First training

README.md

@@ -0,0 +1,35 @@
+---
+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://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: sighmon/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:cbc6cab8a0a402aee89c455bbf8be55b30d4a040cff5188f5d5902e463c6d071
+size 2259626

Worm/Worm-1010000.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbc6cab8a0a402aee89c455bbf8be55b30d4a040cff5188f5d5902e463c6d071
+size 2259626

Worm/Worm-1010000.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f063ef8514b13e1043fad16d81093c63b1bc89ad03094b6185fa16c55bd480a
+size 13496972

Worm/Worm-499000.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd93f6096ef6a4874112728d2ed5b0693f8df6d52245b63ac77a9a5f2c46633f
+size 2259626

Worm/Worm-499000.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:871cd04f2ce3d94158ebdd5fabe4799fe2ca58e76379ebd1ed8a95fdb5536d7c
+size 13496887

Worm/Worm-999000.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5dea889eaa2e545520ffc9e6af139e9b613235730fd3a9451fc554ffb5d039d
+size 2259626

Worm/Worm-999000.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cba8e0f35b22e05f7f9e9305284c1759a895cd5634b6f8ded6b799f04104da51
+size 13496887

Worm/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91c962af242542fff9bd20aca83d04278af62fad2bd14a7a155679b8ca50a899
+size 13496802

Worm/events.out.tfevents.1739582329.4cb23311cdf8.4829.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08a6eb9420e923840a8b425e1ea43086a83a3276030923d0de988166c0e9a7c4
+size 158180

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": 1000000, "time_horizon": 1000, "summary_freq": 30000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/Worm/Worm", "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": "Worm Training", "initialize_from": null, "load_model": false, "resume": false, "force": true, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -0,0 +1,79 @@
+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: 1000000
+    time_horizon: 1000
+    summary_freq: 30000
+    threaded: false
+    self_play: null
+    behavioral_cloning: null
+env_settings:
+  env_path: ./training-envs-executables/linux/Worm/Worm
+  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: Worm Training
+  initialize_from: null
+  load_model: false
+  resume: false
+  force: true
+  train_model: false
+  inference: false
+  results_dir: results
+torch_settings:
+  device: null
+debug: false

run_logs/Player-0.log

@@ -0,0 +1,319 @@
+Mono path[0] = '/content/ml-agents/training-envs-executables/linux/Worm/Worm_Data/Managed'
+Mono config path = '/content/ml-agents/training-envs-executables/linux/Worm/Worm_Data/MonoBleedingEdge/etc'
+Found 1 interfaces on host : 0) 172.28.0.12
+Multi-casting "[IP] 172.28.0.12 [Port] 55264 [Flags] 2 [Guid] 3764076662 [EditorId] 588871222 [Version] 1048832 [Id] LinuxPlayer(13,172.28.0.12) [Debug] 0 [PackageName] LinuxPlayer [ProjectName] UnityEnvironment" to [225.0.0.222:54997]...
+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/UnityEnvironment
+Unable to load player prefs
+Initialize engine version: 2021.3.5f1 (40eb3a945986)
+[Subsystems] Discovering subsystems at path /content/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
+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  0.100 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: 0.868245 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 1 worker threads for Enlighten.
+abort_threads: Failed aborting id: 0x7e2b3ffff640, mono_thread_manage will ignore it
+
+PlayerConnection::CleanupMemory Statistics:
+[ALLOC_TEMP_TLS] TLS Allocator
+  StackAllocators : 
+    [ALLOC_TEMP_MAIN]
+      Peak usage frame count: [4.0 KB-8.0 KB]: 20194 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_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 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 6]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_AUDIO_FMOD mixer 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 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 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_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 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_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_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_Profiler.Dispatcher]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 240 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]
+      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_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_Job.Worker 0]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0.8 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 9]
+      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_EnlightenWorker]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 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_MEMORYPROFILER]
+  Peak usage frame count: [64.0 KB-128.0 KB]: 20195 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 52
+    [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]: 20195 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 5.0 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 20195 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]: 20194 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]: 20195 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]: 20195 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]: 20194 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]: 20195 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]: 20194 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: [16.0 KB-32.0 KB]: 20195 frames
+  Requested Block Size 16.0 MB
+  Peak Block count 1
+  Peak Allocated memory 29.2 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":1739583719108,"processId":4846,"allocatedMemory":1970109,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"NewDelete":12801},{"Thread":34460},{"Manager":10603},{"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":3423},{"DynamicArray":30868},{"HashMap":7680},{"Utility":1360},{"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": 1.3861826658248901,
+            "min": 1.3861826658248901,
+            "max": 1.418938398361206,
+            "count": 33
+        },
+        "Worm.Policy.Entropy.sum": {
+            "value": 41585.48046875,
+            "min": 41585.48046875,
+            "max": 42568.15234375,
+            "count": 33
+        },
+        "Worm.Environment.EpisodeLength.mean": {
+            "value": 999.0,
+            "min": 999.0,
+            "max": 999.0,
+            "count": 33
+        },
+        "Worm.Environment.EpisodeLength.sum": {
+            "value": 29970.0,
+            "min": 29970.0,
+            "max": 29970.0,
+            "count": 33
+        },
+        "Worm.Step.mean": {
+            "value": 989000.0,
+            "min": 29000.0,
+            "max": 989000.0,
+            "count": 33
+        },
+        "Worm.Step.sum": {
+            "value": 989000.0,
+            "min": 29000.0,
+            "max": 989000.0,
+            "count": 33
+        },
+        "Worm.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 6.004525661468506,
+            "min": -0.051633987575769424,
+            "max": 6.004525661468506,
+            "count": 33
+        },
+        "Worm.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 180.13577270507812,
+            "min": -1.4973856210708618,
+            "max": 180.13577270507812,
+            "count": 33
+        },
+        "Worm.Environment.CumulativeReward.mean": {
+            "value": 61.040428225199385,
+            "min": 0.1919361693656136,
+            "max": 61.930335680643715,
+            "count": 33
+        },
+        "Worm.Environment.CumulativeReward.sum": {
+            "value": 1831.2128467559814,
+            "min": 5.566148911602795,
+            "max": 1857.9100704193115,
+            "count": 33
+        },
+        "Worm.Policy.ExtrinsicReward.mean": {
+            "value": 61.040428225199385,
+            "min": 0.1919361693656136,
+            "max": 61.930335680643715,
+            "count": 33
+        },
+        "Worm.Policy.ExtrinsicReward.sum": {
+            "value": 1831.2128467559814,
+            "min": 5.566148911602795,
+            "max": 1857.9100704193115,
+            "count": 33
+        },
+        "Worm.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 33
+        },
+        "Worm.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 33
+        },
+        "Worm.Losses.PolicyLoss.mean": {
+            "value": 0.014891214704784076,
+            "min": 0.01339010396900232,
+            "max": 0.021539426104850247,
+            "count": 32
+        },
+        "Worm.Losses.PolicyLoss.sum": {
+            "value": 0.014891214704784076,
+            "min": 0.01339010396900232,
+            "max": 0.021539426104850247,
+            "count": 32
+        },
+        "Worm.Losses.ValueLoss.mean": {
+            "value": 0.6217004770324344,
+            "min": 0.0009417563407970149,
+            "max": 0.6217004770324344,
+            "count": 32
+        },
+        "Worm.Losses.ValueLoss.sum": {
+            "value": 0.6217004770324344,
+            "min": 0.0009417563407970149,
+            "max": 0.6217004770324344,
+            "count": 32
+        },
+        "Worm.Policy.LearningRate.mean": {
+            "value": 1.2000096000000011e-05,
+            "min": 1.2000096000000011e-05,
+            "max": 0.0002910000029999999,
+            "count": 32
+        },
+        "Worm.Policy.LearningRate.sum": {
+            "value": 1.2000096000000011e-05,
+            "min": 1.2000096000000011e-05,
+            "max": 0.0002910000029999999,
+            "count": 32
+        },
+        "Worm.Policy.Epsilon.mean": {
+            "value": 0.10400000000000001,
+            "min": 0.10400000000000001,
+            "max": 0.19699999999999998,
+            "count": 32
+        },
+        "Worm.Policy.Epsilon.sum": {
+            "value": 0.10400000000000001,
+            "min": 0.10400000000000001,
+            "max": 0.19699999999999998,
+            "count": 32
+        },
+        "Worm.Policy.Beta.mean": {
+            "value": 0.00020960000000000022,
+            "min": 0.00020960000000000022,
+            "max": 0.0048503,
+            "count": 32
+        },
+        "Worm.Policy.Beta.sum": {
+            "value": 0.00020960000000000022,
+            "min": 0.00020960000000000022,
+            "max": 0.0048503,
+            "count": 32
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1739582328",
+        "python_version": "3.10.12 (main, Jul  5 2023, 18:54:27) [GCC 11.2.0]",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Worm.yaml --env=./training-envs-executables/linux/Worm/Worm --run-id=Worm Training --no-graphics --force",
+        "mlagents_version": "1.2.0.dev0",
+        "mlagents_envs_version": "1.2.0.dev0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "2.6.0+cu124",
+        "numpy_version": "1.23.5",
+        "end_time_seconds": "1739583719"
+    },
+    "total": 1390.625428935,
+    "count": 1,
+    "self": 0.5769163620000199,
+    "children": {
+        "run_training.setup": {
+            "total": 0.021503205000044545,
+            "count": 1,
+            "self": 0.021503205000044545
+        },
+        "TrainerController.start_learning": {
+            "total": 1390.0270093679999,
+            "count": 1,
+            "self": 2.0359425620704314,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 3.182218063000164,
+                    "count": 1,
+                    "self": 3.182218063000164
+                },
+                "TrainerController.advance": {
+                    "total": 1384.6823440109295,
+                    "count": 101000,
+                    "self": 2.120266040037677,
+                    "children": {
+                        "env_step": {
+                            "total": 1166.401741433958,
+                            "count": 101000,
+                            "self": 967.9786514139496,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 197.17970346301627,
+                                    "count": 101000,
+                                    "self": 7.428139034011792,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 189.75156442900447,
+                                            "count": 101000,
+                                            "self": 189.75156442900447
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 1.2433865569921636,
+                                    "count": 101000,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 1386.0217035990797,
+                                            "count": 101000,
+                                            "is_parallel": true,
+                                            "self": 551.4499236080947,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.0010331799999221403,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.00025955199998861644,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.0007736279999335238,
+                                                                    "count": 2,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0007736279999335238
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.031536455999912505,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0002573480003320583,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.0004152059998432378,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0004152059998432378
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.030326579999837122,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.030326579999837122
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.0005373219999000867,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00016747100016800687,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.0003698509997320798,
+                                                                            "count": 2,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.0003698509997320798
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 834.5717799909851,
+                                                    "count": 100999,
+                                                    "is_parallel": true,
+                                                    "self": 18.06819325792003,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 30.929885190010054,
+                                                            "count": 100999,
+                                                            "is_parallel": true,
+                                                            "self": 30.929885190010054
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 742.2309833430102,
+                                                            "count": 100999,
+                                                            "is_parallel": true,
+                                                            "self": 742.2309833430102
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 43.34271820004483,
+                                                            "count": 100999,
+                                                            "is_parallel": true,
+                                                            "self": 13.99210863813255,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 29.35060956191228,
+                                                                    "count": 201998,
+                                                                    "is_parallel": true,
+                                                                    "self": 29.35060956191228
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 216.16033653693376,
+                            "count": 101000,
+                            "self": 2.382445713875086,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 56.379384717058656,
+                                    "count": 101000,
+                                    "self": 56.02510363605893,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 0.3542810809997263,
+                                            "count": 2,
+                                            "self": 0.3542810809997263
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 157.398506106,
+                                    "count": 33,
+                                    "self": 126.13356308099537,
+                                    "children": {
+                                        "TorchPPOOptimizer.update": {
+                                            "total": 31.26494302500464,
+                                            "count": 1386,
+                                            "self": 31.26494302500464
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 9.509999472356867e-07,
+                    "count": 1,
+                    "self": 9.509999472356867e-07
+                },
+                "TrainerController._save_models": {
+                    "total": 0.12650378099988302,
+                    "count": 1,
+                    "self": 0.0017894199995680538,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.12471436100031497,
+                            "count": 1,
+                            "self": 0.12471436100031497
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,47 @@
+{
+    "Worm": {
+        "checkpoints": [
+            {
+                "steps": 499000,
+                "file_path": "results/Worm Training/Worm/Worm-499000.onnx",
+                "reward": 5.444664415560271,
+                "creation_time": 1739583014.3891568,
+                "auxillary_file_paths": [
+                    "results/Worm Training/Worm/Worm-499000.pt"
+                ]
+            },
+            {
+                "steps": 999000,
+                "file_path": "results/Worm Training/Worm/Worm-999000.onnx",
+                "reward": 74.78468449910481,
+                "creation_time": 1739583706.4880865,
+                "auxillary_file_paths": [
+                    "results/Worm Training/Worm/Worm-999000.pt"
+                ]
+            },
+            {
+                "steps": 1010000,
+                "file_path": "results/Worm Training/Worm/Worm-1010000.onnx",
+                "reward": 68.18643827438355,
+                "creation_time": 1739583718.5951498,
+                "auxillary_file_paths": [
+                    "results/Worm Training/Worm/Worm-1010000.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 1010000,
+            "file_path": "results/Worm Training/Worm.onnx",
+            "reward": 68.18643827438355,
+            "creation_time": 1739583718.5951498,
+            "auxillary_file_paths": [
+                "results/Worm Training/Worm/Worm-1010000.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "1.2.0.dev0",
+        "torch_version": "2.6.0+cu124"
+    }
+}