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: blu666/poca_3_layer_run2
+  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 sha256:24f5805b4ec1252e25786722e0cacc688c1e6a4cf13cde8ca6b755846ac986da
+size 2820313

SoccerTwos/SoccerTwos-33499985.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b7a973cdcd27695b0eb601d19478d22205541970893dcef5939785a92c07853
+size 2820313

SoccerTwos/SoccerTwos-33499985.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab81e3e6f9a3a431bacac846c00445d40f18d2365d2e84d7b1062c95300964c9
+size 34741042

SoccerTwos/SoccerTwos-33999912.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ed78de71912e109812bf67c6dcdf2eac18117078520759459d9562773282acb
+size 2820313

SoccerTwos/SoccerTwos-33999912.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e79b24ef762bbd7a4db985e81b39f005e0999935acbeee6b0eb77a407abbabd8
+size 34741042

SoccerTwos/SoccerTwos-34499999.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f1c67356408c4ccb1e56ebd8cedee9713bb17e1ca0c2995c1f466064b59bf2b
+size 2820313

SoccerTwos/SoccerTwos-34499999.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15667789065cfb70224d044b34360c6d0c85133e2b32ba674141504740913600
+size 34741042

SoccerTwos/SoccerTwos-34999970.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24f5805b4ec1252e25786722e0cacc688c1e6a4cf13cde8ca6b755846ac986da
+size 2820313

SoccerTwos/SoccerTwos-34999970.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:203fb82a041e226ef35a13bcebbfda56ebc1af1953281c467397058a21a66f37
+size 34741042

SoccerTwos/SoccerTwos-35000046.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24f5805b4ec1252e25786722e0cacc688c1e6a4cf13cde8ca6b755846ac986da
+size 2820313

SoccerTwos/SoccerTwos-35000046.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0dfcbcb927157ee3ed4e815e64c3ca7995636a4fea16bac43b6c38f42e2fe3cf
+size 34741042

SoccerTwos/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:987c3e80bb12a5bee918ed55c4c4c0f4105ab8f27ac75264f3882720c3bfe30b
+size 34739782

SoccerTwos/events.out.tfevents.1713943268.BLU-DELL-U.672265.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fdb0a1f7a0d78960defcd6d1eb8c6ff1750a6e234f13fe7eb8d88fd76afe063c
+size 663037

SoccerTwos/events.out.tfevents.1713944301.BLU-DELL-U.680140.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f39bb8900a894e32d1e0dd36ea7f63204120b942ad527f895cbd5f1aa118fc4
+size 7419653

SoccerTwos/events.out.tfevents.1713951227.BLU-DELL-U.732672.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:912eeabd945b418a93ed2688cba39080878053100d76d893883f183132740a02
+size 83159

SoccerTwos/events.out.tfevents.1713951315.BLU-DELL-U.733581.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:557733038b8b5fe1fc01393117256bc6bfb15bb4158fad508125b6a8e0965ed7
+size 1717291

SoccerTwos/events.out.tfevents.1713954700.BLU-DELL-U.744950.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1053aec3c2600cadec0315b89663722730ce719e8bec7f56cd0a4459e62c488b
+size 3896249

SoccerTwos/events.out.tfevents.1713958741.BLU-DELL-U.773207.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:283087354c060fb0ba7bba93a7a3c7269251281a05ee5ee6e0a6a27331cefd3a
+size 11039648

SoccerTwos/events.out.tfevents.1713993659.BLU-DELL-U.964322.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eeb39cdcb0fd8386067b2269043655198d29151a50d93d81266d8cc8426c070c
+size 4574582

SoccerTwos/events.out.tfevents.1713999955.BLU-DELL-U.1002452.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:046f9a9fb9fc951926a324e2a2bf574832ba2f0b028668a7d3c8d9677a889166
+size 2601283

SoccerTwos/events.out.tfevents.1714002651.BLU-DELL-U.1020509.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f9c1f2dd3f995c76783047dcd909d9774ba111d543b2714b41e3d433bd2ee4a
+size 72703

SoccerTwos/events.out.tfevents.1714002748.BLU-DELL-U.1021435.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cc0c4c5e7fca0785a7e17f5ef6d10e6a6b24819219c051da9505ee009fa0a06
+size 3033169

config.json

@@ -0,0 +1 @@
+{"default_settings": null, "behaviors": {"SoccerTwos": {"trainer_type": "poca", "hyperparameters": {"batch_size": 2048, "buffer_size": 20480, "learning_rate": 0.0002, "beta": 0.003, "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": 35000000, "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": "../test_env/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": "poca_3_layer_run2", "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: 0.0002
+      beta: 0.003
+      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: 35000000
+    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: ../test_env/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: poca_3_layer_run2
+  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 +1,344 @@
+Mono path[0] = '/home/luyijie/meam6240-final/test_env/SoccerTwos_Data/Managed'
+Mono config path = '/home/luyijie/meam6240-final/test_env/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/luyijie/meam6240-final/test_env/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  0.042 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: 0.442495 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 10 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]: 55563 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 249.5 KB
+      Overflow Count 4
+    [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_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 0.7 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 0]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 10]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 9]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 5]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 14]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_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 14]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      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_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_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 10
+      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 19
+      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_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 11]
+      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_Background Job.Worker 4]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_BatchDeleteObjects]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+[ALLOC_DEFAULT] Dual Thread Allocator
+  Peak main deferred allocation count 3
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 1.0 MB
+    [ALLOC_DEFAULT_MAIN]
+      Peak usage frame count: [4.0 MB-8.0 MB]: 55564 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 5.2 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 55564 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 17.1 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]: 55563 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]: 55564 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]: 55564 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]: 55563 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]: 55564 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]: 55563 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": 1.1660494804382324,
+            "min": 1.163506269454956,
+            "max": 1.5379496812820435,
+            "count": 295
+        },
+        "SoccerTwos.Policy.Entropy.sum": {
+            "value": 23582.18359375,
+            "min": 19643.19921875,
+            "max": 35234.51953125,
+            "count": 295
+        },
+        "SoccerTwos.Environment.EpisodeLength.mean": {
+            "value": 56.03409090909091,
+            "min": 51.357894736842105,
+            "max": 114.25,
+            "count": 295
+        },
+        "SoccerTwos.Environment.EpisodeLength.sum": {
+            "value": 19724.0,
+            "min": 18504.0,
+            "max": 20940.0,
+            "count": 295
+        },
+        "SoccerTwos.Self-play.ELO.mean": {
+            "value": 1765.943921066491,
+            "min": 1677.620447333749,
+            "max": 1765.943921066491,
+            "count": 295
+        },
+        "SoccerTwos.Self-play.ELO.sum": {
+            "value": 310806.1301077024,
+            "min": 151670.54174021896,
+            "max": 327663.5806721868,
+            "count": 295
+        },
+        "SoccerTwos.Step.mean": {
+            "value": 34999970.0,
+            "min": 32059955.0,
+            "max": 34999970.0,
+            "count": 295
+        },
+        "SoccerTwos.Step.sum": {
+            "value": 34999970.0,
+            "min": 32059955.0,
+            "max": 34999970.0,
+            "count": 295
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
+            "value": 0.001140120322816074,
+            "min": -0.10083454847335815,
+            "max": 0.042552459985017776,
+            "count": 295
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
+            "value": 0.19952106475830078,
+            "min": -14.988079071044922,
+            "max": 5.947393894195557,
+            "count": 295
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 0.0022361918818205595,
+            "min": -0.09997288882732391,
+            "max": 0.04147672653198242,
+            "count": 295
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 0.39133358001708984,
+            "min": -15.114870071411133,
+            "max": 5.880364894866943,
+            "count": 295
+        },
+        "SoccerTwos.Environment.CumulativeReward.mean": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 295
+        },
+        "SoccerTwos.Environment.CumulativeReward.sum": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 295
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.mean": {
+            "value": 0.046221715382167274,
+            "min": -0.3833907290010263,
+            "max": 0.2875151093915212,
+            "count": 295
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.sum": {
+            "value": 8.088800191879272,
+            "min": -57.89200007915497,
+            "max": 39.96460020542145,
+            "count": 295
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.mean": {
+            "value": 0.046221715382167274,
+            "min": -0.3833907290010263,
+            "max": 0.2875151093915212,
+            "count": 295
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.sum": {
+            "value": 8.088800191879272,
+            "min": -57.89200007915497,
+            "max": 39.96460020542145,
+            "count": 295
+        },
+        "SoccerTwos.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 295
+        },
+        "SoccerTwos.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 295
+        },
+        "SoccerTwos.Losses.PolicyLoss.mean": {
+            "value": 0.01998710645517955,
+            "min": 0.013047904896181232,
+            "max": 0.022752037628864248,
+            "count": 143
+        },
+        "SoccerTwos.Losses.PolicyLoss.sum": {
+            "value": 0.01998710645517955,
+            "min": 0.013047904896181232,
+            "max": 0.022752037628864248,
+            "count": 143
+        },
+        "SoccerTwos.Losses.ValueLoss.mean": {
+            "value": 0.09735343083739281,
+            "min": 0.07494692032535871,
+            "max": 0.10981472209095955,
+            "count": 143
+        },
+        "SoccerTwos.Losses.ValueLoss.sum": {
+            "value": 0.09735343083739281,
+            "min": 0.07494692032535871,
+            "max": 0.10981472209095955,
+            "count": 143
+        },
+        "SoccerTwos.Losses.BaselineLoss.mean": {
+            "value": 0.09839346880714099,
+            "min": 0.07544731299082438,
+            "max": 0.11057015061378479,
+            "count": 143
+        },
+        "SoccerTwos.Losses.BaselineLoss.sum": {
+            "value": 0.09839346880714099,
+            "min": 0.07544731299082438,
+            "max": 0.11057015061378479,
+            "count": 143
+        },
+        "SoccerTwos.Policy.LearningRate.mean": {
+            "value": 0.00019999999999999996,
+            "min": 0.00019999999999999996,
+            "max": 0.00019999999999999996,
+            "count": 143
+        },
+        "SoccerTwos.Policy.LearningRate.sum": {
+            "value": 0.00019999999999999996,
+            "min": 0.00019999999999999996,
+            "max": 0.00019999999999999996,
+            "count": 143
+        },
+        "SoccerTwos.Policy.Epsilon.mean": {
+            "value": 0.20000000000000007,
+            "min": 0.20000000000000007,
+            "max": 0.20000000000000007,
+            "count": 143
+        },
+        "SoccerTwos.Policy.Epsilon.sum": {
+            "value": 0.20000000000000007,
+            "min": 0.20000000000000007,
+            "max": 0.20000000000000007,
+            "count": 143
+        },
+        "SoccerTwos.Policy.Beta.mean": {
+            "value": 0.003000000000000001,
+            "min": 0.003000000000000001,
+            "max": 0.003000000000000001,
+            "count": 143
+        },
+        "SoccerTwos.Policy.Beta.sum": {
+            "value": 0.003000000000000001,
+            "min": 0.003000000000000001,
+            "max": 0.003000000000000001,
+            "count": 143
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1714002747",
+        "python_version": "3.10.12 | packaged by conda-forge | (main, Jun 23 2023, 22:40:32) [GCC 12.3.0]",
+        "command_line_arguments": "/home/luyijie/anaconda3/envs/rl/bin/mlagents-learn ./config/SoccerTwos/poca_3_layer_15M.yaml --env=../test_env/SoccerTwos.x86_64 --run-id=poca_3_layer_run2 --resume --no-graphics",
+        "mlagents_version": "1.1.0.dev0",
+        "mlagents_envs_version": "1.1.0.dev0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "2.2.2+cu121",
+        "numpy_version": "1.23.5",
+        "end_time_seconds": "1714006276"
+    },
+    "total": 3528.3960621570004,
+    "count": 1,
+    "self": 0.21940860597533174,
+    "children": {
+        "run_training.setup": {
+            "total": 0.019762242009164765,
+            "count": 1,
+            "self": 0.019762242009164765
+        },
+        "TrainerController.start_learning": {
+            "total": 3528.156891309016,
+            "count": 1,
+            "self": 2.8068258461134974,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 1.0686781560070813,
+                    "count": 16,
+                    "self": 1.0686781560070813
+                },
+                "TrainerController.advance": {
+                    "total": 3524.159241624875,
+                    "count": 201816,
+                    "self": 2.9596669372403994,
+                    "children": {
+                        "env_step": {
+                            "total": 2688.116283382813,
+                            "count": 201816,
+                            "self": 2147.7309492602944,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 538.3741281694965,
+                                    "count": 201816,
+                                    "self": 19.001167727459688,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 519.3729604420369,
+                                            "count": 370430,
+                                            "self": 519.3729604420369
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 2.0112059530219994,
+                                    "count": 201816,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 3523.7675522350182,
+                                            "count": 201816,
+                                            "is_parallel": true,
+                                            "self": 1722.7399015523551,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.0015797200030647218,
+                                                            "count": 2,
+                                                            "is_parallel": true,
+                                                            "self": 0.00037731899647042155,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.0012024010065943003,
+                                                                    "count": 8,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0012024010065943003
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.0223209060204681,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.00048822598182596266,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.0002748020051512867,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0002748020051512867
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.020063389994902536,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.020063389994902536
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.0014944880385883152,
+                                                                    "count": 2,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00026823501684702933,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.001226253021741286,
+                                                                            "count": 8,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.001226253021741286
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "steps_from_proto": {
+                                                    "total": 0.016255242080660537,
+                                                    "count": 30,
+                                                    "is_parallel": true,
+                                                    "self": 0.0031940351182129234,
+                                                    "children": {
+                                                        "_process_rank_one_or_two_observation": {
+                                                            "total": 0.013061206962447613,
+                                                            "count": 120,
+                                                            "is_parallel": true,
+                                                            "self": 0.013061206962447613
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 1801.0113954405824,
+                                                    "count": 201815,
+                                                    "is_parallel": true,
+                                                    "self": 86.53916094452143,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 47.5667131379887,
+                                                            "count": 201815,
+                                                            "is_parallel": true,
+                                                            "self": 47.5667131379887
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 1435.8657774784951,
+                                                            "count": 201815,
+                                                            "is_parallel": true,
+                                                            "self": 1435.8657774784951
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 231.03974387957714,
+                                                            "count": 403630,
+                                                            "is_parallel": true,
+                                                            "self": 44.62914385346812,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 186.41060002610902,
+                                                                    "count": 1614520,
+                                                                    "is_parallel": true,
+                                                                    "self": 186.41060002610902
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 833.0832913048216,
+                            "count": 201816,
+                            "self": 21.082576109969523,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 280.2782274468045,
+                                    "count": 201816,
+                                    "self": 279.4932862937858,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 0.7849411530187353,
+                                            "count": 6,
+                                            "self": 0.7849411530187353
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 531.7224877480476,
+                                    "count": 143,
+                                    "self": 212.42356030928204,
+                                    "children": {
+                                        "TorchPOCAOptimizer.update": {
+                                            "total": 319.29892743876553,
+                                            "count": 4290,
+                                            "self": 319.29892743876553
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 5.00003807246685e-07,
+                    "count": 1,
+                    "self": 5.00003807246685e-07
+                },
+                "TrainerController._save_models": {
+                    "total": 0.12214518201653846,
+                    "count": 1,
+                    "self": 0.00182851601857692,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.12031666599796154,
+                            "count": 1,
+                            "self": 0.12031666599796154
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,66 @@
+{
+    "SoccerTwos": {
+        "checkpoints": [
+            {
+                "steps": 33499985,
+                "file_path": "results/poca_3_layer_run2/SoccerTwos/SoccerTwos-33499985.onnx",
+                "reward": 0.0,
+                "creation_time": 1714004682.0488105,
+                "auxillary_file_paths": [
+                    "results/poca_3_layer_run2/SoccerTwos/SoccerTwos-33499985.pt"
+                ]
+            },
+            {
+                "steps": 33999912,
+                "file_path": "results/poca_3_layer_run2/SoccerTwos/SoccerTwos-33999912.onnx",
+                "reward": 0.0,
+                "creation_time": 1714005218.0183423,
+                "auxillary_file_paths": [
+                    "results/poca_3_layer_run2/SoccerTwos/SoccerTwos-33999912.pt"
+                ]
+            },
+            {
+                "steps": 34499999,
+                "file_path": "results/poca_3_layer_run2/SoccerTwos/SoccerTwos-34499999.onnx",
+                "reward": 0.0,
+                "creation_time": 1714005748.2461889,
+                "auxillary_file_paths": [
+                    "results/poca_3_layer_run2/SoccerTwos/SoccerTwos-34499999.pt"
+                ]
+            },
+            {
+                "steps": 34999970,
+                "file_path": "results/poca_3_layer_run2/SoccerTwos/SoccerTwos-34999970.onnx",
+                "reward": 0.0,
+                "creation_time": 1714006275.9874969,
+                "auxillary_file_paths": [
+                    "results/poca_3_layer_run2/SoccerTwos/SoccerTwos-34999970.pt"
+                ]
+            },
+            {
+                "steps": 35000046,
+                "file_path": "results/poca_3_layer_run2/SoccerTwos/SoccerTwos-35000046.onnx",
+                "reward": 0.0,
+                "creation_time": 1714006276.1177914,
+                "auxillary_file_paths": [
+                    "results/poca_3_layer_run2/SoccerTwos/SoccerTwos-35000046.pt"
+                ]
+            }
+        ],
+        "elo": 1768.568042898388,
+        "final_checkpoint": {
+            "steps": 35000046,
+            "file_path": "results/poca_3_layer_run2/SoccerTwos.onnx",
+            "reward": 0.0,
+            "creation_time": 1714006276.1177914,
+            "auxillary_file_paths": [
+                "results/poca_3_layer_run2/SoccerTwos/SoccerTwos-35000046.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "1.1.0.dev0",
+        "torch_version": "2.2.2+cu121"
+    }
+}