First trained multi-agents

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: andyleow/poca-SoccerTwos
+  3. Step 2: Select your *.nn /*.onnx file
+  4. Click on Watch the agent play 👀
+  

SoccerTwos.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93d2bbef66c493c087884e9f28ecb052cfe74391cf33b56e3481a662b376443d
+size 1763423

SoccerTwos/SoccerTwos-0.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0026653c6c66527a5aa3b4a0a63b3f63c87b906d4882d7cf91668a1718f3396
+size 1763423

SoccerTwos/SoccerTwos-0.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb8d53a1386482f16e25665056c9ed71ca58ea14952f501304cc61f5b14b672d
+size 9478713

SoccerTwos/SoccerTwos-11999980.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:720689c776fd6c467a95250ee6beee71bbc02e7df255361feed5451911a95d0c
+size 1763423

SoccerTwos/SoccerTwos-11999980.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc8146c4bd4ac86a7be532be4c06641ac80691b2e148150f7c498a15a7c94b1a
+size 28422417

SoccerTwos/SoccerTwos-12499917.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7878fc595d802a034049bc92420294fd6c391fff15023df1bdd1fc8d47e77a67
+size 1763423

SoccerTwos/SoccerTwos-12499917.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc14e537de8105e7e42bf514ac687c03cde0c05c20ea211708509bbcb5b7d245
+size 28422417

SoccerTwos/SoccerTwos-12999890.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b20235127de69ab065470e01e1775da895fd97057fdd7fa4ee25b932ac03759
+size 1763423

SoccerTwos/SoccerTwos-12999890.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc503f59bac1d34d074caada59906bf8b0ccd5a59843b599b1548681c6ca5c68
+size 28422417

SoccerTwos/SoccerTwos-13499973.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be80866558314a280a628005420e7c2b15ac81f50b6bc2551a7f51d3ae5b6fef
+size 1763423

SoccerTwos/SoccerTwos-13499973.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e5470ae03ffc3a92508dfc2f57f2f4efffbd1b5a16cdd9071d95dc08ed42cc2
+size 28422417

SoccerTwos/SoccerTwos-13647362.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93d2bbef66c493c087884e9f28ecb052cfe74391cf33b56e3481a662b376443d
+size 1763423

SoccerTwos/SoccerTwos-13647362.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30fff713a94341ff5f1e03deee3e799058b3a8cfeff0e6fe28ae06e234fac0e6
+size 28422417

SoccerTwos/SoccerTwos-499194.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07f096cc5549198ed753d99244b3a998929ec09e6f0f0ec1f9ddc4e823fc6bc9
+size 1763423

SoccerTwos/SoccerTwos-499194.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b71b8a053d2bcc9f019ce2c64514d771bf2b443245da720eee77f56fe76411a0
+size 28422417

SoccerTwos/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30fff713a94341ff5f1e03deee3e799058b3a8cfeff0e6fe28ae06e234fac0e6
+size 28422417

SoccerTwos/events.out.tfevents.1682726715.andy-XPS-15-9520.420050.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36c5f591a5acecac3903bdbbf8b10e4be0105fba3fbc51d73f36c8727814d6d6
+size 53442

SoccerTwos/events.out.tfevents.1682790517.andy-XPS-15-9520.9942.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd370688ba20cdee715d5894b6e47edd9ab458115abedc8d7a9641d3c5826850
+size 519211

SoccerTwos/events.out.tfevents.1682792614.andy-XPS-15-9520.7613.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f8e4c444765c777294d73052f0eeb3eb8bb9457f0051e25c09988f8649ab797
+size 13495524

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": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "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": 50000000, "time_horizon": 1000, "summary_freq": 10000, "threaded": false, "self_play": {"save_steps": 50000, "team_change": 200000, "swap_steps": 10000, "window": 10, "play_against_latest_model_ratio": 0.5, "initial_elo": 1200.0}, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/SoccerTwos.exe", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SoccerTwos", "initialize_from": null, "load_model": false, "resume": true, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -0,0 +1,82 @@
+default_settings: null
+behaviors:
+  SoccerTwos:
+    trainer_type: poca
+    hyperparameters:
+      batch_size: 2048
+      buffer_size: 20480
+      learning_rate: 0.0003
+      beta: 0.005
+      epsilon: 0.2
+      lambd: 0.95
+      num_epoch: 3
+      learning_rate_schedule: linear
+      beta_schedule: linear
+      epsilon_schedule: linear
+    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: 50000000
+    time_horizon: 1000
+    summary_freq: 10000
+    threaded: false
+    self_play:
+      save_steps: 50000
+      team_change: 200000
+      swap_steps: 10000
+      window: 10
+      play_against_latest_model_ratio: 0.5
+      initial_elo: 1200.0
+    behavioral_cloning: null
+env_settings:
+  env_path: ./training-envs-executables/SoccerTwos.exe
+  env_args: null
+  base_port: 5005
+  num_envs: 1
+  num_areas: 1
+  seed: -1
+  max_lifetime_restarts: 10
+  restarts_rate_limit_n: 1
+  restarts_rate_limit_period_s: 60
+engine_settings:
+  width: 84
+  height: 84
+  quality_level: 5
+  time_scale: 20
+  target_frame_rate: -1
+  capture_frame_rate: 60
+  no_graphics: true
+environment_parameters: null
+checkpoint_settings:
+  run_id: SoccerTwos
+  initialize_from: null
+  load_model: false
+  resume: true
+  force: false
+  train_model: false
+  inference: false
+  results_dir: results
+torch_settings:
+  device: null
+debug: false

run_logs/Player-0.log

@@ -0,0 +1,411 @@
+Mono path[0] = '/home/andy/Learning/Code/DeepRL/ml-agents/training-envs-executables/SoccerTwos_Data/Managed'
+Mono config path = '/home/andy/Learning/Code/DeepRL/ml-agents/training-envs-executables/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/andy/Learning/Code/DeepRL/ml-agents/training-envs-executables/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  0.053 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: 0.354029 ms
+Registered Communicator in Agent.
+ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+requesting resize 84 x 84
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+TOO LONG
+GRPC Exception: Status(StatusCode=Cancelled, Detail="CANCELLED"). Disconnecting from trainer.
+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]: 247539 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 0.7 KB
+      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_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 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_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 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]: 247540 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]: 247540 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]: 247539 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]: 247540 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]: 247540 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]: 247539 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]: 247540 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]: 247539 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": 1.2389752864837646,
+            "min": 1.192740559577942,
+            "max": 3.195857286453247,
+            "count": 1315
+        },
+        "SoccerTwos.Policy.Entropy.sum": {
+            "value": 23669.3828125,
+            "min": 19074.072265625,
+            "max": 102130.59375,
+            "count": 1315
+        },
+        "SoccerTwos.Environment.EpisodeLength.mean": {
+            "value": 67.82191780821918,
+            "min": 39.53658536585366,
+            "max": 768.2857142857143,
+            "count": 1315
+        },
+        "SoccerTwos.Environment.EpisodeLength.sum": {
+            "value": 19804.0,
+            "min": 1964.0,
+            "max": 27560.0,
+            "count": 1315
+        },
+        "SoccerTwos.Self-play.ELO.mean": {
+            "value": 1660.927805186417,
+            "min": 1200.8382712135203,
+            "max": 1700.0138429330032,
+            "count": 1315
+        },
+        "SoccerTwos.Self-play.ELO.sum": {
+            "value": 242495.45955721688,
+            "min": 4815.796468811134,
+            "max": 389108.3581683973,
+            "count": 1315
+        },
+        "SoccerTwos.Step.mean": {
+            "value": 13639994.0,
+            "min": 499845.0,
+            "max": 13639994.0,
+            "count": 1315
+        },
+        "SoccerTwos.Step.sum": {
+            "value": 13639994.0,
+            "min": 499845.0,
+            "max": 13639994.0,
+            "count": 1315
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
+            "value": -0.03319062665104866,
+            "min": -0.1299733817577362,
+            "max": 0.17914806306362152,
+            "count": 1315
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
+            "value": -4.845831394195557,
+            "min": -23.12368392944336,
+            "max": 28.771757125854492,
+            "count": 1315
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
+            "value": -0.02986469678580761,
+            "min": -0.13352249562740326,
+            "max": 0.17410315573215485,
+            "count": 1315
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
+            "value": -4.360245704650879,
+            "min": -23.812545776367188,
+            "max": 27.896865844726562,
+            "count": 1315
+        },
+        "SoccerTwos.Environment.CumulativeReward.mean": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 1315
+        },
+        "SoccerTwos.Environment.CumulativeReward.sum": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 1315
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.mean": {
+            "value": -0.10844657764042893,
+            "min": -0.3918595745208416,
+            "max": 0.8689599871635437,
+            "count": 1315
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.sum": {
+            "value": -15.833200335502625,
+            "min": -53.9908002614975,
+            "max": 61.52560043334961,
+            "count": 1315
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.mean": {
+            "value": -0.10844657764042893,
+            "min": -0.3918595745208416,
+            "max": 0.8689599871635437,
+            "count": 1315
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.sum": {
+            "value": -15.833200335502625,
+            "min": -53.9908002614975,
+            "max": 61.52560043334961,
+            "count": 1315
+        },
+        "SoccerTwos.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 1315
+        },
+        "SoccerTwos.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 1315
+        },
+        "SoccerTwos.Losses.PolicyLoss.mean": {
+            "value": 0.01649892200754645,
+            "min": 0.010418944589522047,
+            "max": 0.02519332440181946,
+            "count": 637
+        },
+        "SoccerTwos.Losses.PolicyLoss.sum": {
+            "value": 0.01649892200754645,
+            "min": 0.010418944589522047,
+            "max": 0.02519332440181946,
+            "count": 637
+        },
+        "SoccerTwos.Losses.ValueLoss.mean": {
+            "value": 0.11030864467223485,
+            "min": 0.004580775909643207,
+            "max": 0.12992660452922186,
+            "count": 637
+        },
+        "SoccerTwos.Losses.ValueLoss.sum": {
+            "value": 0.11030864467223485,
+            "min": 0.004580775909643207,
+            "max": 0.12992660452922186,
+            "count": 637
+        },
+        "SoccerTwos.Losses.BaselineLoss.mean": {
+            "value": 0.1119449923435847,
+            "min": 0.005066171359632992,
+            "max": 0.13194381843010586,
+            "count": 637
+        },
+        "SoccerTwos.Losses.BaselineLoss.sum": {
+            "value": 0.1119449923435847,
+            "min": 0.005066171359632992,
+            "max": 0.13194381843010586,
+            "count": 637
+        },
+        "SoccerTwos.Policy.LearningRate.mean": {
+            "value": 0.00021822696325768804,
+            "min": 0.00021822696325768804,
+            "max": 0.00029685148904950407,
+            "count": 637
+        },
+        "SoccerTwos.Policy.LearningRate.sum": {
+            "value": 0.00021822696325768804,
+            "min": 0.00021822696325768804,
+            "max": 0.00029685148904950407,
+            "count": 637
+        },
+        "SoccerTwos.Policy.Epsilon.mean": {
+            "value": 0.1727423120000001,
+            "min": 0.1727423120000001,
+            "max": 0.19895049600000003,
+            "count": 637
+        },
+        "SoccerTwos.Policy.Epsilon.sum": {
+            "value": 0.1727423120000001,
+            "min": 0.1727423120000001,
+            "max": 0.19895049600000003,
+            "count": 637
+        },
+        "SoccerTwos.Policy.Beta.mean": {
+            "value": 0.003639841368799999,
+            "min": 0.003639841368799999,
+            "max": 0.0049476297504,
+            "count": 637
+        },
+        "SoccerTwos.Policy.Beta.sum": {
+            "value": 0.003639841368799999,
+            "min": 0.003639841368799999,
+            "max": 0.0049476297504,
+            "count": 637
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1682792614",
+        "python_version": "3.9.16 (main, Mar  8 2023, 14:00:05) \n[GCC 11.2.0]",
+        "command_line_arguments": "/home/andy/miniconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.exe --run-id=SoccerTwos --no-graphics --resume",
+        "mlagents_version": "0.31.0.dev0",
+        "mlagents_envs_version": "0.31.0.dev0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "1.9.1+cu111",
+        "numpy_version": "1.21.2",
+        "end_time_seconds": "1682805784"
+    },
+    "total": 13170.478400429001,
+    "count": 1,
+    "self": 0.11451995200150122,
+    "children": {
+        "run_training.setup": {
+            "total": 0.017183438000003548,
+            "count": 1,
+            "self": 0.017183438000003548
+        },
+        "TrainerController.start_learning": {
+            "total": 13170.346697039,
+            "count": 1,
+            "self": 13.617829919769065,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 3.810976455004166,
+                    "count": 67,
+                    "self": 3.810976455004166
+                },
+                "TrainerController.advance": {
+                    "total": 13152.806086595227,
+                    "count": 908619,
+                    "self": 13.606468632695396,
+                    "children": {
+                        "env_step": {
+                            "total": 9397.882361869435,
+                            "count": 908619,
+                            "self": 7379.434900308707,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 2010.5868766365184,
+                                    "count": 908619,
+                                    "self": 74.37173181011303,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 1936.2151448264053,
+                                            "count": 1650288,
+                                            "self": 1936.2151448264053
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 7.860584924209434,
+                                    "count": 908618,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 13150.660306459717,
+                                            "count": 908618,
+                                            "is_parallel": true,
+                                            "self": 7114.535387440636,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.0021984389999971654,
+                                                            "count": 2,
+                                                            "is_parallel": true,
+                                                            "self": 0.0007423129999750699,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.0014561260000220955,
+                                                                    "count": 8,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0014561260000220955
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.020773693999998954,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0005645100000180037,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.0002574309999943125,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0002574309999943125
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.018135178999997947,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.018135178999997947
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.001816573999988691,
+                                                                    "count": 2,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00036952799999312447,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.0014470459999955665,
+                                                                            "count": 8,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.0014470459999955665
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "steps_from_proto": {
+                                                    "total": 0.06438660299920684,
+                                                    "count": 132,
+                                                    "is_parallel": true,
+                                                    "self": 0.012203641987113656,
+                                                    "children": {
+                                                        "_process_rank_one_or_two_observation": {
+                                                            "total": 0.05218296101209319,
+                                                            "count": 528,
+                                                            "is_parallel": true,
+                                                            "self": 0.05218296101209319
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 6036.060532416081,
+                                                    "count": 908617,
+                                                    "is_parallel": true,
+                                                    "self": 353.9628599567386,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 188.69598787112716,
+                                                            "count": 908617,
+                                                            "is_parallel": true,
+                                                            "self": 188.69598787112716
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 4560.231735345039,
+                                                            "count": 908617,
+                                                            "is_parallel": true,
+                                                            "self": 4560.231735345039
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 933.1699492431767,
+                                                            "count": 1817234,
+                                                            "is_parallel": true,
+                                                            "self": 170.58127413483544,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 762.5886751083412,
+                                                                    "count": 7268936,
+                                                                    "is_parallel": true,
+                                                                    "self": 762.5886751083412
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 3741.3172560930966,
+                            "count": 908618,
+                            "self": 82.74986690176092,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 1233.0701926203355,
+                                    "count": 908618,
+                                    "self": 1229.9086767063293,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 3.1615159140062445,
+                                            "count": 27,
+                                            "self": 3.1615159140062445
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 2425.497196571,
+                                    "count": 637,
+                                    "self": 1117.3064080499869,
+                                    "children": {
+                                        "TorchPOCAOptimizer.update": {
+                                            "total": 1308.1907885210132,
+                                            "count": 19116,
+                                            "self": 1308.1907885210132
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 9.430004865862429e-07,
+                    "count": 1,
+                    "self": 9.430004865862429e-07
+                },
+                "TrainerController._save_models": {
+                    "total": 0.1118031259993586,
+                    "count": 1,
+                    "self": 0.0010670190004020697,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.11073610699895653,
+                            "count": 1,
+                            "self": 0.11073610699895653
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,66 @@
+{
+    "SoccerTwos": {
+        "elo": 1660.9278051864171,
+        "checkpoints": [
+            {
+                "steps": 11999980,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-11999980.onnx",
+                "reward": 0.0,
+                "creation_time": 1682804123.0387483,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-11999980.pt"
+                ]
+            },
+            {
+                "steps": 12499917,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-12499917.onnx",
+                "reward": 0.0,
+                "creation_time": 1682804633.5152636,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-12499917.pt"
+                ]
+            },
+            {
+                "steps": 12999890,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-12999890.onnx",
+                "reward": 0.0,
+                "creation_time": 1682805134.1373038,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-12999890.pt"
+                ]
+            },
+            {
+                "steps": 13499973,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-13499973.onnx",
+                "reward": 0.0,
+                "creation_time": 1682805633.0401745,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-13499973.pt"
+                ]
+            },
+            {
+                "steps": 13647362,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-13647362.onnx",
+                "reward": 0.0,
+                "creation_time": 1682805784.437112,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-13647362.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 13647362,
+            "file_path": "results/SoccerTwos/SoccerTwos.onnx",
+            "reward": 0.0,
+            "creation_time": 1682805784.437112,
+            "auxillary_file_paths": [
+                "results/SoccerTwos/SoccerTwos/SoccerTwos-13647362.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "0.31.0.dev0",
+        "torch_version": "1.9.1+cu111"
+    }
+}