Push about 3.9m steps of SoccerTwos

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: HilbertS/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 sha256:55c519cb85d5c27b74453edae10b519afacb18118917850833bc74dbb34bf8a2
+size 1764633

SoccerTwos/SoccerTwos-302934.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89883774aee01649e6c1632f517fe0c6f1d176882bc7bbfc24c5365c79b30743
+size 1764633

SoccerTwos/SoccerTwos-302934.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e8c5b5618c526ba5508b567b2bf3e6bec86129ad26aaf43a56566896a4e72c3
+size 28421201

SoccerTwos/SoccerTwos-3499953.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:459975a312bbe80c0dddf5d05f493f3ecb0c7c89e1022a3facd400221cc71391
+size 1764633

SoccerTwos/SoccerTwos-3499953.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5913852ab388679c7d0d23cc8edb70e20ef2c65b980bc19231c38801a3109524
+size 28421201

SoccerTwos/SoccerTwos-3499994.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:459975a312bbe80c0dddf5d05f493f3ecb0c7c89e1022a3facd400221cc71391
+size 1764633

SoccerTwos/SoccerTwos-3499994.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8675c81203a442942975a75e68d6d0a66df19660941dbc4aeed0178f04767c7f
+size 28421201

SoccerTwos/SoccerTwos-3500115.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:459975a312bbe80c0dddf5d05f493f3ecb0c7c89e1022a3facd400221cc71391
+size 1764633

SoccerTwos/SoccerTwos-3500115.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d05514caaa3b40f3e8d4576775552ff740672d84378d5a94a9d067e000cd7b1f
+size 28421201

SoccerTwos/SoccerTwos-3999934.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8abe4763e424259284971bbbad52a698f70674abaa83ce7391cc9dabc5c8cfee
+size 1764633

SoccerTwos/SoccerTwos-3999934.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7850c2214f3e36602bb0303259c9f019577543bbc846526767c2bb92261d6c7
+size 28421201

SoccerTwos/SoccerTwos-4499936.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5fed2d98c8b321d5aae97be29a361970e5ee22e4c1d1ab4967087d4f9d4dcf0
+size 1764633

SoccerTwos/SoccerTwos-4499936.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b14df05d3403a0a7f35115c45894ae259cefb982779b4707d9cfa039d5697190
+size 28421201

SoccerTwos/SoccerTwos-4999968.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55f35265b09fb8ebfab3e25d6476ade1b3e1b7c7bda2e830189179c17119f03a
+size 1764633

SoccerTwos/SoccerTwos-4999968.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38dbab1d67f5ef097ee4c2b3d1b34eb48f0696986cc1b29387ff7cf30146e5c4
+size 28421201

SoccerTwos/SoccerTwos-5045530.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55c519cb85d5c27b74453edae10b519afacb18118917850833bc74dbb34bf8a2
+size 1764633

SoccerTwos/SoccerTwos-5045530.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91263b84dbf06b8224c3653c04bec3792995bf5dd0d486b64d87b253f10e4bb6
+size 28421201

SoccerTwos/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91263b84dbf06b8224c3653c04bec3792995bf5dd0d486b64d87b253f10e4bb6
+size 28421201

SoccerTwos/events.out.tfevents.1688467203.9dec38a81fa4.13.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7aa848363c7d02cae3062ffe7d7306ec2c794e8abc4fe0dc7de99fb2b32436e3
+size 222289

SoccerTwos/events.out.tfevents.1688468293.9dec38a81fa4.111.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67f1c45986461826a90f82a92e1001744c57ae931604261dcab8f4e55c4f9bec
+size 20961

SoccerTwos/events.out.tfevents.1688468547.1f7385ae0d75.7.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8232a42ea9987a50228d19ca9fd6e4efa19797a1e1fc5a906fdb1b339acc30e
+size 4774658

SoccerTwos/events.out.tfevents.1688480842.b62c2384141c.6.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11509e6f8770a2fca03c89783ce0cf7e529b9f54aee31f9a48b19d9c7a1671ce
+size 2050

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.x86_64", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SoccerTwos", "initialize_from": null, "load_model": false, "resume": true, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -0,0 +1,82 @@
+default_settings: null
+behaviors:
+  SoccerTwos:
+    trainer_type: poca
+    hyperparameters:
+      batch_size: 2048
+      buffer_size: 20480
+      learning_rate: 0.0003
+      beta: 0.005
+      epsilon: 0.2
+      lambd: 0.95
+      num_epoch: 3
+      learning_rate_schedule: constant
+      beta_schedule: constant
+      epsilon_schedule: constant
+    checkpoint_interval: 500000
+    network_settings:
+      normalize: false
+      hidden_units: 512
+      num_layers: 2
+      vis_encode_type: simple
+      memory: null
+      goal_conditioning_type: hyper
+      deterministic: false
+    reward_signals:
+      extrinsic:
+        gamma: 0.99
+        strength: 1.0
+        network_settings:
+          normalize: false
+          hidden_units: 128
+          num_layers: 2
+          vis_encode_type: simple
+          memory: null
+          goal_conditioning_type: hyper
+          deterministic: false
+    init_path: null
+    keep_checkpoints: 5
+    even_checkpoints: false
+    max_steps: 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.x86_64
+  env_args: null
+  base_port: 5005
+  num_envs: 1
+  num_areas: 1
+  seed: -1
+  max_lifetime_restarts: 10
+  restarts_rate_limit_n: 1
+  restarts_rate_limit_period_s: 60
+engine_settings:
+  width: 84
+  height: 84
+  quality_level: 5
+  time_scale: 20
+  target_frame_rate: -1
+  capture_frame_rate: 60
+  no_graphics: true
+environment_parameters: null
+checkpoint_settings:
+  run_id: SoccerTwos
+  initialize_from: null
+  load_model: false
+  resume: true
+  force: false
+  train_model: false
+  inference: false
+  results_dir: results
+torch_settings:
+  device: null
+debug: false

run_logs/Player-0.log

@@ -0,0 +1,344 @@
+Mono path[0] = '/code/ml-agents/training-envs-executables/SoccerTwos_Data/Managed'
+Mono config path = '/code/ml-agents/training-envs-executables/SoccerTwos_Data/MonoBleedingEdge/etc'
+Preloaded 'lib_burst_generated.so'
+Preloaded 'libgrpc_csharp_ext.x64.so'
+PlayerPrefs - Creating folder: /root/.config/unity3d/Unity Technologies
+PlayerPrefs - Creating folder: /root/.config/unity3d/Unity Technologies/SoccerTwos
+Unable to load player prefs
+Initialize engine version: 2021.3.14f1 (eee1884e7226)
+[Subsystems] Discovering subsystems at path /code/ml-agents/training-envs-executables/SoccerTwos_Data/UnitySubsystems
+Forcing GfxDevice: Null
+GfxDevice: creating device client; threaded=0; jobified=0
+NullGfxDevice:
+    Version:  NULL 1.0 [1.0]
+    Renderer: Null Device
+    Vendor:   Unity Technologies
+FMOD initialized on nosound output
+Begin MonoManager ReloadAssembly
+- Completed reload, in  0.087 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: 0.782612 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: [4.0 KB-8.0 KB]: 1 frames, [8.0 KB-16.0 KB]: 8 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_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 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 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 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]: 89323 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_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 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 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 0.7 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 2]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 3]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 11]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 0]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 4]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_BatchDeleteObjects]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+[ALLOC_DEFAULT] Dual Thread Allocator
+  Peak main deferred allocation count 6
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 1.0 MB
+    [ALLOC_DEFAULT_MAIN]
+      Peak usage frame count: [4.0 MB-8.0 MB]: 89324 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]: 89324 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 17.4 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]: 89323 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]: 89324 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]: 89324 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]: 89323 frames, [4.0 MB-8.0 MB]: 1 frames
+      Requested Block Size 4.0 MB
+      Peak Block count 2
+      Peak Allocated memory 4.5 MB
+      Peak Large allocation bytes 0 B
+[ALLOC_TYPETREE] Dual Thread Allocator
+  Peak main deferred allocation count 0
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 1.0 MB
+    [ALLOC_TYPETREE_MAIN]
+      Peak usage frame count: [0-1.0 KB]: 89324 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]: 89323 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": 1.9089889526367188,
+            "min": 1.8442237377166748,
+            "max": 3.213865041732788,
+            "count": 472
+        },
+        "SoccerTwos.Policy.Entropy.sum": {
+            "value": 35919.53515625,
+            "min": 29317.10546875,
+            "max": 120344.625,
+            "count": 472
+        },
+        "SoccerTwos.Environment.EpisodeLength.mean": {
+            "value": 62.17948717948718,
+            "min": 42.51304347826087,
+            "max": 999.0,
+            "count": 472
+        },
+        "SoccerTwos.Environment.EpisodeLength.sum": {
+            "value": 19400.0,
+            "min": 11112.0,
+            "max": 28436.0,
+            "count": 472
+        },
+        "SoccerTwos.Self-play.ELO.mean": {
+            "value": 1556.9494059513054,
+            "min": 1184.4253004330594,
+            "max": 1576.660508881427,
+            "count": 471
+        },
+        "SoccerTwos.Self-play.ELO.sum": {
+            "value": 242884.10732840362,
+            "min": 2370.6947943219175,
+            "max": 334525.03998778446,
+            "count": 471
+        },
+        "SoccerTwos.Step.mean": {
+            "value": 5039949.0,
+            "min": 329805.0,
+            "max": 5039949.0,
+            "count": 472
+        },
+        "SoccerTwos.Step.sum": {
+            "value": 5039949.0,
+            "min": 329805.0,
+            "max": 5039949.0,
+            "count": 472
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
+            "value": -0.010436630807816982,
+            "min": -0.09697045385837555,
+            "max": 0.1714733988046646,
+            "count": 472
+        },
+        "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
+            "value": -1.6385509967803955,
+            "min": -16.600444793701172,
+            "max": 23.41659164428711,
+            "count": 472
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
+            "value": -0.01028787437826395,
+            "min": -0.09972328692674637,
+            "max": 0.17430460453033447,
+            "count": 472
+        },
+        "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
+            "value": -1.6151962280273438,
+            "min": -17.1435546875,
+            "max": 23.17365837097168,
+            "count": 472
+        },
+        "SoccerTwos.Environment.CumulativeReward.mean": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 472
+        },
+        "SoccerTwos.Environment.CumulativeReward.sum": {
+            "value": 0.0,
+            "min": 0.0,
+            "max": 0.0,
+            "count": 472
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.mean": {
+            "value": 0.10489171933216654,
+            "min": -0.5669750012457371,
+            "max": 0.44391110796987276,
+            "count": 472
+        },
+        "SoccerTwos.Policy.ExtrinsicReward.sum": {
+            "value": 16.467999935150146,
+            "min": -50.66320013999939,
+            "max": 46.512000262737274,
+            "count": 472
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.mean": {
+            "value": 0.10489171933216654,
+            "min": -0.5669750012457371,
+            "max": 0.44391110796987276,
+            "count": 472
+        },
+        "SoccerTwos.Environment.GroupCumulativeReward.sum": {
+            "value": 16.467999935150146,
+            "min": -50.66320013999939,
+            "max": 46.512000262737274,
+            "count": 472
+        },
+        "SoccerTwos.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 472
+        },
+        "SoccerTwos.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 472
+        },
+        "SoccerTwos.Losses.PolicyLoss.mean": {
+            "value": 0.016275092681947476,
+            "min": 0.010151559529488926,
+            "max": 0.024196836646297015,
+            "count": 227
+        },
+        "SoccerTwos.Losses.PolicyLoss.sum": {
+            "value": 0.016275092681947476,
+            "min": 0.010151559529488926,
+            "max": 0.024196836646297015,
+            "count": 227
+        },
+        "SoccerTwos.Losses.ValueLoss.mean": {
+            "value": 0.09684030537803968,
+            "min": 0.0013416305688830714,
+            "max": 0.11689281612634658,
+            "count": 227
+        },
+        "SoccerTwos.Losses.ValueLoss.sum": {
+            "value": 0.09684030537803968,
+            "min": 0.0013416305688830714,
+            "max": 0.11689281612634658,
+            "count": 227
+        },
+        "SoccerTwos.Losses.BaselineLoss.mean": {
+            "value": 0.09833643784125647,
+            "min": 0.0013579658038603763,
+            "max": 0.11826808328429858,
+            "count": 227
+        },
+        "SoccerTwos.Losses.BaselineLoss.sum": {
+            "value": 0.09833643784125647,
+            "min": 0.0013579658038603763,
+            "max": 0.11826808328429858,
+            "count": 227
+        },
+        "SoccerTwos.Policy.LearningRate.mean": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 227
+        },
+        "SoccerTwos.Policy.LearningRate.sum": {
+            "value": 0.0003,
+            "min": 0.0003,
+            "max": 0.0003,
+            "count": 227
+        },
+        "SoccerTwos.Policy.Epsilon.mean": {
+            "value": 0.20000000000000007,
+            "min": 0.20000000000000007,
+            "max": 0.20000000000000007,
+            "count": 227
+        },
+        "SoccerTwos.Policy.Epsilon.sum": {
+            "value": 0.20000000000000007,
+            "min": 0.20000000000000007,
+            "max": 0.20000000000000007,
+            "count": 227
+        },
+        "SoccerTwos.Policy.Beta.mean": {
+            "value": 0.005000000000000001,
+            "min": 0.005000000000000001,
+            "max": 0.005000000000000001,
+            "count": 227
+        },
+        "SoccerTwos.Policy.Beta.sum": {
+            "value": 0.005000000000000001,
+            "min": 0.005000000000000001,
+            "max": 0.005000000000000001,
+            "count": 227
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1688468546",
+        "python_version": "3.10.10 (main, Mar 21 2023, 18:45:11) [GCC 11.2.0]",
+        "command_line_arguments": "/opt/conda/bin/mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/SoccerTwos.x86_64 --run-id=SoccerTwos --no-graphics --resume",
+        "mlagents_version": "0.31.0.dev0",
+        "mlagents_envs_version": "0.31.0.dev0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "1.11.0+cu102",
+        "numpy_version": "1.21.2",
+        "end_time_seconds": "1688485154"
+    },
+    "total": 16607.525235416368,
+    "count": 1,
+    "self": 0.013366627972573042,
+    "children": {
+        "run_training.setup": {
+            "total": 0.015603977721184492,
+            "count": 1,
+            "self": 0.015603977721184492
+        },
+        "TrainerController.start_learning": {
+            "total": 16607.496264810674,
+            "count": 1,
+            "self": 8.919515123125166,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 1.5175714301876724,
+                    "count": 25,
+                    "self": 1.5175714301876724
+                },
+                "TrainerController.advance": {
+                    "total": 16596.756896799896,
+                    "count": 322264,
+                    "self": 7.916705624666065,
+                    "children": {
+                        "env_step": {
+                            "total": 5911.727526604664,
+                            "count": 322264,
+                            "self": 4514.543463871349,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 1392.023328505922,
+                                    "count": 322264,
+                                    "self": 49.78212635125965,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 1342.2412021546625,
+                                            "count": 595496,
+                                            "self": 1342.2412021546625
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 5.1607342273928225,
+                                    "count": 322264,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 16555.016848264262,
+                                            "count": 322264,
+                                            "is_parallel": true,
+                                            "self": 12923.445410506334,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.00312175415456295,
+                                                            "count": 2,
+                                                            "is_parallel": true,
+                                                            "self": 0.0008582943119108677,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.0022634598426520824,
+                                                                    "count": 8,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0022634598426520824
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.026854357682168484,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0006880271248519421,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.0005317311733961105,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0005317311733961105
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.023468355182558298,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.023468355182558298
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.002166244201362133,
+                                                                    "count": 2,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.000483611598610878,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.001682632602751255,
+                                                                            "count": 8,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.001682632602751255
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "steps_from_proto": {
+                                                    "total": 0.053547489922493696,
+                                                    "count": 48,
+                                                    "is_parallel": true,
+                                                    "self": 0.010899828281253576,
+                                                    "children": {
+                                                        "_process_rank_one_or_two_observation": {
+                                                            "total": 0.04264766164124012,
+                                                            "count": 192,
+                                                            "is_parallel": true,
+                                                            "self": 0.04264766164124012
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 3631.5178902680054,
+                                                    "count": 322263,
+                                                    "is_parallel": true,
+                                                    "self": 189.9846967374906,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 131.83427887735888,
+                                                            "count": 322263,
+                                                            "is_parallel": true,
+                                                            "self": 131.83427887735888
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 2676.0341983493418,
+                                                            "count": 322263,
+                                                            "is_parallel": true,
+                                                            "self": 2676.0341983493418
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 633.6647163038142,
+                                                            "count": 644526,
+                                                            "is_parallel": true,
+                                                            "self": 126.69072948535904,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 506.97398681845516,
+                                                                    "count": 2578104,
+                                                                    "is_parallel": true,
+                                                                    "self": 506.97398681845516
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 10677.112664570566,
+                            "count": 322264,
+                            "self": 69.58496827818453,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 1633.3974608271383,
+                                    "count": 322264,
+                                    "self": 1630.1399948387407,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 3.2574659883975983,
+                                            "count": 10,
+                                            "self": 3.2574659883975983
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 8974.130235465243,
+                                    "count": 228,
+                                    "self": 946.202926828526,
+                                    "children": {
+                                        "TorchPOCAOptimizer.update": {
+                                            "total": 8027.9273086367175,
+                                            "count": 6840,
+                                            "self": 8027.9273086367175
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 2.514570951461792e-06,
+                    "count": 1,
+                    "self": 2.514570951461792e-06
+                },
+                "TrainerController._save_models": {
+                    "total": 0.30227894289419055,
+                    "count": 1,
+                    "self": 0.005925939884036779,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.29635300301015377,
+                            "count": 1,
+                            "self": 0.29635300301015377
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,66 @@
+{
+    "SoccerTwos": {
+        "elo": 1555.8789853677063,
+        "checkpoints": [
+            {
+                "steps": 3499953,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-3499953.onnx",
+                "reward": 0.0,
+                "creation_time": 1688479621.0784702,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-3499953.pt"
+                ]
+            },
+            {
+                "steps": 3999934,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-3999934.onnx",
+                "reward": 0.0,
+                "creation_time": 1688481429.264853,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-3999934.pt"
+                ]
+            },
+            {
+                "steps": 4499936,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-4499936.onnx",
+                "reward": 0.0,
+                "creation_time": 1688483203.9654279,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-4499936.pt"
+                ]
+            },
+            {
+                "steps": 4999968,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-4999968.onnx",
+                "reward": 0.0,
+                "creation_time": 1688484962.4464383,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-4999968.pt"
+                ]
+            },
+            {
+                "steps": 5045530,
+                "file_path": "results/SoccerTwos/SoccerTwos/SoccerTwos-5045530.onnx",
+                "reward": null,
+                "creation_time": 1688485154.198391,
+                "auxillary_file_paths": [
+                    "results/SoccerTwos/SoccerTwos/SoccerTwos-5045530.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 5045530,
+            "file_path": "results/SoccerTwos/SoccerTwos.onnx",
+            "reward": null,
+            "creation_time": 1688485154.198391,
+            "auxillary_file_paths": [
+                "results/SoccerTwos/SoccerTwos/SoccerTwos-5045530.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "0.31.0.dev0",
+        "torch_version": "1.11.0+cu102"
+    }
+}