First Push

README.md

@@ -0,0 +1,35 @@
+---
+library_name: ml-agents
+tags:
+- SoccerTwos
+- deep-reinforcement-learning
+- reinforcement-learning
+- ML-Agents-SoccerTwos
+---
+
+  # **poca** Agent playing **SoccerTwos**
+  This is a trained model of a **poca** agent playing **SoccerTwos**
+  using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
+
+  ## Usage (with ML-Agents)
+  The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/
+
+  We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
+  - A *short tutorial* where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your
+  browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction
+  - A *longer tutorial* to understand how works ML-Agents:
+  https://huggingface.co/learn/deep-rl-course/unit5/introduction
+
+  ### Resume the training
+  ```bash
+  mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume
+  ```
+
+  ### Watch your Agent play
+  You can watch your agent **playing directly in your browser**
+
+  1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity
+  2. Step 1: Find your model_id: pratsy/poca-SoccerTwos-v2
+  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:a5d1d21c2d5986b860b8506a1a90faaaaea4cd86825ef983786fca67c10abaa9
+size 1768746

SoccerTwos/SoccerTwos-4629708.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:544895a8089ad0c504a2c2fe22cd7fbeb9d32ed4d07a042118034d7406614f62
+size 1768746

SoccerTwos/SoccerTwos-4629708.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae6a067a8a978a5569a0fdd2d75c9dd718962ed36a5129b2bd0c4875e36f5125
+size 28429903

SoccerTwos/SoccerTwos-499510.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f56cede461af3a41681e6dd6e191928b2d61988de5cd52bd5643825a076d956
+size 28429781

SoccerTwos/SoccerTwos-4999950.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:197f148adcdd85e5c5c84f9316c95f98413e1466e72cbb329c9c1b7885c2a7eb
+size 1768746

SoccerTwos/SoccerTwos-4999950.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1308e4104965e880323151a5bbfe5110b845fae4eab46755704c7449c31c3b7
+size 28429903

SoccerTwos/SoccerTwos-5499944.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba7c87ca558277a06f7eeea91d79f94d10de36f37628c06bb03f07a1c3a62a89
+size 1768746

SoccerTwos/SoccerTwos-5499944.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b4cf823e431397107ae27a494f6091e1b7b642c7533878f301da2f0aa6abd11
+size 28429903

SoccerTwos/SoccerTwos-5999980.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac93f5399f30d7be70f9f5f104860fe058e62421d5cac82761b849bb9303c565
+size 1768746

SoccerTwos/SoccerTwos-5999980.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fd00e6fccd14b7fd34122cbea1fb632e915b2ececdd20c095ec92e16005d79f
+size 28429903

SoccerTwos/SoccerTwos-6194580.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5d1d21c2d5986b860b8506a1a90faaaaea4cd86825ef983786fca67c10abaa9
+size 1768746

SoccerTwos/SoccerTwos-6194580.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e948c7d5e445810603846ddacbbe8e47f081c65c5154dcd1ebba34410e88a383
+size 28429903

SoccerTwos/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db05e289cd7db39f9cb2b733856640353d651395cdd84eea4d48f4c157b46a5b
+size 28428927

SoccerTwos/events.out.tfevents.1690707416.RSHN-XPS.11388.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33b66b3a5603b34059086b8eb52b5f8848b9074aa81c41ad577089939c788b08
+size 345113

SoccerTwos/events.out.tfevents.1690710152.RSHN-XPS.10476.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:631eb3342b816e5c5a814515fb0fdc1afd71d4ffb450e40c20acd9e345f5c7d3
+size 1414

SoccerTwos/events.out.tfevents.1690710652.RSHN-XPS.8400.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c240a915bf42cf10f8143596fa7e75a0fd5428787445584f55bf1bfb1b01bc5b
+size 7427

SoccerTwos/events.out.tfevents.1690710721.RSHN-XPS.19672.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3bd56debd37e890c69491474f4da2fd4eb7163a2da66c1f229d32b8b8f060ef1
+size 3707605

SoccerTwos/events.out.tfevents.1690776257.RSHN-XPS.9512.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e5e420c0f72da18c9af229721b0ce6d4314b212c91ecae8766dfaa14ae5aed1
+size 1614461

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": 50000000, "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.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: 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: 50000000
+    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.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 +1,282 @@
+Mono path[0] = 'C:/Users/praty/ml-agents/training-envs-executables/SoccerTwos/SoccerTwos_Data/Managed'
+Mono config path = 'C:/Users/praty/ml-agents/training-envs-executables/SoccerTwos/MonoBleedingEdge/etc'
+Initialize engine version: 2021.3.14f1 (eee1884e7226)
+[Subsystems] Discovering subsystems at path C:/Users/praty/ml-agents/training-envs-executables/SoccerTwos/SoccerTwos_Data/UnitySubsystems
+Forcing GfxDevice: Null
+GfxDevice: creating device client; threaded=0; jobified=0
+NullGfxDevice:
+    Version:  NULL 1.0 [1.0]
+    Renderer: Null Device
+    Vendor:   Unity Technologies
+Begin MonoManager ReloadAssembly
+- Completed reload, in  2.133 seconds
+ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+Microsoft Media Foundation video decoding to texture disabled: graphics device is Null, only Direct3D 11 and Direct3D 12 (only on desktop) are supported for hardware-accelerated video decoding.
+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: 0.791100 ms
+Registered Communicator in Agent.
+ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+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]: 29476 frames, [2.0 MB-4.0 MB]: 1 frames
+      Initial Block Size 4.0 MB
+      Current Block Size 4.0 MB
+      Peak Allocated Bytes 2.0 MB
+      Overflow Count 0
+    [ALLOC_TEMP_Loading.AsyncRead]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 312 B
+      Overflow Count 0
+    [ALLOC_TEMP_Loading.PreloadManager]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 67.1 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 54 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 0.8 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 54 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 54 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 54 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 54 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 54 B
+      Overflow Count 0
+    [ALLOC_TEMP_EnlightenWorker] x 4
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 54 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 54 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 54 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 54 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 54 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 54 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 54 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 54 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 54 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 54 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 54 B
+      Overflow Count 0
+    [ALLOC_TEMP_BatchDeleteObjects]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 54 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 0.9 MB
+    [ALLOC_DEFAULT_MAIN]
+      Peak usage frame count: [4.0 MB-8.0 MB]: 29477 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 4.8 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 29477 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 17.6 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 0.9 MB
+    [ALLOC_GFX_MAIN]
+      Peak usage frame count: [32.0 KB-64.0 KB]: 29476 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]: 29477 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 173.6 KB
+      Peak Large allocation bytes 0 B
+[ALLOC_CACHEOBJECTS] Dual Thread Allocator
+  Peak main deferred allocation count 2
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 0.9 MB
+    [ALLOC_CACHEOBJECTS_MAIN]
+      Peak usage frame count: [0.5 MB-1.0 MB]: 29477 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]: 29476 frames, [2.0 MB-4.0 MB]: 1 frames
+      Requested Block Size 4.0 MB
+      Peak Block count 1
+      Peak Allocated memory 2.2 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 0.9 MB
+    [ALLOC_TYPETREE_MAIN]
+      Peak usage frame count: [0-1.0 KB]: 29477 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]: 29476 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 +1,368 @@
+{
+    "name": "root",
+    "gauges": {
+        "SoccerTwos.Policy.Entropy.mean": {
+            "value": 1.9146578311920166,
+            "min": 1.8816959857940674,
+            "max": 2.0939531326293945,
+            "count": 157
+        },
+        "SoccerTwos.Policy.Entropy.sum": {
+            "value": 38293.15625,
+            "min": 3678.82763671875,
+            "max": 44219.87890625,
+            "count": 157
+        },
+        "SoccerTwos.Environment.EpisodeLength.mean": {
+            "value": 60.592592592592595,
+            "min": 31.166666666666668,
+            "max": 79.50819672131148,
+            "count": 157
+        },
+        "SoccerTwos.Environment.EpisodeLength.sum": {
+            "value": 19632.0,
+            "min": 748.0,
+            "max": 20580.0,
+            "count": 157
+        },
+        "SoccerTwos.Self-play.ELO.mean": {
+            "value": 1657.1777093694855,
+            "min": 1596.0209309391514,
+            "max": 1677.4130578972968,
+            "count": 157
+        },
+        "SoccerTwos.Self-play.ELO.sum": {
+            "value": 268462.78891785664,
+            "min": 19382.28819872509,
+            "max": 352889.09377889097,
+            "count": 157
+        },
+        "SoccerTwos.Step.mean": {
+            "value": 6189770.0,
+            "min": 4629984.0,
+            "max": 6189770.0,
+            "count": 157
+        },
+        "SoccerTwos.Step.sum": {
+            "value": 6189770.0,
+            "min": 4629984.0,
+            "max": 6189770.0,
+            "count": 157
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
+            "value": -0.06133899837732315,
+            "min": -0.09600508213043213,
+            "max": 0.18259942531585693,
+            "count": 157
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
+            "value": -9.99825668334961,
+            "min": -18.144960403442383,
+            "max": 19.597110748291016,
+            "count": 157
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
+            "value": -0.05908508971333504,
+            "min": -0.0944647341966629,
+            "max": 0.17428338527679443,
+            "count": 157
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
+            "value": -9.63086986541748,
+            "min": -17.85383415222168,
+            "max": 20.22264862060547,
+            "count": 157
+        },
+        "SoccerTwos.Environment.CumulativeReward.mean": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 157
+        },
+        "SoccerTwos.Environment.CumulativeReward.sum": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 157
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.mean": {
+            "value": -0.06833864867321553,
+            "min": -0.2674341448923437,
+            "max": 0.19632648712879902,
+            "count": 157
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.sum": {
+            "value": -11.13919973373413,
+            "min": -43.85919976234436,
+            "max": 38.9307998418808,
+            "count": 157
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.mean": {
+            "value": -0.06833864867321553,
+            "min": -0.2674341448923437,
+            "max": 0.19632648712879902,
+            "count": 157
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.sum": {
+            "value": -11.13919973373413,
+            "min": -43.85919976234436,
+            "max": 38.9307998418808,
+            "count": 157
+        },
+        "SoccerTwos.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 157
+        },
+        "SoccerTwos.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 157
+        },
+        "SoccerTwos.Losses.PolicyLoss.mean": {
+            "value": 0.015837372342745463,
+            "min": 0.011977727416281898,
+            "max": 0.02297194521718969,
+            "count": 75
+        },
+        "SoccerTwos.Losses.PolicyLoss.sum": {
+            "value": 0.015837372342745463,
+            "min": 0.011977727416281898,
+            "max": 0.02297194521718969,
+            "count": 75
+        },
+        "SoccerTwos.Losses.ValueLoss.mean": {
+            "value": 0.09520911599198977,
+            "min": 0.0909675675133864,
+            "max": 0.11838576346635818,
+            "count": 75
+        },
+        "SoccerTwos.Losses.ValueLoss.sum": {
+            "value": 0.09520911599198977,
+            "min": 0.0909675675133864,
+            "max": 0.11838576346635818,
+            "count": 75
+        },
+        "SoccerTwos.Losses.BaselineLoss.mean": {
+            "value": 0.09653009250760078,
+            "min": 0.0923578292131424,
+            "max": 0.12042878394325575,
+            "count": 75
+        },
+        "SoccerTwos.Losses.BaselineLoss.sum": {
+            "value": 0.09653009250760078,
+            "min": 0.0923578292131424,
+            "max": 0.12042878394325575,
+            "count": 75
+        },
+        "SoccerTwos.Policy.LearningRate.mean": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 75
+        },
+        "SoccerTwos.Policy.LearningRate.sum": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 75
+        },
+        "SoccerTwos.Policy.Epsilon.mean": {
+            "value": 0.20000000000000007,
+            "min": 0.20000000000000007,
+            "max": 0.20000000000000007,
+            "count": 75
+        },
+        "SoccerTwos.Policy.Epsilon.sum": {
+            "value": 0.20000000000000007,
+            "min": 0.20000000000000007,
+            "max": 0.20000000000000007,
+            "count": 75
+        },
+        "SoccerTwos.Policy.Beta.mean": {
+            "value": 0.005000000000000001,
+            "min": 0.005000000000000001,
+            "max": 0.005000000000000001,
+            "count": 75
+        },
+        "SoccerTwos.Policy.Beta.sum": {
+            "value": 0.005000000000000001,
+            "min": 0.005000000000000001,
+            "max": 0.005000000000000001,
+            "count": 75
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1690776249",
+        "python_version": "3.9.17 (main, Jul  5 2023, 20:47:11) [MSC v.1916 64 bit (AMD64)]",
+        "command_line_arguments": "\\\\?\\C:\\Users\\praty\\anaconda3\\envs\\rl\\Scripts\\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": "2.0.1+cpu",
+        "numpy_version": "1.21.2",
+        "end_time_seconds": "1690783862"
+    },
+    "total": 7613.2275895,
+    "count": 1,
+    "self": 0.9505321000006006,
+    "children": {
+        "run_training.setup": {
+            "total": 0.15083029999999997,
+            "count": 1,
+            "self": 0.15083029999999997
+        },
+        "TrainerController.start_learning": {
+            "total": 7612.1262271,
+            "count": 1,
+            "self": 4.238344899974436,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 7.682890000000809,
+                    "count": 9,
+                    "self": 7.682890000000809
+                },
+                "TrainerController.advance": {
+                    "total": 7599.935367400025,
+                    "count": 108959,
+                    "self": 4.202570799974637,
+                    "children": {
+                        "env_step": {
+                            "total": 3077.6915271000057,
+                            "count": 108959,
+                            "self": 2458.9751897999404,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 616.0361776000498,
+                                    "count": 108959,
+                                    "self": 22.296344799981625,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 593.7398328000681,
+                                            "count": 196516,
+                                            "self": 593.7398328000681
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 2.6801597000153734,
+                                    "count": 108959,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 7598.475134400012,
+                                            "count": 108959,
+                                            "is_parallel": true,
+                                            "self": 5599.011874100275,
+                                            "children": {
+                                                "steps_from_proto": {
+                                                    "total": 0.03077510000040018,
+                                                    "count": 18,
+                                                    "is_parallel": true,
+                                                    "self": 0.005130900002915162,
+                                                    "children": {
+                                                        "_process_rank_one_or_two_observation": {
+                                                            "total": 0.025644199997485018,
+                                                            "count": 72,
+                                                            "is_parallel": true,
+                                                            "self": 0.025644199997485018
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 1999.4324851997364,
+                                                    "count": 108959,
+                                                    "is_parallel": true,
+                                                    "self": 99.331972099925,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 71.20992889990168,
+                                                            "count": 108959,
+                                                            "is_parallel": true,
+                                                            "self": 71.20992889990168
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 1504.614644099912,
+                                                            "count": 108959,
+                                                            "is_parallel": true,
+                                                            "self": 1504.614644099912
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 324.27594009999746,
+                                                            "count": 217918,
+                                                            "is_parallel": true,
+                                                            "self": 64.65784739937868,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 259.6180927006188,
+                                                                    "count": 871672,
+                                                                    "is_parallel": true,
+                                                                    "self": 259.6180927006188
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 4518.041269500045,
+                            "count": 108958,
+                            "self": 28.42740490005417,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 693.1102233999923,
+                                    "count": 108958,
+                                    "self": 692.305933399992,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 0.8042900000002646,
+                                            "count": 3,
+                                            "self": 0.8042900000002646
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 3796.5036411999986,
+                                    "count": 76,
+                                    "self": 325.9799644000127,
+                                    "children": {
+                                        "TorchPOCAOptimizer.update": {
+                                            "total": 3470.523676799986,
+                                            "count": 2280,
+                                            "self": 3470.523676799986
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 1.99999976757681e-06,
+                    "count": 1,
+                    "self": 1.99999976757681e-06
+                },
+                "TrainerController._save_models": {
+                    "total": 0.26962279999952443,
+                    "count": 1,
+                    "self": 0.015377699999589822,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.2542450999999346,
+                            "count": 1,
+                            "self": 0.2542450999999346
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,66 @@
+{
+    "SoccerTwos": {
+        "elo": 1657.051752632537,
+        "checkpoints": [
+            {
+                "steps": 4629708,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-4629708.onnx",
+                "reward": 0.0,
+                "creation_time": 1690730865.216606,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-4629708.pt"
+                ]
+            },
+            {
+                "steps": 4999950,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-4999950.onnx",
+                "reward": 0.0,
+                "creation_time": 1690778015.966372,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-4999950.pt"
+                ]
+            },
+            {
+                "steps": 5499944,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-5499944.onnx",
+                "reward": 0.0,
+                "creation_time": 1690780456.7916024,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-5499944.pt"
+                ]
+            },
+            {
+                "steps": 5999980,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-5999980.onnx",
+                "reward": 0.0,
+                "creation_time": 1690782904.6702092,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-5999980.pt"
+                ]
+            },
+            {
+                "steps": 6194580,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-6194580.onnx",
+                "reward": 0.0,
+                "creation_time": 1690783862.0253565,
+                "auxillary_file_paths": [
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-6194580.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 6194580,
+            "file_path": "results\\SoccerTwos\\SoccerTwos.onnx",
+            "reward": 0.0,
+            "creation_time": 1690783862.0253565,
+            "auxillary_file_paths": [
+                "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-6194580.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "0.31.0.dev0",
+        "torch_version": "2.0.1+cpu"
+    }
+}