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: ezrab/poca-SoccerTwos2d
+  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 sha256:41a918f838628e26656e80620c103ad7f06b9d6b2dfc60b8881f7a1a441263ca
+size 1768747

SoccerTwos/SoccerTwos-10000302.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41a918f838628e26656e80620c103ad7f06b9d6b2dfc60b8881f7a1a441263ca
+size 1768747

SoccerTwos/SoccerTwos-10000302.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69eeaad958c101ec2e495b795a6fbe44d4cbbca177cae977a4785326cb17bc67
+size 28430482

SoccerTwos/SoccerTwos-8499976.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c22e1b35332d2f4b543d6ea177cff108e820f6a60e6bab3ea27224dadebc002
+size 1768747

SoccerTwos/SoccerTwos-8499976.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f65d58fd95b2ef4e1b081c665a1de2663806322bc32c28ac006b451dc354532
+size 28430358

SoccerTwos/SoccerTwos-8999970.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2aaafbd765ff41dbfa068f34711c0221ebfd0c5ee553b9e6c5b525f05bc727c
+size 1768747

SoccerTwos/SoccerTwos-8999970.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9aec097b3abf043228f474281118cbdf3a6f5ce92baaeff667365c6d6517db9
+size 28430358

SoccerTwos/SoccerTwos-9499986.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98bc337a9a583a19672af089a457556c4afb18af6f2265d32575b1454e4a73d4
+size 1768747

SoccerTwos/SoccerTwos-9499986.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32f27a8cb2aa966ba5eb5396978f73efca36ed6acb8ac4ded3022a387d388231
+size 28430358

SoccerTwos/SoccerTwos-9999872.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41a918f838628e26656e80620c103ad7f06b9d6b2dfc60b8881f7a1a441263ca
+size 1768747

SoccerTwos/SoccerTwos-9999872.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:457e205bd00a280039c3835b3709fbe902b2b45d48429f4c670aa87c23f59c8d
+size 28430358

SoccerTwos/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8cb2bfe7dca2828ac8cc219d7b8a8e3327150e9255a7c4bbd5be69a57d8f54eb
+size 28429366

SoccerTwos/events.out.tfevents.1742335869.6faaf9ae6aa7.97.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b890c012a9742ac1947125ef3a3789d9eac28870ff6af6e74a451318dd4668d
+size 4614420

SoccerTwos/events.out.tfevents.1742357252.6faaf9ae6aa7.520.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0112a5010469b03805ab1bba7e8668c9a78032788c3b841bf203614e5c91c0c
+size 1028849

SoccerTwos/events.out.tfevents.1742361674.6faaf9ae6aa7.662.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81aa6ef07d6c2e247f45073add5983a5e4ca3284017a444d6d2f4e7196789e02
+size 1028849

SoccerTwos/events.out.tfevents.1742365790.6faaf9ae6aa7.802.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abc221d52733ddc3d2bbc4bc1ee3953cecc9b42d89d763275e91840427b09e59
+size 1028849

SoccerTwos/events.out.tfevents.1742369858.6faaf9ae6aa7.942.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29104db31a42ed41d28e84a4d2cb381ebbbfe5fc4eac9394b084bfc8be3d2dac
+size 2056804

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": 10000000, "time_horizon": 1000, "summary_freq": 10000, "threaded": false, "self_play": {"save_steps": 50000, "team_change": 200000, "swap_steps": 2000, "window": 100, "play_against_latest_model_ratio": 0.5, "initial_elo": 1200.0}, "behavioral_cloning": null}}, "env_settings": {"env_path": "/kaggle/working/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: 10000000
+    time_horizon: 1000
+    summary_freq: 10000
+    threaded: false
+    self_play:
+      save_steps: 50000
+      team_change: 200000
+      swap_steps: 2000
+      window: 100
+      play_against_latest_model_ratio: 0.5
+      initial_elo: 1200.0
+    behavioral_cloning: null
+env_settings:
+  env_path: /kaggle/working/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 +1,284 @@
+Mono path[0] = '/kaggle/working/SoccerTwos_Data/Managed'
+Mono config path = '/kaggle/working/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 /kaggle/working/SoccerTwos_Data/UnitySubsystems
+Forcing GfxDevice: Null
+GfxDevice: creating device client; threaded=0; jobified=0
+NullGfxDevice:
+    Version:  NULL 1.0 [1.0]
+    Renderer: Null Device
+    Vendor:   Unity Technologies
+ALSA lib confmisc.c:855:(parse_card) cannot find card '0'
+ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_card_inum returned error: No such file or directory
+ALSA lib confmisc.c:422:(snd_func_concat) error evaluating strings
+ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_concat returned error: No such file or directory
+ALSA lib confmisc.c:1334:(snd_func_refer) error evaluating name
+ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_refer returned error: No such file or directory
+ALSA lib conf.c:5701:(snd_config_expand) Evaluate error: No such file or directory
+ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM default
+FMOD failed to initialize the output device.: "Error initializing output device. " (60)
+Forced to initialize FMOD to to the device driver's system output rate 48000, this may impact performance and/or give inconsistent experiences compared to selected sample rate 48000
+ALSA lib confmisc.c:855:(parse_card) cannot find card '0'
+ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_card_inum returned error: No such file or directory
+ALSA lib confmisc.c:422:(snd_func_concat) error evaluating strings
+ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_concat returned error: No such file or directory
+ALSA lib confmisc.c:1334:(snd_func_refer) error evaluating name
+ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_refer returned error: No such file or directory
+ALSA lib conf.c:5701:(snd_config_expand) Evaluate error: No such file or directory
+ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM default
+FMOD failed to initialize the output device.: "Error initializing output device. " (60)
+FMOD initialized on nosound output
+Begin MonoManager ReloadAssembly
+- Completed reload, in  0.142 seconds
+ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+WARNING: Shader Unsupported: 'Standard (Specular setup)' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
+ERROR: Shader Standard (Specular setup) shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+WARNING: Shader Unsupported: 'Standard (Specular setup)' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
+WARNING: Shader Unsupported: 'Autodesk Interactive' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
+ERROR: Shader Autodesk Interactive shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+WARNING: Shader Unsupported: 'Autodesk Interactive' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
+WARNING: Shader Unsupported: 'Standard' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
+ERROR: Shader Standard shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+WARNING: Shader Unsupported: 'Standard' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
+UnloadTime: 1.028891 ms
+Registered Communicator in Agent.
+ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+requesting resize 84 x 84
+Setting up 2 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]: 37633 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 249.5 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_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 0]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0.7 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 10]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 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_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 2
+      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 3
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 5]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 13]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 1]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 2]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 3]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 11]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 0]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 4]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_BatchDeleteObjects]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+[ALLOC_DEFAULT] Dual Thread Allocator
+  Peak main deferred allocation count 5
+    [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]: 37634 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]: 37634 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 17.5 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]: 37633 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]: 37634 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]: 37634 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]: 37633 frames, [4.0 MB-8.0 MB]: 1 frames
+      Requested Block Size 4.0 MB
+      Peak Block count 2
+      Peak Allocated memory 4.4 MB
+      Peak Large allocation bytes 0 B
+[ALLOC_TYPETREE] Dual Thread Allocator
+  Peak main deferred allocation count 0
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 1.0 MB
+    [ALLOC_TYPETREE_MAIN]
+      Peak usage frame count: [0-1.0 KB]: 37634 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]: 37633 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": 1.7675894498825073,
+            "min": 1.7560936212539673,
+            "max": 1.90109384059906,
+            "count": 200
+        },
+        "SoccerTwos.Policy.Entropy.sum": {
+            "value": 36539.609375,
+            "min": 31464.638671875,
+            "max": 44063.8359375,
+            "count": 200
+        },
+        "SoccerTwos.Environment.EpisodeLength.mean": {
+            "value": 72.01428571428572,
+            "min": 47.8235294117647,
+            "max": 85.64285714285714,
+            "count": 200
+        },
+        "SoccerTwos.Environment.EpisodeLength.sum": {
+            "value": 20164.0,
+            "min": 18344.0,
+            "max": 20896.0,
+            "count": 200
+        },
+        "SoccerTwos.Self-play.ELO.mean": {
+            "value": 1782.6707366284404,
+            "min": 1728.8981005237488,
+            "max": 1825.397400178024,
+            "count": 200
+        },
+        "SoccerTwos.Self-play.ELO.sum": {
+            "value": 249573.90312798167,
+            "min": 196875.18104178057,
+            "max": 366048.19721326703,
+            "count": 200
+        },
+        "SoccerTwos.Step.mean": {
+            "value": 9999872.0,
+            "min": 8009943.0,
+            "max": 9999872.0,
+            "count": 200
+        },
+        "SoccerTwos.Step.sum": {
+            "value": 9999872.0,
+            "min": 8009943.0,
+            "max": 9999872.0,
+            "count": 200
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
+            "value": -0.005632105749100447,
+            "min": -0.08237681537866592,
+            "max": 0.10987689346075058,
+            "count": 200
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
+            "value": -0.7884948253631592,
+            "min": -13.449801445007324,
+            "max": 17.03091812133789,
+            "count": 200
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
+            "value": -0.012240163050591946,
+            "min": -0.08354859799146652,
+            "max": 0.10938543826341629,
+            "count": 200
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
+            "value": -1.713622808456421,
+            "min": -13.530614852905273,
+            "max": 16.954742431640625,
+            "count": 200
+        },
+        "SoccerTwos.Environment.CumulativeReward.mean": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 200
+        },
+        "SoccerTwos.Environment.CumulativeReward.sum": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 200
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.mean": {
+            "value": -0.041045715127672466,
+            "min": -0.3278630859899841,
+            "max": 0.27545290377832227,
+            "count": 200
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.sum": {
+            "value": -5.7464001178741455,
+            "min": -48.85159981250763,
+            "max": 45.108400106430054,
+            "count": 200
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.mean": {
+            "value": -0.041045715127672466,
+            "min": -0.3278630859899841,
+            "max": 0.27545290377832227,
+            "count": 200
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.sum": {
+            "value": -5.7464001178741455,
+            "min": -48.85159981250763,
+            "max": 45.108400106430054,
+            "count": 200
+        },
+        "SoccerTwos.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 200
+        },
+        "SoccerTwos.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 200
+        },
+        "SoccerTwos.Losses.PolicyLoss.mean": {
+            "value": 0.012184776676197847,
+            "min": 0.012184776676197847,
+            "max": 0.025904368401582663,
+            "count": 97
+        },
+        "SoccerTwos.Losses.PolicyLoss.sum": {
+            "value": 0.012184776676197847,
+            "min": 0.012184776676197847,
+            "max": 0.025904368401582663,
+            "count": 97
+        },
+        "SoccerTwos.Losses.ValueLoss.mean": {
+            "value": 0.10116277212897937,
+            "min": 0.09247966259717941,
+            "max": 0.11678934420148532,
+            "count": 97
+        },
+        "SoccerTwos.Losses.ValueLoss.sum": {
+            "value": 0.10116277212897937,
+            "min": 0.09247966259717941,
+            "max": 0.11678934420148532,
+            "count": 97
+        },
+        "SoccerTwos.Losses.BaselineLoss.mean": {
+            "value": 0.10259491056203843,
+            "min": 0.09378573422630627,
+            "max": 0.11908057381709417,
+            "count": 97
+        },
+        "SoccerTwos.Losses.BaselineLoss.sum": {
+            "value": 0.10259491056203843,
+            "min": 0.09378573422630627,
+            "max": 0.11908057381709417,
+            "count": 97
+        },
+        "SoccerTwos.Policy.LearningRate.mean": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 97
+        },
+        "SoccerTwos.Policy.LearningRate.sum": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 97
+        },
+        "SoccerTwos.Policy.Epsilon.mean": {
+            "value": 0.20000000000000007,
+            "min": 0.20000000000000007,
+            "max": 0.20000000000000007,
+            "count": 97
+        },
+        "SoccerTwos.Policy.Epsilon.sum": {
+            "value": 0.20000000000000007,
+            "min": 0.20000000000000007,
+            "max": 0.20000000000000007,
+            "count": 97
+        },
+        "SoccerTwos.Policy.Beta.mean": {
+            "value": 0.005000000000000001,
+            "min": 0.005000000000000001,
+            "max": 0.005000000000000001,
+            "count": 97
+        },
+        "SoccerTwos.Policy.Beta.sum": {
+            "value": 0.005000000000000001,
+            "min": 0.005000000000000001,
+            "max": 0.005000000000000001,
+            "count": 97
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1742369857",
+        "python_version": "3.10.12 (main, Nov  6 2024, 20:22:13) [GCC 11.4.0]",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn SoccerTwos.yaml --env=/kaggle/working/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+cu121",
+        "numpy_version": "1.23.5",
+        "end_time_seconds": "1742378087"
+    },
+    "total": 8230.279236997994,
+    "count": 1,
+    "self": 0.5388216399951489,
+    "children": {
+        "run_training.setup": {
+            "total": 0.10921803500241367,
+            "count": 1,
+            "self": 0.10921803500241367
+        },
+        "TrainerController.start_learning": {
+            "total": 8229.631197322997,
+            "count": 1,
+            "self": 5.220221450785175,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 3.095407430002524,
+                    "count": 11,
+                    "self": 3.095407430002524
+                },
+                "TrainerController.advance": {
+                    "total": 8221.031829924214,
+                    "count": 138571,
+                    "self": 5.711883769639826,
+                    "children": {
+                        "env_step": {
+                            "total": 4002.323373769199,
+                            "count": 138571,
+                            "self": 3188.963194181066,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 810.2459795889663,
+                                    "count": 138571,
+                                    "self": 33.80987963719963,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 776.4360999517667,
+                                            "count": 250896,
+                                            "self": 776.4360999517667
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 3.1141999991668854,
+                                    "count": 138571,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 8218.953397456855,
+                                            "count": 138571,
+                                            "is_parallel": true,
+                                            "self": 5601.854040677259,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.003945423006371129,
+                                                            "count": 2,
+                                                            "is_parallel": true,
+                                                            "self": 0.0011204350084881298,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.0028249879978829995,
+                                                                    "count": 8,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0028249879978829995
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.045710075995884836,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0009038530042744242,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.000769617996411398,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.000769617996411398
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.041449666998232715,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.041449666998232715
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.0025869379969662987,
+                                                                    "count": 2,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0006126579901319928,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.001974280006834306,
+                                                                            "count": 8,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.001974280006834306
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "steps_from_proto": {
+                                                    "total": 0.025127086009888444,
+                                                    "count": 20,
+                                                    "is_parallel": true,
+                                                    "self": 0.005275540963339154,
+                                                    "children": {
+                                                        "_process_rank_one_or_two_observation": {
+                                                            "total": 0.01985154504654929,
+                                                            "count": 80,
+                                                            "is_parallel": true,
+                                                            "self": 0.01985154504654929
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 2617.074229693586,
+                                                    "count": 138570,
+                                                    "is_parallel": true,
+                                                    "self": 157.93649124117655,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 108.59582978139952,
+                                                            "count": 138570,
+                                                            "is_parallel": true,
+                                                            "self": 108.59582978139952
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 1904.412547840555,
+                                                            "count": 138570,
+                                                            "is_parallel": true,
+                                                            "self": 1904.412547840555
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 446.12936083045497,
+                                                            "count": 277140,
+                                                            "is_parallel": true,
+                                                            "self": 85.68184083596861,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 360.44751999448636,
+                                                                    "count": 1108560,
+                                                                    "is_parallel": true,
+                                                                    "self": 360.44751999448636
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 4212.996572385375,
+                            "count": 138571,
+                            "self": 39.71242667516344,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 842.641055664215,
+                                    "count": 138571,
+                                    "self": 841.5595301182111,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 1.0815255460038316,
+                                            "count": 4,
+                                            "self": 1.0815255460038316
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 3330.6430900459964,
+                                    "count": 97,
+                                    "self": 347.02466652496514,
+                                    "children": {
+                                        "TorchPOCAOptimizer.update": {
+                                            "total": 2983.618423521031,
+                                            "count": 2910,
+                                            "self": 2983.618423521031
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 1.2300006346777081e-06,
+                    "count": 1,
+                    "self": 1.2300006346777081e-06
+                },
+                "TrainerController._save_models": {
+                    "total": 0.2837372879948816,
+                    "count": 1,
+                    "self": 0.006636472993704956,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.27710081500117667,
+                            "count": 1,
+                            "self": 0.27710081500117667
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,66 @@
+{
+    "SoccerTwos": {
+        "checkpoints": [
+            {
+                "steps": 8499976,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-8499976.onnx",
+                "reward": 0.0,
+                "creation_time": 1742371870.0334554,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-8499976.pt"
+                ]
+            },
+            {
+                "steps": 8999970,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-8999970.onnx",
+                "reward": 0.0,
+                "creation_time": 1742373900.9006097,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-8999970.pt"
+                ]
+            },
+            {
+                "steps": 9499986,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-9499986.onnx",
+                "reward": 0.0,
+                "creation_time": 1742375934.9383352,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-9499986.pt"
+                ]
+            },
+            {
+                "steps": 9999872,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-9999872.onnx",
+                "reward": 0.0,
+                "creation_time": 1742378086.622705,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-9999872.pt"
+                ]
+            },
+            {
+                "steps": 10000302,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-10000302.onnx",
+                "reward": 0.0,
+                "creation_time": 1742378087.0250568,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-10000302.pt"
+                ]
+            }
+        ],
+        "elo": 1778.746376538464,
+        "final_checkpoint": {
+            "steps": 10000302,
+            "file_path": "results/SoccerTwos/SoccerTwos.onnx",
+            "reward": 0.0,
+            "creation_time": 1742378087.0250568,
+            "auxillary_file_paths": [
+                "results/SoccerTwos/SoccerTwos/SoccerTwos-10000302.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "1.2.0.dev0",
+        "torch_version": "2.5.1+cu121"
+    }
+}