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: earlzero/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 sha256:53c56717a562c666fb863b0b6c28091c44c0df48590ed8734847bbd790a75592
+size 1768747

SoccerTwos/SoccerTwos-4999972.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d9472c19dde31920202f8c7ffaf582545432267284fe3af9f00fa6dc90ab466
+size 1768747

SoccerTwos/SoccerTwos-4999972.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:212083374bf1b44a962cca13a3c67e2a3e2c3d81af02bad1994289862eab9201
+size 28432022

SoccerTwos/SoccerTwos-5499948.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dad31f5b586a5444c3315da79f4d17ed4b44be820a159f27e868fed1c51c6097
+size 1768747

SoccerTwos/SoccerTwos-5499948.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:179a119ae832d1006ab9e1fcb4f4a76c72f05112f1e551adcebcdf9eb07fe41e
+size 28432022

SoccerTwos/SoccerTwos-5999920.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1763b794c44cba7314960e02dbf9585f24ecb9bf6b858a5d9f8a5d6161aef641
+size 1768747

SoccerTwos/SoccerTwos-5999920.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f0c52d55187862ffda12d4db2dc2d5f3ff758b34d594dc2365bc93af3783278
+size 28432022

SoccerTwos/SoccerTwos-6499996.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5dfdc290497dedfea50fb1f2c1c10c92bf23ca34cc119d4351ded387cb66d600
+size 1768747

SoccerTwos/SoccerTwos-6499996.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39633e946723c686c45dc36caf5e51de28363879f0d18015ff32ba66a233b441
+size 28432022

SoccerTwos/SoccerTwos-6839752.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53c56717a562c666fb863b0b6c28091c44c0df48590ed8734847bbd790a75592
+size 1768747

SoccerTwos/SoccerTwos-6839752.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22765c79e0590a9a801ec56c572ae9fbacd7811505dc1f41d414ac4f0a21262d
+size 28432022

SoccerTwos/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53d088ef561eb1d018caa67a6ca4c17401e10c1f1c4d44394f1eba192030ef4c
+size 28431030

SoccerTwos/events.out.tfevents.1734802220.chiba.18785.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e09d7ccd3cf57b400754389c1819aa17c54d509758271f184950bd3999063dd
+size 1880258

SoccerTwos/events.out.tfevents.1734805267.chiba.19254.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b115ff77b5f7d9217dd88950a0fb8bfe4fd52e5c8d22eb65586eac2f8d4f031
+size 4924141

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-env-executables/SoccerTwo/SoccerTwos.x86_64", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "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 +1,84 @@
+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-env-executables/SoccerTwo/SoccerTwos.x86_64
+  env_args: null
+  base_port: 5005
+  num_envs: 1
+  num_areas: 1
+  timeout_wait: 60
+  seed: -1
+  max_lifetime_restarts: 10
+  restarts_rate_limit_n: 1
+  restarts_rate_limit_period_s: 60
+engine_settings:
+  width: 84
+  height: 84
+  quality_level: 5
+  time_scale: 20
+  target_frame_rate: -1
+  capture_frame_rate: 60
+  no_graphics: true
+  no_graphics_monitor: false
+environment_parameters: null
+checkpoint_settings:
+  run_id: 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 +1,305 @@
+Mono path[0] = '/home/ez/ml/rl/ml-agents/training-env-executables/SoccerTwo/SoccerTwos_Data/Managed'
+Mono config path = '/home/ez/ml/rl/ml-agents/training-env-executables/SoccerTwo/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/ez/ml/rl/ml-agents/training-env-executables/SoccerTwo/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  0.057 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: 0.505860 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
+Setting up 6 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]: 90293 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 0.7 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 0]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 10]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 9]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 5]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 14]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_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 6
+      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 11
+      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_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 4
+    [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]: 90294 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 4.7 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 90294 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 1.0 MB
+    [ALLOC_GFX_MAIN]
+      Peak usage frame count: [32.0 KB-64.0 KB]: 90293 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]: 90294 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]: 90294 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]: 90293 frames, [2.0 MB-4.0 MB]: 1 frames
+      Requested Block Size 4.0 MB
+      Peak Block count 1
+      Peak Allocated memory 4.0 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]: 90294 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]: 90293 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": 1.6470953226089478,
+            "min": 1.5953850746154785,
+            "max": 2.3093199729919434,
+            "count": 479
+        },
+        "SoccerTwos.Policy.Entropy.sum": {
+            "value": 34523.1171875,
+            "min": 29625.490234375,
+            "max": 51072.29296875,
+            "count": 479
+        },
+        "SoccerTwos.Environment.EpisodeLength.mean": {
+            "value": 51.21649484536083,
+            "min": 41.720338983050844,
+            "max": 83.73770491803279,
+            "count": 479
+        },
+        "SoccerTwos.Environment.EpisodeLength.sum": {
+            "value": 19872.0,
+            "min": 14200.0,
+            "max": 20692.0,
+            "count": 479
+        },
+        "SoccerTwos.Self-play.ELO.mean": {
+            "value": 1608.7605317785462,
+            "min": 1472.4185017158015,
+            "max": 1627.1288522807756,
+            "count": 479
+        },
+        "SoccerTwos.Self-play.ELO.sum": {
+            "value": 312099.543165038,
+            "min": 139141.5329085182,
+            "max": 377112.46624928806,
+            "count": 479
+        },
+        "SoccerTwos.Step.mean": {
+            "value": 6829854.0,
+            "min": 2049932.0,
+            "max": 6829854.0,
+            "count": 479
+        },
+        "SoccerTwos.Step.sum": {
+            "value": 6829854.0,
+            "min": 2049932.0,
+            "max": 6829854.0,
+            "count": 479
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
+            "value": -0.013270261697471142,
+            "min": -0.14858590066432953,
+            "max": 0.10823917388916016,
+            "count": 479
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
+            "value": -2.5611605644226074,
+            "min": -24.516674041748047,
+            "max": 15.802919387817383,
+            "count": 479
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
+            "value": -0.010980118997395039,
+            "min": -0.1502770185470581,
+            "max": 0.11209087818861008,
+            "count": 479
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
+            "value": -2.1191630363464355,
+            "min": -24.79570770263672,
+            "max": 16.36526870727539,
+            "count": 479
+        },
+        "SoccerTwos.Environment.CumulativeReward.mean": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 479
+        },
+        "SoccerTwos.Environment.CumulativeReward.sum": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 479
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.mean": {
+            "value": 0.016830051501180224,
+            "min": -0.4204434791336889,
+            "max": 0.27019212658949726,
+            "count": 479
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.sum": {
+            "value": 3.248199939727783,
+            "min": -55.13759970664978,
+            "max": 49.95380002260208,
+            "count": 479
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.mean": {
+            "value": 0.016830051501180224,
+            "min": -0.4204434791336889,
+            "max": 0.27019212658949726,
+            "count": 479
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.sum": {
+            "value": 3.248199939727783,
+            "min": -55.13759970664978,
+            "max": 49.95380002260208,
+            "count": 479
+        },
+        "SoccerTwos.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 479
+        },
+        "SoccerTwos.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 479
+        },
+        "SoccerTwos.Losses.PolicyLoss.mean": {
+            "value": 0.01711671534285415,
+            "min": 0.011406772219925188,
+            "max": 0.023807225172640757,
+            "count": 232
+        },
+        "SoccerTwos.Losses.PolicyLoss.sum": {
+            "value": 0.01711671534285415,
+            "min": 0.011406772219925188,
+            "max": 0.023807225172640757,
+            "count": 232
+        },
+        "SoccerTwos.Losses.ValueLoss.mean": {
+            "value": 0.11728582382202149,
+            "min": 0.07979752396543821,
+            "max": 0.12634022161364555,
+            "count": 232
+        },
+        "SoccerTwos.Losses.ValueLoss.sum": {
+            "value": 0.11728582382202149,
+            "min": 0.07979752396543821,
+            "max": 0.12634022161364555,
+            "count": 232
+        },
+        "SoccerTwos.Losses.BaselineLoss.mean": {
+            "value": 0.11893877113858858,
+            "min": 0.08056673184037208,
+            "max": 0.12834935064117114,
+            "count": 232
+        },
+        "SoccerTwos.Losses.BaselineLoss.sum": {
+            "value": 0.11893877113858858,
+            "min": 0.08056673184037208,
+            "max": 0.12834935064117114,
+            "count": 232
+        },
+        "SoccerTwos.Policy.LearningRate.mean": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 232
+        },
+        "SoccerTwos.Policy.LearningRate.sum": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 232
+        },
+        "SoccerTwos.Policy.Epsilon.mean": {
+            "value": 0.20000000000000007,
+            "min": 0.20000000000000007,
+            "max": 0.20000000000000007,
+            "count": 232
+        },
+        "SoccerTwos.Policy.Epsilon.sum": {
+            "value": 0.20000000000000007,
+            "min": 0.20000000000000007,
+            "max": 0.20000000000000007,
+            "count": 232
+        },
+        "SoccerTwos.Policy.Beta.mean": {
+            "value": 0.005000000000000001,
+            "min": 0.005000000000000001,
+            "max": 0.005000000000000001,
+            "count": 232
+        },
+        "SoccerTwos.Policy.Beta.sum": {
+            "value": 0.005000000000000001,
+            "min": 0.005000000000000001,
+            "max": 0.005000000000000001,
+            "count": 232
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1734805267",
+        "python_version": "3.10.12 (main, Jul  5 2023, 18:54:27) [GCC 11.2.0]",
+        "command_line_arguments": "/home/ez/miniconda3/envs/rl/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-env-executables/SoccerTwo/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --resume",
+        "mlagents_version": "1.2.0.dev0",
+        "mlagents_envs_version": "1.2.0.dev0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "2.5.1+cu124",
+        "numpy_version": "1.23.5",
+        "end_time_seconds": "1734812675"
+    },
+    "total": 7407.930592285993,
+    "count": 1,
+    "self": 0.0830988860107027,
+    "children": {
+        "run_training.setup": {
+            "total": 0.014124214998446405,
+            "count": 1,
+            "self": 0.014124214998446405
+        },
+        "TrainerController.start_learning": {
+            "total": 7407.833369184984,
+            "count": 1,
+            "self": 4.557064374006586,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 1.5468581588647794,
+                    "count": 25,
+                    "self": 1.5468581588647794
+                },
+                "TrainerController.advance": {
+                    "total": 7401.59500303914,
+                    "count": 333334,
+                    "self": 3.933105544099817,
+                    "children": {
+                        "env_step": {
+                            "total": 5963.718467488739,
+                            "count": 333334,
+                            "self": 4762.2044231270265,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 1198.8402411262214,
+                                    "count": 333334,
+                                    "self": 22.965649539168226,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 1175.8745915870531,
+                                            "count": 601966,
+                                            "self": 1175.8745915870531
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 2.673803235491505,
+                                    "count": 333334,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 7396.952812148578,
+                                            "count": 333334,
+                                            "is_parallel": true,
+                                            "self": 3185.231254872866,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.0018544579797890037,
+                                                            "count": 2,
+                                                            "is_parallel": true,
+                                                            "self": 0.00043329395703040063,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.001421164022758603,
+                                                                    "count": 8,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.001421164022758603
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.018671988014830276,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0004823860072065145,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.0006805970042478293,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0006805970042478293
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.016217303986195475,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.016217303986195475
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.0012917010171804577,
+                                                                    "count": 2,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00022089105914346874,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.001070809958036989,
+                                                                            "count": 8,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.001070809958036989
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "steps_from_proto": {
+                                                    "total": 0.057611184020061046,
+                                                    "count": 48,
+                                                    "is_parallel": true,
+                                                    "self": 0.008995019015856087,
+                                                    "children": {
+                                                        "_process_rank_one_or_two_observation": {
+                                                            "total": 0.04861616500420496,
+                                                            "count": 192,
+                                                            "is_parallel": true,
+                                                            "self": 0.04861616500420496
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 4211.663946091692,
+                                                    "count": 333333,
+                                                    "is_parallel": true,
+                                                    "self": 283.66528311476577,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 173.266821395664,
+                                                            "count": 333333,
+                                                            "is_parallel": true,
+                                                            "self": 173.266821395664
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 3011.904557889997,
+                                                            "count": 333333,
+                                                            "is_parallel": true,
+                                                            "self": 3011.904557889997
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 742.8272836912656,
+                                                            "count": 666666,
+                                                            "is_parallel": true,
+                                                            "self": 117.61646822033799,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 625.2108154709276,
+                                                                    "count": 2666664,
+                                                                    "is_parallel": true,
+                                                                    "self": 625.2108154709276
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 1433.9434300063003,
+                            "count": 333334,
+                            "self": 32.3608399060322,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 698.8355939066096,
+                                    "count": 333334,
+                                    "self": 697.6233816336025,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 1.212212273007026,
+                                            "count": 9,
+                                            "self": 1.212212273007026
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 702.7469961936586,
+                                    "count": 233,
+                                    "self": 445.06726305090706,
+                                    "children": {
+                                        "TorchPOCAOptimizer.update": {
+                                            "total": 257.6797331427515,
+                                            "count": 6960,
+                                            "self": 257.6797331427515
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 9.899958968162537e-07,
+                    "count": 1,
+                    "self": 9.899958968162537e-07
+                },
+                "TrainerController._save_models": {
+                    "total": 0.1344426229770761,
+                    "count": 1,
+                    "self": 0.002314659970579669,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.13212796300649643,
+                            "count": 1,
+                            "self": 0.13212796300649643
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,66 @@
+{
+    "SoccerTwos": {
+        "checkpoints": [
+            {
+                "steps": 4999972,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-4999972.onnx",
+                "reward": 0.0,
+                "creation_time": 1734809814.9078634,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-4999972.pt"
+                ]
+            },
+            {
+                "steps": 5499948,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-5499948.onnx",
+                "reward": 0.0,
+                "creation_time": 1734810592.2808547,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-5499948.pt"
+                ]
+            },
+            {
+                "steps": 5999920,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-5999920.onnx",
+                "reward": 0.0,
+                "creation_time": 1734811369.3588557,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-5999920.pt"
+                ]
+            },
+            {
+                "steps": 6499996,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-6499996.onnx",
+                "reward": 0.0,
+                "creation_time": 1734812145.805644,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-6499996.pt"
+                ]
+            },
+            {
+                "steps": 6839752,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-6839752.onnx",
+                "reward": null,
+                "creation_time": 1734812675.3241463,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-6839752.pt"
+                ]
+            }
+        ],
+        "elo": 1615.2103645695183,
+        "final_checkpoint": {
+            "steps": 6839752,
+            "file_path": "results/SoccerTwos/SoccerTwos.onnx",
+            "reward": null,
+            "creation_time": 1734812675.3241463,
+            "auxillary_file_paths": [
+                "results/SoccerTwos/SoccerTwos/SoccerTwos-6839752.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "1.2.0.dev0",
+        "torch_version": "2.5.1+cu124"
+    }
+}