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: yizhangliu/poca-SoccerTwos-v7
+  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:c81d50c5ae95ff5426393317b8b426b9381291b18ce88eed0aed3b6effd11357
+size 2815689

SoccerTwos/SoccerTwos-23499838.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ea016b671255dac44b09b34410198623567f59bfef4105ddb0107efdbfab143
+size 2815689

SoccerTwos/SoccerTwos-23499838.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3eebbe7141f2d401a180300635017cd431bc489a2df18b7a2469f7af2e01aec
+size 34728689

SoccerTwos/SoccerTwos-23999936.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f488d0b8baab7a321d9078de3959872287c6c165d07fd6e184b2cf90e243d8d
+size 2815689

SoccerTwos/SoccerTwos-23999936.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d8e4d88237c987b4e8c872ecd8e144f11b7f37ac03fbfb46992e31cb85e2131
+size 34728689

SoccerTwos/SoccerTwos-24499921.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ab2ace3dab782c1b589231137f7a854e1fd6bb38327476aeb00a4be0140a548
+size 2815689

SoccerTwos/SoccerTwos-24499921.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a92b71792783eee9e2af590ccd5c716d9a92f87fd2c73053adbcbc0e7148d94
+size 34728689

SoccerTwos/SoccerTwos-24999978.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c81d50c5ae95ff5426393317b8b426b9381291b18ce88eed0aed3b6effd11357
+size 2815689

SoccerTwos/SoccerTwos-24999978.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:725fff86076e58387d9cea8401a00303488d915190e0e87961c03719bd6c32e1
+size 34728689

SoccerTwos/SoccerTwos-25000130.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c81d50c5ae95ff5426393317b8b426b9381291b18ce88eed0aed3b6effd11357
+size 2815689

SoccerTwos/SoccerTwos-25000130.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a8df5e0c7881525be22fa74639a7dd511f489278e0c316d6d21fa280e14e81d
+size 34728689

SoccerTwos/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a8df5e0c7881525be22fa74639a7dd511f489278e0c316d6d21fa280e14e81d
+size 34728689

SoccerTwos/events.out.tfevents.1675807222.liuyz_T480.11474.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce8eb6e162f36f949c23510b50558db1fdb6218ae6c39f72a30a64103591128d
+size 5424217

SoccerTwos/events.out.tfevents.1675857683.liuyz_T480.12757.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c1e76f311e3171033277ec4b7481918400ad2cdf992183e6315b8d750a82298
+size 10180700

SoccerTwos/events.out.tfevents.1675995124.liuyz_T480.18429.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a195743053eafcc5eb7b9369104a08f89348ce701b69fc9b18e6b31a6983586
+size 5098059

config.json

@@ -0,0 +1 @@
+{"default_settings": null, "behaviors": {"SoccerTwos": {"trainer_type": "poca", "hyperparameters": {"batch_size": 2048, "buffer_size": 40960, "learning_rate": 0.0001, "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": 25000000, "time_horizon": 2048, "summary_freq": 10000, "threaded": false, "self_play": {"save_steps": 50000, "team_change": 250000, "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: 40960
+      learning_rate: 0.0001
+      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: 25000000
+    time_horizon: 2048
+    summary_freq: 10000
+    threaded: false
+    self_play:
+      save_steps: 50000
+      team_change: 250000
+      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 +1,304 @@
+Mono path[0] = '/home/liuyz/ml-agents/training-envs-executables/SoccerTwos/SoccerTwos_Data/Managed'
+Mono config path = '/home/liuyz/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/liuyz/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
+ALSA lib confmisc.c:767:(parse_card) cannot find card '0'
+ALSA lib conf.c:4732:(_snd_config_evaluate) function snd_func_card_driver returned error: No such file or directory
+ALSA lib confmisc.c:392:(snd_func_concat) error evaluating strings
+ALSA lib conf.c:4732:(_snd_config_evaluate) function snd_func_concat returned error: No such file or directory
+ALSA lib confmisc.c:1246:(snd_func_refer) error evaluating name
+ALSA lib conf.c:4732:(_snd_config_evaluate) function snd_func_refer returned error: No such file or directory
+ALSA lib conf.c:5220:(snd_config_expand) Evaluate error: No such file or directory
+ALSA lib pcm.c:2642:(snd_pcm_open_noupdate) Unknown PCM default
+FMOD failed to initialize the output device.: "Error initializing output device. " (60)
+Forced to initialize FMOD to to the device driver's system output rate 48000, this may impact performance and/or give inconsistent experiences compared to selected sample rate 48000
+ALSA lib confmisc.c:767:(parse_card) cannot find card '0'
+ALSA lib conf.c:4732:(_snd_config_evaluate) function snd_func_card_driver returned error: No such file or directory
+ALSA lib confmisc.c:392:(snd_func_concat) error evaluating strings
+ALSA lib conf.c:4732:(_snd_config_evaluate) function snd_func_concat returned error: No such file or directory
+ALSA lib confmisc.c:1246:(snd_func_refer) error evaluating name
+ALSA lib conf.c:4732:(_snd_config_evaluate) function snd_func_refer returned error: No such file or directory
+ALSA lib conf.c:5220:(snd_config_expand) Evaluate error: No such file or directory
+ALSA lib pcm.c:2642:(snd_pcm_open_noupdate) Unknown PCM default
+FMOD failed to initialize the output device.: "Error initializing output device. " (60)
+FMOD initialized on nosound output
+Begin MonoManager ReloadAssembly
+- Completed reload, in  0.127 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: 1.295200 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 4 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]: 94060 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 4
+      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 7
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 5]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 13]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_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_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 6
+    [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]: 94061 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]: 94061 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]: 94060 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]: 94061 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]: 94061 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]: 94060 frames, [4.0 MB-8.0 MB]: 1 frames
+      Requested Block Size 4.0 MB
+      Peak Block count 2
+      Peak Allocated memory 4.4 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]: 94061 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]: 94060 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": 1.9021496772766113,
+            "min": 1.8278286457061768,
+            "max": 2.0336482524871826,
+            "count": 500
+        },
+        "SoccerTwos.Policy.Entropy.sum": {
+            "value": 39808.1875,
+            "min": 31856.9765625,
+            "max": 49968.15234375,
+            "count": 500
+        },
+        "SoccerTwos.Environment.EpisodeLength.mean": {
+            "value": 56.15909090909091,
+            "min": 44.46363636363636,
+            "max": 103.45833333333333,
+            "count": 500
+        },
+        "SoccerTwos.Environment.EpisodeLength.sum": {
+            "value": 19768.0,
+            "min": 18588.0,
+            "max": 20676.0,
+            "count": 500
+        },
+        "SoccerTwos.Self-play.ELO.mean": {
+            "value": 1555.385077202667,
+            "min": 1494.539175487284,
+            "max": 1576.1815326925348,
+            "count": 500
+        },
+        "SoccerTwos.Self-play.ELO.sum": {
+            "value": 273747.77358766936,
+            "min": 148491.1755175332,
+            "max": 336654.3063271615,
+            "count": 500
+        },
+        "SoccerTwos.Step.mean": {
+            "value": 24999978.0,
+            "min": 20009991.0,
+            "max": 24999978.0,
+            "count": 500
+        },
+        "SoccerTwos.Step.sum": {
+            "value": 24999978.0,
+            "min": 20009991.0,
+            "max": 24999978.0,
+            "count": 500
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
+            "value": -0.01763874664902687,
+            "min": -0.10776752978563309,
+            "max": 0.07479347288608551,
+            "count": 500
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
+            "value": -3.086780548095703,
+            "min": -17.547164916992188,
+            "max": 12.565303802490234,
+            "count": 500
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
+            "value": -0.01813901588320732,
+            "min": -0.11023017019033432,
+            "max": 0.0698384940624237,
+            "count": 500
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
+            "value": -3.174327850341797,
+            "min": -18.204742431640625,
+            "max": 11.732867240905762,
+            "count": 500
+        },
+        "SoccerTwos.Environment.CumulativeReward.mean": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 500
+        },
+        "SoccerTwos.Environment.CumulativeReward.sum": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 500
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.mean": {
+            "value": 0.0786628542627607,
+            "min": -0.34376484986507533,
+            "max": 0.4665142857298559,
+            "count": 500
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.sum": {
+            "value": 13.765999495983124,
+            "min": -59.32819986343384,
+            "max": 47.49799942970276,
+            "count": 500
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.mean": {
+            "value": 0.0786628542627607,
+            "min": -0.34376484986507533,
+            "max": 0.4665142857298559,
+            "count": 500
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.sum": {
+            "value": 13.765999495983124,
+            "min": -59.32819986343384,
+            "max": 47.49799942970276,
+            "count": 500
+        },
+        "SoccerTwos.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 500
+        },
+        "SoccerTwos.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 500
+        },
+        "SoccerTwos.Losses.PolicyLoss.mean": {
+            "value": 0.01652876395867982,
+            "min": 0.013891844534009578,
+            "max": 0.023010420791979413,
+            "count": 121
+        },
+        "SoccerTwos.Losses.PolicyLoss.sum": {
+            "value": 0.01652876395867982,
+            "min": 0.013891844534009578,
+            "max": 0.023010420791979413,
+            "count": 121
+        },
+        "SoccerTwos.Losses.ValueLoss.mean": {
+            "value": 0.10607224243382612,
+            "min": 0.08422205423315367,
+            "max": 0.1170943199346463,
+            "count": 121
+        },
+        "SoccerTwos.Losses.ValueLoss.sum": {
+            "value": 0.10607224243382612,
+            "min": 0.08422205423315367,
+            "max": 0.1170943199346463,
+            "count": 121
+        },
+        "SoccerTwos.Losses.BaselineLoss.mean": {
+            "value": 0.10775665591160456,
+            "min": 0.08507357910275459,
+            "max": 0.11834435512622198,
+            "count": 121
+        },
+        "SoccerTwos.Losses.BaselineLoss.sum": {
+            "value": 0.10775665591160456,
+            "min": 0.08507357910275459,
+            "max": 0.11834435512622198,
+            "count": 121
+        },
+        "SoccerTwos.Policy.LearningRate.mean": {
+            "value": 0.00010000000000000003,
+            "min": 0.00010000000000000003,
+            "max": 0.00010000000000000003,
+            "count": 121
+        },
+        "SoccerTwos.Policy.LearningRate.sum": {
+            "value": 0.00010000000000000003,
+            "min": 0.00010000000000000003,
+            "max": 0.00010000000000000003,
+            "count": 121
+        },
+        "SoccerTwos.Policy.Epsilon.mean": {
+            "value": 0.19999999999999993,
+            "min": 0.19999999999999993,
+            "max": 0.19999999999999993,
+            "count": 121
+        },
+        "SoccerTwos.Policy.Epsilon.sum": {
+            "value": 0.19999999999999993,
+            "min": 0.19999999999999993,
+            "max": 0.19999999999999993,
+            "count": 121
+        },
+        "SoccerTwos.Policy.Beta.mean": {
+            "value": 0.005000000000000001,
+            "min": 0.005000000000000001,
+            "max": 0.005000000000000001,
+            "count": 121
+        },
+        "SoccerTwos.Policy.Beta.sum": {
+            "value": 0.005000000000000001,
+            "min": 0.005000000000000001,
+            "max": 0.005000000000000001,
+            "count": 121
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1675995123",
+        "python_version": "3.9.16 (main, Feb  6 2023, 20:06:40) \n[GCC 9.3.0]",
+        "command_line_arguments": "/usr/bin/mlagents-learn ./config/poca/SoccerTwos_v4.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": "1.11.0+cu102",
+        "numpy_version": "1.21.2",
+        "end_time_seconds": "1676016142"
+    },
+    "total": 21019.160699600005,
+    "count": 1,
+    "self": 0.4239419000223279,
+    "children": {
+        "run_training.setup": {
+            "total": 0.02791030000662431,
+            "count": 1,
+            "self": 0.02791030000662431
+        },
+        "TrainerController.start_learning": {
+            "total": 21018.708847399976,
+            "count": 1,
+            "self": 12.252090293797664,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 1.578472400084138,
+                    "count": 21,
+                    "self": 1.578472400084138
+                },
+                "TrainerController.advance": {
+                    "total": 21004.07154440612,
+                    "count": 346217,
+                    "self": 13.339027916430496,
+                    "children": {
+                        "env_step": {
+                            "total": 11195.647434503247,
+                            "count": 346217,
+                            "self": 9608.978213496332,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 1579.37136202713,
+                                    "count": 346217,
+                                    "self": 65.21483358863043,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 1514.1565284384997,
+                                            "count": 627082,
+                                            "self": 1514.1565284384997
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 7.297858979785815,
+                                    "count": 346217,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 20991.833144892298,
+                                            "count": 346217,
+                                            "is_parallel": true,
+                                            "self": 12627.482296909031,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.004215100023429841,
+                                                            "count": 2,
+                                                            "is_parallel": true,
+                                                            "self": 0.0011841999948956072,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.0030309000285342336,
+                                                                    "count": 8,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0030309000285342336
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.034806600015144795,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0005694999708794057,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.00045980000868439674,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00045980000868439674
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.032166399993002415,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.032166399993002415
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.001610900042578578,
+                                                                    "count": 2,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00036669994005933404,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.001244200102519244,
+                                                                            "count": 8,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.001244200102519244
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "steps_from_proto": {
+                                                    "total": 0.04493440012447536,
+                                                    "count": 40,
+                                                    "is_parallel": true,
+                                                    "self": 0.009977000067010522,
+                                                    "children": {
+                                                        "_process_rank_one_or_two_observation": {
+                                                            "total": 0.03495740005746484,
+                                                            "count": 160,
+                                                            "is_parallel": true,
+                                                            "self": 0.03495740005746484
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 8364.305913583143,
+                                                    "count": 346216,
+                                                    "is_parallel": true,
+                                                    "self": 273.51644306909293,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 217.13113000715384,
+                                                            "count": 346216,
+                                                            "is_parallel": true,
+                                                            "self": 217.13113000715384
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 7046.747987709532,
+                                                            "count": 346216,
+                                                            "is_parallel": true,
+                                                            "self": 7046.747987709532
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 826.9103527973639,
+                                                            "count": 692432,
+                                                            "is_parallel": true,
+                                                            "self": 182.80608186731115,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 644.1042709300527,
+                                                                    "count": 2769728,
+                                                                    "is_parallel": true,
+                                                                    "self": 644.1042709300527
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 9795.085081986443,
+                            "count": 346217,
+                            "self": 69.57300218037562,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 1763.8578488061903,
+                                    "count": 346217,
+                                    "self": 1761.022810106224,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 2.8350386999663897,
+                                            "count": 10,
+                                            "self": 2.8350386999663897
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 7961.654230999877,
+                                    "count": 121,
+                                    "self": 920.4508470981964,
+                                    "children": {
+                                        "TorchPOCAOptimizer.update": {
+                                            "total": 7041.20338390168,
+                                            "count": 7260,
+                                            "self": 7041.20338390168
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 2.4999608285725117e-06,
+                    "count": 1,
+                    "self": 2.4999608285725117e-06
+                },
+                "TrainerController._save_models": {
+                    "total": 0.8067378000123426,
+                    "count": 1,
+                    "self": 0.00272019999101758,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.804017600021325,
+                            "count": 1,
+                            "self": 0.804017600021325
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,66 @@
+{
+    "SoccerTwos": {
+        "checkpoints": [
+            {
+                "steps": 23499838,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-23499838.onnx",
+                "reward": 0.0,
+                "creation_time": 1676009879.863911,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-23499838.pt"
+                ]
+            },
+            {
+                "steps": 23999936,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-23999936.onnx",
+                "reward": 0.0,
+                "creation_time": 1676012134.3548849,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-23999936.pt"
+                ]
+            },
+            {
+                "steps": 24499921,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-24499921.onnx",
+                "reward": 0.0,
+                "creation_time": 1676014137.1423542,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-24499921.pt"
+                ]
+            },
+            {
+                "steps": 24999978,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-24999978.onnx",
+                "reward": 0.0,
+                "creation_time": 1676016141.245036,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-24999978.pt"
+                ]
+            },
+            {
+                "steps": 25000130,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-25000130.onnx",
+                "reward": 0.0,
+                "creation_time": 1676016142.1005976,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-25000130.pt"
+                ]
+            }
+        ],
+        "elo": 1559.1137301294127,
+        "final_checkpoint": {
+            "steps": 25000130,
+            "file_path": "results/SoccerTwos/SoccerTwos.onnx",
+            "reward": 0.0,
+            "creation_time": 1676016142.1005976,
+            "auxillary_file_paths": [
+                "results/SoccerTwos/SoccerTwos/SoccerTwos-25000130.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "0.31.0.dev0",
+        "torch_version": "1.11.0+cu102"
+    }
+}