First MLAgents

README.md

@@ -0,0 +1,31 @@
+
+---
+      tags:
+      - unity-ml-agents
+      - ml-agents
+      - deep-reinforcement-learning
+      - reinforcement-learning
+      - ML-Agents-Worm
+      library_name: ml-agents
+---
+    
+  # **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: Write your model_id: osanseviero/worms
+  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:b312c96fc2c6d8b64ba13efaef5fa48af3daf5da19840c28e4f71aafa42499d7
+size 2255979

Worm/Worm-110000.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b312c96fc2c6d8b64ba13efaef5fa48af3daf5da19840c28e4f71aafa42499d7
+size 2255979

Worm/Worm-110000.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd917782bf3dca48ed31c1996948552bd1f510edd1cd3e4863c45ac98478669c
+size 13493359

Worm/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd917782bf3dca48ed31c1996948552bd1f510edd1cd3e4863c45ac98478669c
+size 13493359

Worm/events.out.tfevents.1656848219.osanseviero-Amd-Am4-Gen3.8196.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac04f0d427a9d7e70773a747fab819a3ca967c3358f0266c0f1608e6316d36fc
+size 17283

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, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "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, "checkpoint_interval": 500000, "max_steps": 100000, "time_horizon": 1000, "summary_freq": 30000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "trained-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": "training", "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 +1,75 @@
+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
+      learning_rate_schedule: linear
+      beta_schedule: linear
+      epsilon_schedule: linear
+    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
+    checkpoint_interval: 500000
+    max_steps: 100000
+    time_horizon: 1000
+    summary_freq: 30000
+    threaded: false
+    self_play: null
+    behavioral_cloning: null
+env_settings:
+  env_path: trained-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: training
+  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 +1,364 @@
+Mono path[0] = '/home/osanseviero/Desktop/workspace/repos/ml-agents/trained-envs-executables/linux/Worm/Worm_Data/Managed'
+Mono config path = '/home/osanseviero/Desktop/workspace/repos/ml-agents/trained-envs-executables/linux/Worm/Worm_Data/MonoBleedingEdge/etc'
+Found 3 interfaces on host : 0) 192.168.178.23 1) 172.19.0.1 2) 172.17.0.1
+Multi-casting "[IP] 192.168.178.23 [Port] 55263 [Flags] 2 [Guid] 4114615211 [EditorId] 588871222 [Version] 1048832 [Id] LinuxPlayer(13,192.168.178.23) [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/osanseviero/Desktop/workspace/repos/ml-agents/trained-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  0.050 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: 0.510080 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 8 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]: 2199 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_Profiler.Dispatcher]
+      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 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_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 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_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_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_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_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 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 243.4 KB
+      Overflow Count 4
+    [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_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 14]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 3]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 12]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_AssetGarbageCollectorHelper] x 15
+      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 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 0]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 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_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 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_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] x 8
+      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_Job.Worker 7]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0.8 KB
+      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]: 2200 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]: 2200 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]: 2200 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]: 2199 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]: 2200 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]: 2200 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]: 2199 frames, [2.0 MB-4.0 MB]: 1 frames
+      Requested Block Size 4.0 MB
+      Peak Block count 1
+      Peak Allocated memory 3.8 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]: 2200 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]: 2199 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]: 2200 frames
+  Requested Block Size 16.0 MB
+  Peak Block count 1
+  Peak Allocated memory 38.5 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":1656848281392,"processId":8225,"allocatedMemory":1984199,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"NewDelete":12801},{"Thread":34852},{"Manager":18447},{"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":3565},{"DynamicArray":30868},{"HashMap":7680},{"Utility":7072},{"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": 1.4186432361602783,
+            "min": 1.41836416721344,
+            "max": 1.418938398361206,
+            "count": 3
+        },
+        "Worm.Policy.Entropy.sum": {
+            "value": 42559.296875,
+            "min": 42550.92578125,
+            "max": 42568.15234375,
+            "count": 3
+        },
+        "Worm.Environment.EpisodeLength.mean": {
+            "value": 999.0,
+            "min": 999.0,
+            "max": 999.0,
+            "count": 3
+        },
+        "Worm.Environment.EpisodeLength.sum": {
+            "value": 29970.0,
+            "min": 29970.0,
+            "max": 29970.0,
+            "count": 3
+        },
+        "Worm.Step.mean": {
+            "value": 89000.0,
+            "min": 29000.0,
+            "max": 89000.0,
+            "count": 3
+        },
+        "Worm.Step.sum": {
+            "value": 89000.0,
+            "min": 29000.0,
+            "max": 89000.0,
+            "count": 3
+        },
+        "Worm.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 0.04667310044169426,
+            "min": 0.042724449187517166,
+            "max": 0.04667310044169426,
+            "count": 3
+        },
+        "Worm.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 1.4001929759979248,
+            "min": 1.2612950801849365,
+            "max": 1.4001929759979248,
+            "count": 3
+        },
+        "Worm.Environment.CumulativeReward.mean": {
+            "value": 0.48600394654398166,
+            "min": 0.19933532153566677,
+            "max": 0.48600394654398166,
+            "count": 3
+        },
+        "Worm.Environment.CumulativeReward.sum": {
+            "value": 14.580118396319449,
+            "min": 5.9800596460700035,
+            "max": 14.580118396319449,
+            "count": 3
+        },
+        "Worm.Policy.ExtrinsicReward.mean": {
+            "value": 0.48600394654398166,
+            "min": 0.19933532153566677,
+            "max": 0.48600394654398166,
+            "count": 3
+        },
+        "Worm.Policy.ExtrinsicReward.sum": {
+            "value": 14.580118396319449,
+            "min": 5.9800596460700035,
+            "max": 14.580118396319449,
+            "count": 3
+        },
+        "Worm.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 3
+        },
+        "Worm.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 3
+        },
+        "Worm.Losses.PolicyLoss.mean": {
+            "value": 0.021550595627299378,
+            "min": 0.018366376078726415,
+            "max": 0.021550595627299378,
+            "count": 2
+        },
+        "Worm.Losses.PolicyLoss.sum": {
+            "value": 0.021550595627299378,
+            "min": 0.018366376078726415,
+            "max": 0.021550595627299378,
+            "count": 2
+        },
+        "Worm.Losses.ValueLoss.mean": {
+            "value": 0.0020331353242952553,
+            "min": 0.0020331353242952553,
+            "max": 0.0084186820923129,
+            "count": 2
+        },
+        "Worm.Losses.ValueLoss.sum": {
+            "value": 0.0020331353242952553,
+            "min": 0.0020331353242952553,
+            "max": 0.0084186820923129,
+            "count": 2
+        },
+        "Worm.Policy.LearningRate.mean": {
+            "value": 0.00012000006,
+            "min": 0.00012000006,
+            "max": 0.00021000003000000005,
+            "count": 2
+        },
+        "Worm.Policy.LearningRate.sum": {
+            "value": 0.00012000006,
+            "min": 0.00012000006,
+            "max": 0.00021000003000000005,
+            "count": 2
+        },
+        "Worm.Policy.Epsilon.mean": {
+            "value": 0.13999999999999999,
+            "min": 0.13999999999999999,
+            "max": 0.16999999999999998,
+            "count": 2
+        },
+        "Worm.Policy.Epsilon.sum": {
+            "value": 0.13999999999999999,
+            "min": 0.13999999999999999,
+            "max": 0.16999999999999998,
+            "count": 2
+        },
+        "Worm.Policy.Beta.mean": {
+            "value": 0.002006,
+            "min": 0.002006,
+            "max": 0.003503,
+            "count": 2
+        },
+        "Worm.Policy.Beta.sum": {
+            "value": 0.002006,
+            "min": 0.002006,
+            "max": 0.003503,
+            "count": 2
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1656848218",
+        "python_version": "3.7.13 (default, Mar 29 2022, 02:18:16) \n[GCC 7.5.0]",
+        "command_line_arguments": "/home/osanseviero/miniconda3/envs/mlagents/bin/mlagents-learn config/ppo/Worm.yaml --env=trained-envs-executables/linux/Worm/Worm --run-id=training --no-graphics",
+        "mlagents_version": "0.29.0.dev0",
+        "mlagents_envs_version": "0.29.0.dev0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "1.8.0",
+        "numpy_version": "1.21.5",
+        "end_time_seconds": "1656848281"
+    },
+    "total": 63.20981318899999,
+    "count": 1,
+    "self": 0.21756502699997782,
+    "children": {
+        "run_training.setup": {
+            "total": 0.011864887000001545,
+            "count": 1,
+            "self": 0.011864887000001545
+        },
+        "TrainerController.start_learning": {
+            "total": 62.98038327500001,
+            "count": 1,
+            "self": 0.11905975900333488,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 2.0940638189999845,
+                    "count": 1,
+                    "self": 2.0940638189999845
+                },
+                "TrainerController.advance": {
+                    "total": 60.70532365099666,
+                    "count": 11000,
+                    "self": 0.12366392499302492,
+                    "children": {
+                        "env_step": {
+                            "total": 47.097982624001475,
+                            "count": 11000,
+                            "self": 37.81521809599985,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 9.211672923999458,
+                                    "count": 11000,
+                                    "self": 0.4888320110017048,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 8.722840912997754,
+                                            "count": 11000,
+                                            "self": 2.3672766420068,
+                                            "children": {
+                                                "TorchPolicy.sample_actions": {
+                                                    "total": 6.3555642709909534,
+                                                    "count": 11000,
+                                                    "self": 6.3555642709909534
+                                                }
+                                            }
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 0.07109160400216297,
+                                    "count": 11000,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 62.43959642200389,
+                                            "count": 11000,
+                                            "is_parallel": true,
+                                            "self": 31.027620766000723,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.00048800000001847366,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0001534439999204551,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.00033455600009801856,
+                                                                    "count": 2,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00033455600009801856
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.012903008999956,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.00010182199991959351,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.00019712400001026253,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00019712400001026253
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.012344298000016352,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.012344298000016352
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.00025976500000979286,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00010080200001993944,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.00015896299998985342,
+                                                                            "count": 2,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.00015896299998985342
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 31.411975656003165,
+                                                    "count": 10999,
+                                                    "is_parallel": true,
+                                                    "self": 0.8720366130122557,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 1.2969238320011982,
+                                                            "count": 10999,
+                                                            "is_parallel": true,
+                                                            "self": 1.2969238320011982
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 27.124492783997198,
+                                                            "count": 10999,
+                                                            "is_parallel": true,
+                                                            "self": 27.124492783997198
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 2.118522426992513,
+                                                            "count": 10999,
+                                                            "is_parallel": true,
+                                                            "self": 0.8417608799842355,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 1.2767615470082774,
+                                                                    "count": 21998,
+                                                                    "is_parallel": true,
+                                                                    "self": 1.2767615470082774
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 13.483677102002162,
+                            "count": 11000,
+                            "self": 0.14227185999698122,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 4.2275462980052225,
+                                    "count": 11000,
+                                    "self": 4.2275462980052225
+                                },
+                                "_update_policy": {
+                                    "total": 9.113858943999958,
+                                    "count": 3,
+                                    "self": 7.840472577000469,
+                                    "children": {
+                                        "TorchPPOOptimizer.update": {
+                                            "total": 1.273386366999489,
+                                            "count": 126,
+                                            "self": 1.273386366999489
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 7.400000185953104e-07,
+                    "count": 1,
+                    "self": 7.400000185953104e-07
+                },
+                "TrainerController._save_models": {
+                    "total": 0.061935306000009405,
+                    "count": 1,
+                    "self": 0.0012024039999687375,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.06073290200004067,
+                            "count": 1,
+                            "self": 0.06073290200004067
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,29 @@
+{
+    "Worm": {
+        "checkpoints": [
+            {
+                "steps": 110000,
+                "file_path": "results/training/Worm/Worm-110000.onnx",
+                "reward": 0.27359586344100534,
+                "creation_time": 1656848281.221885,
+                "auxillary_file_paths": [
+                    "results/training/Worm/Worm-110000.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 110000,
+            "file_path": "results/training/Worm.onnx",
+            "reward": 0.27359586344100534,
+            "creation_time": 1656848281.221885,
+            "auxillary_file_paths": [
+                "results/training/Worm/Worm-110000.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "0.29.0.dev0",
+        "torch_version": "1.8.0"
+    }
+}