618554830551147,
+            "max": -0.5027204155921936,
+            "count": 14
+        },
+        "SoccerTwos.Environment.CumulativeReward.mean": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 14
+        },
+        "SoccerTwos.Environment.CumulativeReward.sum": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 14
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.mean": {
+            "value": -0.07797143182584218,
+            "min": -0.42092499881982803,
+            "max": 0.08781818368218162,
+            "count": 14
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.sum": {
+            "value": -1.0916000455617905,
+            "min": -6.793599992990494,
+            "max": 0.9660000205039978,
+            "count": 14
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.mean": {
+            "value": -0.07797143182584218,
+            "min": -0.42092499881982803,
+            "max": 0.08781818368218162,
+            "count": 14
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.sum": {
+            "value": -1.0916000455617905,
+            "min": -6.793599992990494,
+            "max": 0.9660000205039978,
+            "count": 14
+        },
+        "SoccerTwos.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 14
+        },
+        "SoccerTwos.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 14
+        },
+        "SoccerTwos.Losses.PolicyLoss.mean": {
+            "value": 0.015083407533044617,
+            "min": 0.014016866074719777,
+            "max": 0.021844326495192946,
+            "count": 6
+        },
+        "SoccerTwos.Losses.PolicyLoss.sum": {
+            "value": 0.015083407533044617,
+            "min": 0.014016866074719777,
+            "max": 0.021844326495192946,
+            "count": 6
+        },
+        "SoccerTwos.Losses.ValueLoss.mean": {
+            "value": 0.001888798961105446,
+            "min": 0.001888798961105446,
+            "max": 0.008230537067477901,
+            "count": 6
+        },
+        "SoccerTwos.Losses.ValueLoss.sum": {
+            "value": 0.001888798961105446,
+            "min": 0.001888798961105446,
+            "max": 0.008230537067477901,
+            "count": 6
+        },
+        "SoccerTwos.Losses.BaselineLoss.mean": {
+            "value": 0.0019233887743515274,
+            "min": 0.0019233887743515274,
+            "max": 0.008773141773417592,
+            "count": 6
+        },
+        "SoccerTwos.Losses.BaselineLoss.sum": {
+            "value": 0.0019233887743515274,
+            "min": 0.0019233887743515274,
+            "max": 0.008773141773417592,
+            "count": 6
+        },
+        "SoccerTwos.Policy.LearningRate.mean": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 6
+        },
+        "SoccerTwos.Policy.LearningRate.sum": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 6
+        },
+        "SoccerTwos.Policy.Epsilon.mean": {
+            "value": 0.20000000000000007,
+            "min": 0.20000000000000007,
+            "max": 0.20000000000000007,
+            "count": 6
+        },
+        "SoccerTwos.Policy.Epsilon.sum": {
+            "value": 0.20000000000000007,
+            "min": 0.20000000000000007,
+            "max": 0.20000000000000007,
+            "count": 6
+        },
+        "SoccerTwos.Policy.Beta.mean": {
+            "value": 0.005000000000000001,
+            "min": 0.005000000000000001,
+            "max": 0.005000000000000001,
+            "count": 6
+        },
+        "SoccerTwos.Policy.Beta.sum": {
+            "value": 0.005000000000000001,
+            "min": 0.005000000000000001,
+            "max": 0.005000000000000001,
+            "count": 6
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1675418917",
+        "python_version": "3.8.16 (default, Jan 17 2023, 23:13:24) \n[GCC 11.2.0]",
+        "command_line_arguments": "/home/keshan/miniconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos/SoccerTwos.x86_64 --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": "1.8.1+cu102",
+        "numpy_version": "1.21.2",
+        "end_time_seconds": "1675419108"
+    },
+    "total": 190.42089542699978,
+    "count": 1,
+    "self": 0.4347010009987571,
+    "children": {
+        "run_training.setup": {
+            "total": 0.008017883999855258,
+            "count": 1,
+            "self": 0.008017883999855258
+        },
+        "TrainerController.start_learning": {
+            "total": 189.97817654200117,
+            "count": 1,
+            "self": 0.18120597097367863,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 3.816575750002812,
+                    "count": 2,
+                    "self": 3.816575750002812
+                },
+                "TrainerController.advance": {
+                    "total": 185.78527672802375,
+                    "count": 8988,
+                    "self": 0.18528100555340643,
+                    "children": {
+                        "env_step": {
+                            "total": 137.87652353762314,
+                            "count": 8988,
+                            "self": 99.09597604864757,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 38.66776444188508,
+                                    "count": 8988,
+                                    "self": 0.9768444707333401,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 37.69091997115174,
+                                            "count": 17822,
+                                            "self": 37.69091997115174
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 0.11278304709048825,
+                                    "count": 8988,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 189.05563316128246,
+                                            "count": 8988,
+                                            "is_parallel": true,
+                                            "self": 110.23523233218657,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.0016767560045991559,
+                                                            "count": 2,
+                                                            "is_parallel": true,
+                                                            "self": 0.0005245400025160052,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.0011522160020831507,
+                                                                    "count": 8,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0011522160020831507
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.06330509200051893,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0005964040065009613,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.0028263249987503514,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0028263249987503514
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.05504491799729294,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.05504491799729294
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.004837444997974671,
+                                                                    "count": 2,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.002705122999032028,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.0021323219989426434,
+                                                                            "count": 8,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.0021323219989426434
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "steps_from_proto": {
+                                                    "total": 0.0011779960004787426,
+                                                    "count": 2,
+                                                    "is_parallel": true,
+                                                    "self": 0.00024075599867501296,
+                                                    "children": {
+                                                        "_process_rank_one_or_two_observation": {
+                                                            "total": 0.0009372400018037297,
+                                                            "count": 8,
+                                                            "is_parallel": true,
+                                                            "self": 0.0009372400018037297
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 78.81922283309541,
+                                                    "count": 8987,
+                                                    "is_parallel": true,
+                                                    "self": 4.711719908023952,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 3.3742167089221766,
+                                                            "count": 8987,
+                                                            "is_parallel": true,
+                                                            "self": 3.3742167089221766
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 57.03025105990673,
+                                                            "count": 8987,
+                                                            "is_parallel": true,
+                                                            "self": 57.03025105990673
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 13.70303515624255,
+                                                            "count": 17974,
+                                                            "is_parallel": true,
+                                                            "self": 2.8597794833221997,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 10.84325567292035,
+                                                                    "count": 71896,
+                                                                    "is_parallel": true,
+                                                                    "self": 10.84325567292035
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 47.723472184847196,
+                            "count": 8988,
+                            "self": 1.320126012658875,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 12.188433872190217,
+                                    "count": 8988,
+                                    "self": 11.879833244187466,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 0.30860062800275045,
+                                            "count": 1,
+                                            "self": 0.30860062800275045
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 34.214912299998105,
+                                    "count": 6,
+                                    "self": 14.669095975994423,
+                                    "children": {
+                                        "TorchPOCAOptimizer.update": {
+                                            "total": 19.54581632400368,
+                                            "count": 180,
+                                            "self": 19.54581632400368
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 6.660011422354728e-07,
+                    "count": 1,
+                    "self": 6.660011422354728e-07
+                },
+                "TrainerController._save_models": {
+                    "total": 0.1951174269997864,
+                    "count": 1,
+                    "self": 0.0017176590008602943,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.1933997679989261,
+                            "count": 1,
+                            "self": 0.1933997679989261
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,66 @@
+{
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "0.31.0.dev0",
+        "torch_version": "1.8.1+cu102"
+    },
+    "SoccerTwos": {
+        "checkpoints": [
+            {
+                "steps": 18499990,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-18499990.onnx",
+                "reward": 0.0,
+                "creation_time": 1675417766.9592254,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-18499990.pt"
+                ]
+            },
+            {
+                "steps": 18999996,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-18999996.onnx",
+                "reward": 0.0,
+                "creation_time": 1675418423.3281977,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-18999996.pt"
+                ]
+            },
+            {
+                "steps": 19363512,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-19363512.onnx",
+                "reward": null,
+                "creation_time": 1675418902.6850805,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-19363512.pt"
+                ]
+            },
+            {
+                "steps": 19499134,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-19499134.onnx",
+                "reward": 0.0,
+                "creation_time": 1675419107.3996878,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-19499134.pt"
+                ]
+            },
+            {
+                "steps": 19501134,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-19501134.onnx",
+                "reward": 0.0,
+                "creation_time": 1675419107.7270603,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-19501134.pt"
+                ]
+            }
+        ],
+        "elo": 1619.120991258441,
+        "final_checkpoint": {
+            "steps": 19501134,
+            "file_path": "results/SoccerTwos/SoccerTwos.onnx",
+            "reward": 0.0,
+            "creation_time": 1675419107.7270603,
+            "auxillary_file_paths": [
+                "results/SoccerTwos/SoccerTwos/SoccerTwos-19501134.pt"
+            ]
+        }
+    }
+}