First training of Worm

README.md

@@ -0,0 +1,29 @@
+---
+library_name: ml-agents
+tags:
+- Worm
+- deep-reinforcement-learning
+- reinforcement-learning
+- ML-Agents-Worm
+---
+
+  # **ppo** Agent playing **Worm**
+  This is a trained model of a **ppo** agent playing **Worm** using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
+  
+  ## Usage (with ML-Agents)
+  The Documentation: https://github.com/huggingface/ml-agents#get-started
+  We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
+
+
+  ### Resume the training
+  ```
+  mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume
+  ```
+  ### Watch your Agent play
+  You can watch your agent **playing directly in your browser:**.
+  
+  1. Go to https://huggingface.co/spaces/unity/ML-Agents-Worm
+  2. Step 1: Find your model_id: markeidsaune/ppo-Worm
+  3. Step 2: Select your *.nn /*.onnx file
+  4. Click on Watch the agent play 👀
+  

Worm.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2f53855f52b7a92f1ea2839c4bf4f5665fd44d44bdf06b78ef9d83bfe9fdb6a
+size 2256933

Worm/Worm-5499000.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7db8569c702ce4fff67c68a56115430a1c15c3eda570397897b1cc17f59be019
+size 2256933

Worm/Worm-5499000.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fde7b9f8c41bdaa353ba7b04a1e5ad99b7f97ec42f113d22e54c676b5c7ce753
+size 13491173

Worm/Worm-5999000.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:105e31421a56a2bb9aa17ad1974839104cba490f1462d689840177188f3bdbfd
+size 2256933

Worm/Worm-5999000.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cac7ab8932985936c3d8049f16d869a7132f427dfab5366f4392a30ff7016693
+size 13491173

Worm/Worm-6499000.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b05c8ebb9ebbdba5bbf7932cf8d0b450ffdb4d5e48225400b07b66c228ea3b1
+size 2256933

Worm/Worm-6499000.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70b6643dba446a84fca5153f7ac87a777101d6c19a300ad9e49d7c9945e3b001
+size 13491173

Worm/Worm-6999000.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7f933b913eb64e6c906d9bfcd5d349804c59408d1f98d040af49d5ae95772f6
+size 2256933

Worm/Worm-6999000.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55bb05f2e261fa8e0e2c828891ce37bd59eba042fc884048f3f692c91ccb6ae3
+size 13491173

Worm/Worm-7010000.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2f53855f52b7a92f1ea2839c4bf4f5665fd44d44bdf06b78ef9d83bfe9fdb6a
+size 2256933

Worm/Worm-7010000.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f671e5f3cea8c4ac8e564e9c8c2b4529c59a1357f28e40082c7d326ac596c7b7
+size 13491173

Worm/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f671e5f3cea8c4ac8e564e9c8c2b4529c59a1357f28e40082c7d326ac596c7b7
+size 13491173

Worm/events.out.tfevents.1683739606.barry.1658342.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c364d7dc763aaa5ba3d1d91f275fa1b9fcf70ecf2bdd1402f98212084863f5c7
+size 273551

config.json

@@ -0,0 +1 @@
+{"default_settings": null, "behaviors": {"Worm": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 2024, "buffer_size": 20240, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 500000, "network_settings": {"normalize": true, "hidden_units": 512, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.995, "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": 7000000, "time_horizon": 1000, "summary_freq": 30000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./ml-agents/training-envs-executables/linux/Worm/Worm", "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": "Worm1", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -0,0 +1,77 @@
+default_settings: null
+behaviors:
+  Worm:
+    trainer_type: ppo
+    hyperparameters:
+      batch_size: 2024
+      buffer_size: 20240
+      learning_rate: 0.0003
+      beta: 0.005
+      epsilon: 0.2
+      lambd: 0.95
+      num_epoch: 3
+      shared_critic: false
+      learning_rate_schedule: linear
+      beta_schedule: linear
+      epsilon_schedule: linear
+    checkpoint_interval: 500000
+    network_settings:
+      normalize: true
+      hidden_units: 512
+      num_layers: 3
+      vis_encode_type: simple
+      memory: null
+      goal_conditioning_type: hyper
+      deterministic: false
+    reward_signals:
+      extrinsic:
+        gamma: 0.995
+        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: 7000000
+    time_horizon: 1000
+    summary_freq: 30000
+    threaded: false
+    self_play: null
+    behavioral_cloning: null
+env_settings:
+  env_path: ./ml-agents/training-envs-executables/linux/Worm/Worm
+  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: Worm1
+  initialize_from: null
+  load_model: false
+  resume: false
+  force: false
+  train_model: false
+  inference: false
+  results_dir: results
+torch_settings:
+  device: null
+debug: false

run_logs/Player-0.log

@@ -0,0 +1,384 @@
+Mono path[0] = '/home/mark/rl_course/unit5/ml-agents/training-envs-executables/linux/Worm/Worm_Data/Managed'
+Mono config path = '/home/mark/rl_course/unit5/ml-agents/training-envs-executables/linux/Worm/Worm_Data/MonoBleedingEdge/etc'
+Found 3 interfaces on host : 0) 192.168.0.126 1) 172.17.0.1 2) 172.23.0.1
+Multi-casting "[IP] 192.168.0.126 [Port] 55210 [Flags] 2 [Guid] 1118717541 [EditorId] 588871222 [Version] 1048832 [Id] LinuxPlayer(13,192.168.0.126) [Debug] 0 [PackageName] LinuxPlayer [ProjectName] UnityEnvironment" to [225.0.0.222:54997]...
+Preloaded 'lib_burst_generated.so'
+Preloaded 'libgrpc_csharp_ext.x64.so'
+Initialize engine version: 2021.3.5f1 (40eb3a945986)
+[Subsystems] Discovering subsystems at path /home/mark/rl_course/unit5/ml-agents/training-envs-executables/linux/Worm/Worm_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  0.101 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: 'Legacy Shaders/Diffuse' - 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 Legacy Shaders/Diffuse shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+WARNING: Shader Unsupported: 'Legacy Shaders/Diffuse' - 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: 'ML-Agents/GridPattern' - 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 ML-Agents/GridPattern shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+WARNING: Shader Unsupported: 'ML-Agents/GridPattern' - 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?
+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?
+UnloadTime: 1.237660 ms
+ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+requesting resize 84 x 84
+Setting up 10 worker threads for Enlighten.
+PlayerConnection::CleanupMemory Statistics:
+[ALLOC_TEMP_TLS] TLS Allocator
+  StackAllocators : 
+    [ALLOC_TEMP_MAIN]
+      Peak usage frame count: [4.0 KB-8.0 KB]: 140164 frames, [2.0 MB-4.0 MB]: 1 frames
+      Initial Block Size 4.0 MB
+      Current Block Size 4.0 MB
+      Peak Allocated Bytes 2.0 MB
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 18]
+      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 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 4]
+      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 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 3]
+      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_TEMP_Job.Worker 13]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 2]
+      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_Job.Worker 15]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 12]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Loading.PreloadManager]
+      Initial Block Size 256.0 KB
+      Current Block Size 284.0 KB
+      Peak Allocated Bytes 243.3 KB
+      Overflow Count 4
+    [ALLOC_TEMP_AUDIO_FMOD PulseAudio Mixer]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 17]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 14]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0.8 KB
+      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 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 2]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Profiler.Dispatcher]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 11]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 6]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 0]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_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 9]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_EnlightenWorker] x 10
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_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_Loading.AsyncRead]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 128 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 10]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 16]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 6]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_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_AUDIO_FMOD stream thread]
+      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 7]
+      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 1]
+      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_AssetGarbageCollectorHelper] x 19
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 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_Background Job.Worker 14]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 7]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+[ALLOC_MEMORYPROFILER]
+  Peak usage frame count: [64.0 KB-128.0 KB]: 140165 frames
+  Requested Block Size 1.0 MB
+  Peak Block count 1
+  Peak Allocated memory 103.1 KB
+  Peak Large allocation bytes 0 B
+[ALLOC_DEFAULT] Dual Thread Allocator
+  Peak main deferred allocation count 13
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 0.8 MB
+    [ALLOC_DEFAULT_MAIN]
+      Peak usage frame count: [4.0 MB-8.0 MB]: 140165 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 5.3 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 140165 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 17.9 MB
+      Peak Large allocation bytes 16.0 MB
+[ALLOC_TEMP_JOB_1_FRAME]
+  Initial Block Size 2.0 MB
+  Used Block Count 1
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_TEMP_JOB_2_FRAMES]
+  Initial Block Size 2.0 MB
+  Used Block Count 1
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_TEMP_JOB_4_FRAMES (JobTemp)]
+  Initial Block Size 2.0 MB
+  Used Block Count 2
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_TEMP_JOB_ASYNC (Background)]
+  Initial Block Size 1.0 MB
+  Used Block Count 3
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_GFX] Dual Thread Allocator
+  Peak main deferred allocation count 0
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 0.8 MB
+    [ALLOC_GFX_MAIN]
+      Peak usage frame count: [32.0 KB-64.0 KB]: 140164 frames, [64.0 KB-128.0 KB]: 1 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 67.0 KB
+      Peak Large allocation bytes 0 B
+    [ALLOC_GFX_THREAD]
+      Peak usage frame count: [128.0 KB-256.0 KB]: 140165 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 151.2 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 0.8 MB
+    [ALLOC_CACHEOBJECTS_MAIN]
+      Peak usage frame count: [0.5 MB-1.0 MB]: 140165 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: [256.0 KB-0.5 MB]: 140164 frames, [4.0 MB-8.0 MB]: 1 frames
+      Requested Block Size 4.0 MB
+      Peak Block count 2
+      Peak Allocated memory 4.2 MB
+      Peak Large allocation bytes 0 B
+[ALLOC_TYPETREE] Dual Thread Allocator
+  Peak main deferred allocation count 0
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 0.8 MB
+    [ALLOC_TYPETREE_MAIN]
+      Peak usage frame count: [0-1.0 KB]: 140165 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: [4.0 KB-8.0 KB]: 140164 frames, [8.0 KB-16.0 KB]: 1 frames
+      Requested Block Size 2.0 MB
+      Peak Block count 1
+      Peak Allocated memory 9.3 KB
+      Peak Large allocation bytes 0 B
+[ALLOC_PROFILER]
+  Peak usage frame count: [32.0 KB-64.0 KB]: 140165 frames
+  Requested Block Size 16.0 MB
+  Peak Block count 1
+  Peak Allocated memory 43.8 KB
+  Peak Large allocation bytes 0 B
+    [ALLOC_PROFILER_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 332 B
+##utp:{"type":"MemoryLeaks","version":2,"phase":"Immediate","time":1683750109083,"processId":1658412,"allocatedMemory":1994271,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"NewDelete":12801},{"Thread":34964},{"Manager":26831},{"VertexData":12},{"Geometry":280},{"Texture":16},{"Shader":69173},{"Material":24},{"GfxDevice":35248},{"Animation":304},{"Audio":3976},{"Physics":288},{"Serialization":216},{"Input":9176},{"JobScheduler":200},{"Mono":40},{"ScriptingNativeRuntime":216},{"BaseObject":1609212},{"Resource":592},{"Renderer":1936},{"Transform":48},{"File":800},{"WebCam":24},{"Culling":40},{"Terrain":953},{"Wind":24},{"String":3509},{"DynamicArray":30868},{"HashMap":7680},{"Utility":8704},{"PoolAlloc":1160},{"TypeTree":1792},{"ScriptManager":80},{"RuntimeInitializeOnLoadManager":72},{"SpriteAtlas":112},{"GI":3272},{"Unet":16},{"Director":7760},{"WebRequest":720},{"VR":45473},{"SceneManager":424},{"Video":32},{"LazyScriptCache":32},{"NativeArray":384},{"Camera":25},{"Secure":1},{"SerializationCache":624},{"APIUpdating":5872},{"Subsystems":384},{"VirtualTexturing":57552},{"AssetReference":32}]}

run_logs/timers.json

@@ -0,0 +1,362 @@
+{
+    "name": "root",
+    "gauges": {
+        "Worm.Policy.Entropy.mean": {
+            "value": 0.7546901106834412,
+            "min": 0.7546901106834412,
+            "max": 1.418938398361206,
+            "count": 233
+        },
+        "Worm.Policy.Entropy.sum": {
+            "value": 22640.703125,
+            "min": 22640.703125,
+            "max": 42568.15234375,
+            "count": 233
+        },
+        "Worm.Environment.EpisodeLength.mean": {
+            "value": 999.0,
+            "min": 999.0,
+            "max": 999.0,
+            "count": 233
+        },
+        "Worm.Environment.EpisodeLength.sum": {
+            "value": 29970.0,
+            "min": 29970.0,
+            "max": 29970.0,
+            "count": 233
+        },
+        "Worm.Step.mean": {
+            "value": 6989000.0,
+            "min": 29000.0,
+            "max": 6989000.0,
+            "count": 233
+        },
+        "Worm.Step.sum": {
+            "value": 6989000.0,
+            "min": 29000.0,
+            "max": 6989000.0,
+            "count": 233
+        },
+        "Worm.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 238.57986450195312,
+            "min": -0.030264511704444885,
+            "max": 238.7449493408203,
+            "count": 233
+        },
+        "Worm.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 7157.39599609375,
+            "min": -0.8776708245277405,
+            "max": 7162.3486328125,
+            "count": 233
+        },
+        "Worm.Environment.CumulativeReward.mean": {
+            "value": 1188.4943888346354,
+            "min": 0.17140958830714226,
+            "max": 1188.6684448242188,
+            "count": 233
+        },
+        "Worm.Environment.CumulativeReward.sum": {
+            "value": 35654.83166503906,
+            "min": 5.142287649214268,
+            "max": 35660.05334472656,
+            "count": 233
+        },
+        "Worm.Policy.ExtrinsicReward.mean": {
+            "value": 1188.4943888346354,
+            "min": 0.17140958830714226,
+            "max": 1188.6684448242188,
+            "count": 233
+        },
+        "Worm.Policy.ExtrinsicReward.sum": {
+            "value": 35654.83166503906,
+            "min": 5.142287649214268,
+            "max": 35660.05334472656,
+            "count": 233
+        },
+        "Worm.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 233
+        },
+        "Worm.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 233
+        },
+        "Worm.Losses.PolicyLoss.mean": {
+            "value": 0.01411332649392231,
+            "min": 0.01047790824668482,
+            "max": 0.0235713456256365,
+            "count": 232
+        },
+        "Worm.Losses.PolicyLoss.sum": {
+            "value": 0.01411332649392231,
+            "min": 0.01047790824668482,
+            "max": 0.0235713456256365,
+            "count": 232
+        },
+        "Worm.Losses.ValueLoss.mean": {
+            "value": 11.896761213030134,
+            "min": 0.0010334085063299252,
+            "max": 13.696317945207868,
+            "count": 232
+        },
+        "Worm.Losses.ValueLoss.sum": {
+            "value": 11.896761213030134,
+            "min": 0.0010334085063299252,
+            "max": 13.696317945207868,
+            "count": 232
+        },
+        "Worm.Policy.LearningRate.mean": {
+            "value": 1.7143851428571302e-06,
+            "min": 1.7143851428571302e-06,
+            "max": 0.00029871428614285713,
+            "count": 232
+        },
+        "Worm.Policy.LearningRate.sum": {
+            "value": 1.7143851428571302e-06,
+            "min": 1.7143851428571302e-06,
+            "max": 0.00029871428614285713,
+            "count": 232
+        },
+        "Worm.Policy.Epsilon.mean": {
+            "value": 0.10057142857142858,
+            "min": 0.10057142857142858,
+            "max": 0.1995714285714285,
+            "count": 232
+        },
+        "Worm.Policy.Epsilon.sum": {
+            "value": 0.10057142857142858,
+            "min": 0.10057142857142858,
+            "max": 0.1995714285714285,
+            "count": 232
+        },
+        "Worm.Policy.Beta.mean": {
+            "value": 3.851428571428551e-05,
+            "min": 3.851428571428551e-05,
+            "max": 0.004978614285714285,
+            "count": 232
+        },
+        "Worm.Policy.Beta.sum": {
+            "value": 3.851428571428551e-05,
+            "min": 3.851428571428551e-05,
+            "max": 0.004978614285714285,
+            "count": 232
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1683739604",
+        "python_version": "3.10.11 (main, Apr  5 2023, 14:15:10) [GCC 9.4.0]",
+        "command_line_arguments": "/home/mark/rl_course/.unit5_venv/bin/mlagents-learn ./ml-agents/config/ppo/Worm.yaml --env=./ml-agents/training-envs-executables/linux/Worm/Worm --run-id=Worm1 --no-graphics",
+        "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": "1683750109"
+    },
+    "total": 10504.193586319685,
+    "count": 1,
+    "self": 0.3231488047167659,
+    "children": {
+        "run_training.setup": {
+            "total": 0.013392854947596788,
+            "count": 1,
+            "self": 0.013392854947596788
+        },
+        "TrainerController.start_learning": {
+            "total": 10503.85704466002,
+            "count": 1,
+            "self": 13.384338697884232,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 5.288313401862979,
+                    "count": 1,
+                    "self": 5.288313401862979
+                },
+                "TrainerController.advance": {
+                    "total": 10485.048619326204,
+                    "count": 701000,
+                    "self": 13.016889019403607,
+                    "children": {
+                        "env_step": {
+                            "total": 8093.429603974801,
+                            "count": 701000,
+                            "self": 7228.569016146474,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 855.4780502999201,
+                                    "count": 701000,
+                                    "self": 45.95606778562069,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 809.5219825142995,
+                                            "count": 701000,
+                                            "self": 809.5219825142995
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 9.382537528406829,
+                                    "count": 701000,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 10480.880464751739,
+                                            "count": 701000,
+                                            "is_parallel": true,
+                                            "self": 4168.93715487374,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.0022225920110940933,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0005126679316163063,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.001709924079477787,
+                                                                    "count": 2,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.001709924079477787
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.028827323112636805,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0005137305706739426,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.0008109067566692829,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0008109067566692829
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.026349851861596107,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.026349851861596107
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.0011528339236974716,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00031482381746172905,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.0008380101062357426,
+                                                                            "count": 2,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.0008380101062357426
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 6311.943309877999,
+                                                    "count": 700999,
+                                                    "is_parallel": true,
+                                                    "self": 229.04008141485974,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 382.5745876613073,
+                                                            "count": 700999,
+                                                            "is_parallel": true,
+                                                            "self": 382.5745876613073
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 5163.548799792305,
+                                                            "count": 700999,
+                                                            "is_parallel": true,
+                                                            "self": 5163.548799792305
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 536.7798410095274,
+                                                            "count": 700999,
+                                                            "is_parallel": true,
+                                                            "self": 143.95231797220185,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 392.8275230373256,
+                                                                    "count": 1401998,
+                                                                    "is_parallel": true,
+                                                                    "self": 392.8275230373256
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 2378.602126332,
+                            "count": 701000,
+                            "self": 17.068648553453386,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 389.50852839881554,
+                                    "count": 701000,
+                                    "self": 387.6618690909818,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 1.846659307833761,
+                                            "count": 14,
+                                            "self": 1.846659307833761
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 1972.024949379731,
+                                    "count": 233,
+                                    "self": 1759.5650872197002,
+                                    "children": {
+                                        "TorchPPOOptimizer.update": {
+                                            "total": 212.45986216003075,
+                                            "count": 9786,
+                                            "self": 212.45986216003075
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 1.2759119272232056e-06,
+                    "count": 1,
+                    "self": 1.2759119272232056e-06
+                },
+                "TrainerController._save_models": {
+                    "total": 0.13577195815742016,
+                    "count": 1,
+                    "self": 0.0016271830536425114,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.13414477510377765,
+                            "count": 1,
+                            "self": 0.13414477510377765
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,65 @@
+{
+    "Worm": {
+        "checkpoints": [
+            {
+                "steps": 5499000,
+                "file_path": "results/Worm1/Worm/Worm-5499000.onnx",
+                "reward": 1132.8580593532986,
+                "creation_time": 1683747804.8907518,
+                "auxillary_file_paths": [
+                    "results/Worm1/Worm/Worm-5499000.pt"
+                ]
+            },
+            {
+                "steps": 5999000,
+                "file_path": "results/Worm1/Worm/Worm-5999000.onnx",
+                "reward": 1165.6572055158945,
+                "creation_time": 1683748562.8206983,
+                "auxillary_file_paths": [
+                    "results/Worm1/Worm/Worm-5999000.pt"
+                ]
+            },
+            {
+                "steps": 6499000,
+                "file_path": "results/Worm1/Worm/Worm-6499000.onnx",
+                "reward": 1169.6498059724506,
+                "creation_time": 1683749330.1018562,
+                "auxillary_file_paths": [
+                    "results/Worm1/Worm/Worm-6499000.pt"
+                ]
+            },
+            {
+                "steps": 6999000,
+                "file_path": "results/Worm1/Worm/Worm-6999000.onnx",
+                "reward": 1130.0715196397568,
+                "creation_time": 1683750096.1940665,
+                "auxillary_file_paths": [
+                    "results/Worm1/Worm/Worm-6999000.pt"
+                ]
+            },
+            {
+                "steps": 7010000,
+                "file_path": "results/Worm1/Worm/Worm-7010000.onnx",
+                "reward": 1147.0962707519532,
+                "creation_time": 1683750108.796296,
+                "auxillary_file_paths": [
+                    "results/Worm1/Worm/Worm-7010000.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 7010000,
+            "file_path": "results/Worm1/Worm.onnx",
+            "reward": 1147.0962707519532,
+            "creation_time": 1683750108.796296,
+            "auxillary_file_paths": [
+                "results/Worm1/Worm/Worm-7010000.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "0.31.0.dev0",
+        "torch_version": "1.11.0+cu102"
+    }
+}