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-v5
+  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:a24c105f4281625c0db27952c4077db44e7dd3e8be640388a1e275655320b560
+size 1764633

SoccerTwos/SoccerTwos-13499998.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d551244034f645b38d67f2751f85c83e73cda42cddf29faff9dc29024f70112
+size 1764633

SoccerTwos/SoccerTwos-13499998.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:385b38b66c7cbb92f5b5e6eccc1af9f1d53f099fde1aa57c812bcebc04e2f8aa
+size 28421201

SoccerTwos/SoccerTwos-13999931.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1300095ac1a61b76f37b0706c3d8b491420a2cbb967e8e6de8eb9759d9ab8520
+size 1764633

SoccerTwos/SoccerTwos-13999931.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b03898bfbeaeeb60c3ef243f34176caec3caed634a5e9c11c2274af3e7765ba
+size 28421201

SoccerTwos/SoccerTwos-14499978.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc1e9b039f252fbf1b2ea408caa239f90df02c9a339f0b3ba99513a01f0fcf06
+size 1764633

SoccerTwos/SoccerTwos-14499978.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21f65c799cb8a5741c64c745234b76583bab713b12cb0a1e4562ecd761804520
+size 28421201

SoccerTwos/SoccerTwos-14999930.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a24c105f4281625c0db27952c4077db44e7dd3e8be640388a1e275655320b560
+size 1764633

SoccerTwos/SoccerTwos-14999930.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba35747b4d11b8205fff126f35945254118c1bdc4ea25d7b86c1f0546c9c2840
+size 28421201

SoccerTwos/SoccerTwos-15000100.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a24c105f4281625c0db27952c4077db44e7dd3e8be640388a1e275655320b560
+size 1764633

SoccerTwos/SoccerTwos-15000100.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d8f9a3578bc2483d6e01b6e925b5c11b80c36a4f5ad7f1431cee0fbb39c0295
+size 28421201

SoccerTwos/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d8f9a3578bc2483d6e01b6e925b5c11b80c36a4f5ad7f1431cee0fbb39c0295
+size 28421201

SoccerTwos/events.out.tfevents.1675723668.liuyz_T480.6987.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9ddcfc4497011702ccaf3fdec5df2cf76ea0cc2243e8ab9f060f975e06cfb83
+size 9860424

SoccerTwos/events.out.tfevents.1675764875.liuyz_T480.8956.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cbc6986b576c6ac028950a5d20767e329b5a1e6e43e9dd79eeba8912d4eb936
+size 2056755

SoccerTwos/events.out.tfevents.1675923541.liuyz_T480.15744.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29d53df8ec821f1af82b53247aad13cdfc17cf8bc2537b94ae4a072b0b414356
+size 3084363

config.json

@@ -0,0 +1 @@
+{"default_settings": null, "behaviors": {"SoccerTwos": {"trainer_type": "poca", "hyperparameters": {"batch_size": 2048, "buffer_size": 20480, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "learning_rate_schedule": "constant", "beta_schedule": "constant", "epsilon_schedule": "constant"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 15000000, "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: 2
+      vis_encode_type: simple
+      memory: null
+      goal_conditioning_type: hyper
+      deterministic: false
+    reward_signals:
+      extrinsic:
+        gamma: 0.99
+        strength: 1.0
+        network_settings:
+          normalize: false
+          hidden_units: 128
+          num_layers: 2
+          vis_encode_type: simple
+          memory: null
+          goal_conditioning_type: hyper
+          deterministic: false
+    init_path: null
+    keep_checkpoints: 5
+    even_checkpoints: false
+    max_steps: 15000000
+    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 +1,304 @@
+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  0.124 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: 0.938400 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]: 56482 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 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_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 0.7 KB
+      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 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]: 56483 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 4.9 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 56483 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]: 56482 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]: 56483 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]: 56483 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]: 56482 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]: 56483 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]: 56482 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": 1.542044997215271,
+            "min": 1.440100073814392,
+            "max": 1.6137632131576538,
+            "count": 300
+        },
+        "SoccerTwos.Policy.Entropy.sum": {
+            "value": 32814.71875,
+            "min": 25896.232421875,
+            "max": 35227.22265625,
+            "count": 300
+        },
+        "SoccerTwos.Environment.EpisodeLength.mean": {
+            "value": 58.80952380952381,
+            "min": 44.72477064220183,
+            "max": 86.49122807017544,
+            "count": 300
+        },
+        "SoccerTwos.Environment.EpisodeLength.sum": {
+            "value": 19760.0,
+            "min": 18724.0,
+            "max": 20772.0,
+            "count": 300
+        },
+        "SoccerTwos.Self-play.ELO.mean": {
+            "value": 1653.1870649019568,
+            "min": 1567.552494060283,
+            "max": 1655.0609915835641,
+            "count": 300
+        },
+        "SoccerTwos.Self-play.ELO.sum": {
+            "value": 277735.42690352874,
+            "min": 185288.5933308388,
+            "max": 353285.91771309637,
+            "count": 300
+        },
+        "SoccerTwos.Step.mean": {
+            "value": 14999930.0,
+            "min": 12009982.0,
+            "max": 14999930.0,
+            "count": 300
+        },
+        "SoccerTwos.Step.sum": {
+            "value": 14999930.0,
+            "min": 12009982.0,
+            "max": 14999930.0,
+            "count": 300
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
+            "value": -0.04682938754558563,
+            "min": -0.11298096179962158,
+            "max": 0.093830406665802,
+            "count": 300
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
+            "value": -7.820508003234863,
+            "min": -17.991260528564453,
+            "max": 17.358625411987305,
+            "count": 300
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
+            "value": -0.04404613748192787,
+            "min": -0.10972505807876587,
+            "max": 0.09695275872945786,
+            "count": 300
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
+            "value": -7.3557047843933105,
+            "min": -17.871688842773438,
+            "max": 17.936260223388672,
+            "count": 300
+        },
+        "SoccerTwos.Environment.CumulativeReward.mean": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 300
+        },
+        "SoccerTwos.Environment.CumulativeReward.sum": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 300
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.mean": {
+            "value": -0.12098922201259407,
+            "min": -0.2797437529079616,
+            "max": 0.27960924881731153,
+            "count": 300
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.sum": {
+            "value": -20.20520007610321,
+            "min": -46.605599999427795,
+            "max": 48.3724000453949,
+            "count": 300
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.mean": {
+            "value": -0.12098922201259407,
+            "min": -0.2797437529079616,
+            "max": 0.27960924881731153,
+            "count": 300
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.sum": {
+            "value": -20.20520007610321,
+            "min": -46.605599999427795,
+            "max": 48.3724000453949,
+            "count": 300
+        },
+        "SoccerTwos.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 300
+        },
+        "SoccerTwos.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 300
+        },
+        "SoccerTwos.Losses.PolicyLoss.mean": {
+            "value": 0.016679967249122758,
+            "min": 0.013073392383133372,
+            "max": 0.024770521942991765,
+            "count": 145
+        },
+        "SoccerTwos.Losses.PolicyLoss.sum": {
+            "value": 0.016679967249122758,
+            "min": 0.013073392383133372,
+            "max": 0.024770521942991765,
+            "count": 145
+        },
+        "SoccerTwos.Losses.ValueLoss.mean": {
+            "value": 0.10101278101404508,
+            "min": 0.08707024628917376,
+            "max": 0.11337359274427096,
+            "count": 145
+        },
+        "SoccerTwos.Losses.ValueLoss.sum": {
+            "value": 0.10101278101404508,
+            "min": 0.08707024628917376,
+            "max": 0.11337359274427096,
+            "count": 145
+        },
+        "SoccerTwos.Losses.BaselineLoss.mean": {
+            "value": 0.10257193421324094,
+            "min": 0.08828358178337416,
+            "max": 0.11552387624979019,
+            "count": 145
+        },
+        "SoccerTwos.Losses.BaselineLoss.sum": {
+            "value": 0.10257193421324094,
+            "min": 0.08828358178337416,
+            "max": 0.11552387624979019,
+            "count": 145
+        },
+        "SoccerTwos.Policy.LearningRate.mean": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 145
+        },
+        "SoccerTwos.Policy.LearningRate.sum": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 145
+        },
+        "SoccerTwos.Policy.Epsilon.mean": {
+            "value": 0.20000000000000007,
+            "min": 0.20000000000000007,
+            "max": 0.20000000000000007,
+            "count": 145
+        },
+        "SoccerTwos.Policy.Epsilon.sum": {
+            "value": 0.20000000000000007,
+            "min": 0.20000000000000007,
+            "max": 0.20000000000000007,
+            "count": 145
+        },
+        "SoccerTwos.Policy.Beta.mean": {
+            "value": 0.005000000000000001,
+            "min": 0.005000000000000001,
+            "max": 0.005000000000000001,
+            "count": 145
+        },
+        "SoccerTwos.Policy.Beta.sum": {
+            "value": 0.005000000000000001,
+            "min": 0.005000000000000001,
+            "max": 0.005000000000000001,
+            "count": 145
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1675923540",
+        "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.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": "1675935835"
+    },
+    "total": 12295.671090400021,
+    "count": 1,
+    "self": 0.32222739997087047,
+    "children": {
+        "run_training.setup": {
+            "total": 0.047608000051695853,
+            "count": 1,
+            "self": 0.047608000051695853
+        },
+        "TrainerController.start_learning": {
+            "total": 12295.301254999998,
+            "count": 1,
+            "self": 7.271457104652654,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 1.7654651998891495,
+                    "count": 16,
+                    "self": 1.7654651998891495
+                },
+                "TrainerController.advance": {
+                    "total": 12285.502733295492,
+                    "count": 207000,
+                    "self": 7.892098882293794,
+                    "children": {
+                        "env_step": {
+                            "total": 6744.709322719427,
+                            "count": 207000,
+                            "self": 5854.004936416459,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 886.3216951006325,
+                                    "count": 207000,
+                                    "self": 38.47987049946096,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 847.8418246011715,
+                                            "count": 376556,
+                                            "self": 847.8418246011715
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 4.382691202335991,
+                                    "count": 207000,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 12277.59570988745,
+                                            "count": 207000,
+                                            "is_parallel": true,
+                                            "self": 7156.613118898065,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.004712300025857985,
+                                                            "count": 2,
+                                                            "is_parallel": true,
+                                                            "self": 0.0014410000294446945,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.0032712999964132905,
+                                                                    "count": 8,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0032712999964132905
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.059866299969144166,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0009093000553548336,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.0013091000146232545,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0013091000146232545
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.055025899957399815,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.055025899957399815
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.002621999941766262,
+                                                                    "count": 2,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.000580199935939163,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.002041800005827099,
+                                                                            "count": 8,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.002041800005827099
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "steps_from_proto": {
+                                                    "total": 0.034881899948231876,
+                                                    "count": 30,
+                                                    "is_parallel": true,
+                                                    "self": 0.007476300408598036,
+                                                    "children": {
+                                                        "_process_rank_one_or_two_observation": {
+                                                            "total": 0.02740559953963384,
+                                                            "count": 120,
+                                                            "is_parallel": true,
+                                                            "self": 0.02740559953963384
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 5120.947709089436,
+                                                    "count": 206999,
+                                                    "is_parallel": true,
+                                                    "self": 169.77864146704087,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 129.137426803587,
+                                                            "count": 206999,
+                                                            "is_parallel": true,
+                                                            "self": 129.137426803587
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 4308.419570893282,
+                                                            "count": 206999,
+                                                            "is_parallel": true,
+                                                            "self": 4308.419570893282
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 513.6120699255262,
+                                                            "count": 413998,
+                                                            "is_parallel": true,
+                                                            "self": 112.80534110986628,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 400.8067288156599,
+                                                                    "count": 1655992,
+                                                                    "is_parallel": true,
+                                                                    "self": 400.8067288156599
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 5532.901311693771,
+                            "count": 207000,
+                            "self": 41.952493078657426,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 997.4942364149028,
+                                    "count": 207000,
+                                    "self": 996.1923424148699,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 1.3018940000329167,
+                                            "count": 6,
+                                            "self": 1.3018940000329167
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 4493.454582200211,
+                                    "count": 145,
+                                    "self": 565.9212106984342,
+                                    "children": {
+                                        "TorchPOCAOptimizer.update": {
+                                            "total": 3927.533371501777,
+                                            "count": 4350,
+                                            "self": 3927.533371501777
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 1.9999570213258266e-06,
+                    "count": 1,
+                    "self": 1.9999570213258266e-06
+                },
+                "TrainerController._save_models": {
+                    "total": 0.7615974000073038,
+                    "count": 1,
+                    "self": 0.0016035999869927764,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.759993800020311,
+                            "count": 1,
+                            "self": 0.759993800020311
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,66 @@
+{
+    "SoccerTwos": {
+        "checkpoints": [
+            {
+                "steps": 13499998,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-13499998.onnx",
+                "reward": 0.0,
+                "creation_time": 1675929914.7548213,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-13499998.pt"
+                ]
+            },
+            {
+                "steps": 13999931,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-13999931.onnx",
+                "reward": 0.0,
+                "creation_time": 1675931897.7630072,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-13999931.pt"
+                ]
+            },
+            {
+                "steps": 14499978,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-14499978.onnx",
+                "reward": 0.0,
+                "creation_time": 1675933853.944905,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-14499978.pt"
+                ]
+            },
+            {
+                "steps": 14999930,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-14999930.onnx",
+                "reward": 0.0,
+                "creation_time": 1675935834.8601189,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-14999930.pt"
+                ]
+            },
+            {
+                "steps": 15000100,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-15000100.onnx",
+                "reward": 0.0,
+                "creation_time": 1675935835.6612217,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-15000100.pt"
+                ]
+            }
+        ],
+        "elo": 1651.7468079886064,
+        "final_checkpoint": {
+            "steps": 15000100,
+            "file_path": "results/SoccerTwos/SoccerTwos.onnx",
+            "reward": 0.0,
+            "creation_time": 1675935835.6612217,
+            "auxillary_file_paths": [
+                "results/SoccerTwos/SoccerTwos/SoccerTwos-15000100.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "0.31.0.dev0",
+        "torch_version": "1.11.0+cu102"
+    }
+}