First submit

Pyramids.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f4542e8d17ebe37f669615091c6c06e6083dab5263bdfe22be8a7ff04199b82
+size 1420238

Pyramids/Pyramids-1000024.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f4542e8d17ebe37f669615091c6c06e6083dab5263bdfe22be8a7ff04199b82
+size 1420238

Pyramids/Pyramids-1000024.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1498be95bc8f049adbb7c4bd40fc8901c3316e8662ef6f23ebd7b8e812ead7f
+size 8656731

Pyramids/Pyramids-499898.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b5c7bb32bc34a95d59b167845c479777f7547233a823980777afdce360263e5
+size 1420238

Pyramids/Pyramids-499898.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8707b11cf585236c7f4c6a6441f75f9e44ef67a609fe951c89c2b5793c7bacd1
+size 8656650

Pyramids/Pyramids-999896.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f4542e8d17ebe37f669615091c6c06e6083dab5263bdfe22be8a7ff04199b82
+size 1420238

Pyramids/Pyramids-999896.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e81f51930792161b80233bc097c9623fbcea1a6118f0872729e45640827bcf72
+size 8656650

Pyramids/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b55f180eb18c6bbe1b06e94f2c0744fdc27d2299ada4cc2ded1728d40b8c2d75
+size 8656181

Pyramids/events.out.tfevents.1757547515.ladong-System-Product-Name.23317.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89c38973a1498ecfad0528a2e00b2120b2b2b04b732848d34afb51d449aa5b6e
+size 295941

README.md

@@ -0,0 +1,35 @@
+---
+library_name: ml-agents
+tags:
+- Pyramids
+- deep-reinforcement-learning
+- reinforcement-learning
+- ML-Agents-Pyramids
+---
+
+  # **ppo** Agent playing **Pyramids**
+  This is a trained model of a **ppo** agent playing **Pyramids**
+  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: serendipity0306/ppo-Pyramids
+  3. Step 2: Select your *.nn /*.onnx file
+  4. Click on Watch the agent play 👀
+  

config.json

@@ -0,0 +1 @@
+{"default_settings": null, "behaviors": {"Pyramids": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.01, "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": false, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}, "rnd": {"gamma": 0.99, "strength": 0.01, "network_settings": {"normalize": false, "hidden_units": 64, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0001, "encoding_size": null}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 1000000, "time_horizon": 128, "summary_freq": 30000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/Pyramids/Pyramids", "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": "Pyramids 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 +1,92 @@
+default_settings: null
+behaviors:
+  Pyramids:
+    trainer_type: ppo
+    hyperparameters:
+      batch_size: 128
+      buffer_size: 2048
+      learning_rate: 0.0003
+      beta: 0.01
+      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: false
+      hidden_units: 512
+      num_layers: 2
+      vis_encode_type: simple
+      memory: null
+      goal_conditioning_type: hyper
+      deterministic: false
+    reward_signals:
+      extrinsic:
+        gamma: 0.99
+        strength: 1.0
+        network_settings:
+          normalize: false
+          hidden_units: 128
+          num_layers: 2
+          vis_encode_type: simple
+          memory: null
+          goal_conditioning_type: hyper
+          deterministic: false
+      rnd:
+        gamma: 0.99
+        strength: 0.01
+        network_settings:
+          normalize: false
+          hidden_units: 64
+          num_layers: 3
+          vis_encode_type: simple
+          memory: null
+          goal_conditioning_type: hyper
+          deterministic: false
+        learning_rate: 0.0001
+        encoding_size: null
+    init_path: null
+    keep_checkpoints: 5
+    even_checkpoints: false
+    max_steps: 1000000
+    time_horizon: 128
+    summary_freq: 30000
+    threaded: false
+    self_play: null
+    behavioral_cloning: null
+env_settings:
+  env_path: ./training-envs-executables/linux/Pyramids/Pyramids
+  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: Pyramids 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 +1,383 @@
+Mono path[0] = '/home/ladong/Workspace/huggingface-rl/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/Managed'
+Mono config path = '/home/ladong/Workspace/huggingface-rl/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/MonoBleedingEdge/etc'
+Found 1 interfaces on host : 0) 192.168.1.190
+Multi-casting "[IP] 192.168.1.190 [Port] 55123 [Flags] 2 [Guid] 1847834993 [EditorId] 764847374 [Version] 1048832 [Id] LinuxPlayer(13,192.168.1.190) [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: /home/ladong/.config/unity3d/Unity Technologies
+PlayerPrefs - Creating folder: /home/ladong/.config/unity3d/Unity Technologies/UnityEnvironment
+Unable to load player prefs
+Initialize engine version: 2021.3.5f1 (40eb3a945986)
+[Subsystems] Discovering subsystems at path /home/ladong/Workspace/huggingface-rl/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_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  0.082 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: 'Autodesk Interactive' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
+ERROR: Shader Autodesk Interactive shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+WARNING: Shader Unsupported: 'Autodesk Interactive' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
+WARNING: Shader Unsupported: '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?
+UnloadTime: 0.586120 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 6 worker threads for Enlighten.
+PlayerConnection::CleanupMemory Statistics:
+[ALLOC_TEMP_TLS] TLS Allocator
+  StackAllocators : 
+    [ALLOC_TEMP_MAIN]
+      Peak usage frame count: [16.0 KB-32.0 KB]: 2607 frames, [32.0 KB-64.0 KB]: 12774 frames, [64.0 KB-128.0 KB]: 3383 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_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_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 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 0.8 KB
+      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_Loading.PreloadManager]
+      Initial Block Size 256.0 KB
+      Current Block Size 320.0 KB
+      Peak Allocated Bytes 251.6 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_Profiler.Dispatcher]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 1.9 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 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 11
+      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_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 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 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 6]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_EnlightenWorker] x 6
+      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_Background Job.Worker 9]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 7]
+      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 129 B
+      Overflow Count 0
+[ALLOC_MEMORYPROFILER]
+  Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 18466 frames
+  Requested Block Size 1.0 MB
+  Peak Block count 2
+  Peak Allocated memory 1.6 MB
+  Peak Large allocation bytes 0 B
+[ALLOC_DEFAULT] Dual Thread Allocator
+  Peak main deferred allocation count 19851
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 2.4 MB
+      Failed Allocations. Bucket layout:
+        16B: 6 Subsections = 2048 buckets. Failed count: 280440
+        32B: 37 Subsections = 9472 buckets. Failed count: 2406
+        48B: 56 Subsections = 11468 buckets. Failed count: 1909
+        64B: 44 Subsections = 7509 buckets. Failed count: 369
+        80B: 14 Subsections = 2048 buckets. Failed count: 328865
+        96B: 14 Subsections = 1792 buckets. Failed count: 371677
+        112B: 2 Subsections = 227 buckets. Failed count: 6370
+        128B: 83 Subsections = 8499 buckets. Failed count: 16692
+    [ALLOC_DEFAULT_MAIN]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 18755 frames, [32.0 MB-64.0 MB]: 10 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 3
+      Peak Allocated memory 35.2 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 18765 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 26.6 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 2.4 MB
+      Failed Allocations. Bucket layout:
+        16B: 6 Subsections = 2048 buckets. Failed count: 280440
+        32B: 37 Subsections = 9472 buckets. Failed count: 2406
+        48B: 56 Subsections = 11468 buckets. Failed count: 1909
+        64B: 44 Subsections = 7509 buckets. Failed count: 369
+        80B: 14 Subsections = 2048 buckets. Failed count: 328865
+        96B: 14 Subsections = 1792 buckets. Failed count: 371677
+        112B: 2 Subsections = 227 buckets. Failed count: 6370
+        128B: 83 Subsections = 8499 buckets. Failed count: 16692
+    [ALLOC_GFX_MAIN]
+      Peak usage frame count: [32.0 KB-64.0 KB]: 18764 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: [64.0 KB-128.0 KB]: 18765 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 67.7 KB
+      Peak Large allocation bytes 0 B
+[ALLOC_CACHEOBJECTS] Dual Thread Allocator
+  Peak main deferred allocation count 1
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 2.4 MB
+      Failed Allocations. Bucket layout:
+        16B: 6 Subsections = 2048 buckets. Failed count: 280440
+        32B: 37 Subsections = 9472 buckets. Failed count: 2406
+        48B: 56 Subsections = 11468 buckets. Failed count: 1909
+        64B: 44 Subsections = 7509 buckets. Failed count: 369
+        80B: 14 Subsections = 2048 buckets. Failed count: 328865
+        96B: 14 Subsections = 1792 buckets. Failed count: 371677
+        112B: 2 Subsections = 227 buckets. Failed count: 6370
+        128B: 83 Subsections = 8499 buckets. Failed count: 16692
+    [ALLOC_CACHEOBJECTS_MAIN]
+      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 18466 frames
+      Requested Block Size 4.0 MB
+      Peak Block count 1
+      Peak Allocated memory 1.4 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_CACHEOBJECTS_THREAD]
+      Peak usage frame count: [1.0 MB-2.0 MB]: 18764 frames, [4.0 MB-8.0 MB]: 1 frames
+      Requested Block Size 4.0 MB
+      Peak Block count 2
+      Peak Allocated memory 4.7 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 2.4 MB
+      Failed Allocations. Bucket layout:
+        16B: 6 Subsections = 2048 buckets. Failed count: 280440
+        32B: 37 Subsections = 9472 buckets. Failed count: 2406
+        48B: 56 Subsections = 11468 buckets. Failed count: 1909
+        64B: 44 Subsections = 7509 buckets. Failed count: 369
+        80B: 14 Subsections = 2048 buckets. Failed count: 328865
+        96B: 14 Subsections = 1792 buckets. Failed count: 371677
+        112B: 2 Subsections = 227 buckets. Failed count: 6370
+        128B: 83 Subsections = 8499 buckets. Failed count: 16692
+    [ALLOC_TYPETREE_MAIN]
+      Peak usage frame count: [0-1.0 KB]: 18765 frames
+      Requested Block Size 2.0 MB
+      Peak Block count 1
+      Peak Allocated memory 1.1 KB
+      Peak Large allocation bytes 0 B
+    [ALLOC_TYPETREE_THREAD]
+      Peak usage frame count: [1.0 KB-2.0 KB]: 18765 frames
+      Requested Block Size 2.0 MB
+      Peak Block count 1
+      Peak Allocated memory 1.9 KB
+      Peak Large allocation bytes 0 B
+[ALLOC_PROFILER]
+  Peak usage frame count: [32.0 KB-64.0 KB]: 18765 frames
+  Requested Block Size 16.0 MB
+  Peak Block count 1
+  Peak Allocated memory 34.7 KB
+  Peak Large allocation bytes 0 B
+    [ALLOC_PROFILER_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 396 B
+##utp:{"type":"MemoryLeaks","version":2,"phase":"Immediate","time":1757548661146,"processId":23371,"allocatedMemory":1980734,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"NewDelete":13057},{"Thread":34740},{"Manager":16207},{"VertexData":12},{"Geometry":280},{"Texture":16},{"Shader":69173},{"Material":24},{"GfxDevice":35248},{"Animation":304},{"Audio":3976},{"Physics":288},{"Serialization":216},{"Input":9202},{"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":3570},{"DynamicArray":30868},{"HashMap":7680},{"Utility":5440},{"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":616},{"Camera":25},{"Secure":1},{"SerializationCache":624},{"APIUpdating":5872},{"Subsystems":384},{"VirtualTexturing":57552},{"AssetReference":32}]}

run_logs/timers.json

@@ -0,0 +1,398 @@
+{
+    "name": "root",
+    "gauges": {
+        "Pyramids.Policy.Entropy.mean": {
+            "value": 0.31564950942993164,
+            "min": 0.3051823079586029,
+            "max": 1.4416756629943848,
+            "count": 33
+        },
+        "Pyramids.Policy.Entropy.sum": {
+            "value": 9343.2255859375,
+            "min": 9218.947265625,
+            "max": 43734.671875,
+            "count": 33
+        },
+        "Pyramids.Step.mean": {
+            "value": 989989.0,
+            "min": 29952.0,
+            "max": 989989.0,
+            "count": 33
+        },
+        "Pyramids.Step.sum": {
+            "value": 989989.0,
+            "min": 29952.0,
+            "max": 989989.0,
+            "count": 33
+        },
+        "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 0.6356185674667358,
+            "min": -0.09719794243574142,
+            "max": 0.6356185674667358,
+            "count": 33
+        },
+        "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 183.0581512451172,
+            "min": -23.32750701904297,
+            "max": 183.0581512451172,
+            "count": 33
+        },
+        "Pyramids.Policy.RndValueEstimate.mean": {
+            "value": 0.019015617668628693,
+            "min": 0.011137646622955799,
+            "max": 0.19304729998111725,
+            "count": 33
+        },
+        "Pyramids.Policy.RndValueEstimate.sum": {
+            "value": 5.476497650146484,
+            "min": 3.1185410022735596,
+            "max": 46.33135223388672,
+            "count": 33
+        },
+        "Pyramids.Losses.PolicyLoss.mean": {
+            "value": 0.07201716061118182,
+            "min": 0.06651599989491136,
+            "max": 0.07281037996429378,
+            "count": 33
+        },
+        "Pyramids.Losses.PolicyLoss.sum": {
+            "value": 1.0082402485565456,
+            "min": 0.49753041101095064,
+            "max": 1.0586281552872001,
+            "count": 33
+        },
+        "Pyramids.Losses.ValueLoss.mean": {
+            "value": 0.016889515849246438,
+            "min": 0.0002569722005030127,
+            "max": 0.017437762379995548,
+            "count": 33
+        },
+        "Pyramids.Losses.ValueLoss.sum": {
+            "value": 0.23645322188945014,
+            "min": 0.00282669420553314,
+            "max": 0.2615664356999332,
+            "count": 33
+        },
+        "Pyramids.Policy.LearningRate.mean": {
+            "value": 7.621533173807146e-06,
+            "min": 7.621533173807146e-06,
+            "max": 0.00029515063018788575,
+            "count": 33
+        },
+        "Pyramids.Policy.LearningRate.sum": {
+            "value": 0.00010670146443330004,
+            "min": 0.00010670146443330004,
+            "max": 0.0035079041306986993,
+            "count": 33
+        },
+        "Pyramids.Policy.Epsilon.mean": {
+            "value": 0.10254047857142858,
+            "min": 0.10254047857142858,
+            "max": 0.19838354285714285,
+            "count": 33
+        },
+        "Pyramids.Policy.Epsilon.sum": {
+            "value": 1.4355667,
+            "min": 1.3691136000000002,
+            "max": 2.5693013000000002,
+            "count": 33
+        },
+        "Pyramids.Policy.Beta.mean": {
+            "value": 0.00026379380928571447,
+            "min": 0.00026379380928571447,
+            "max": 0.00983851593142857,
+            "count": 33
+        },
+        "Pyramids.Policy.Beta.sum": {
+            "value": 0.003693113330000002,
+            "min": 0.003693113330000002,
+            "max": 0.11695319987,
+            "count": 33
+        },
+        "Pyramids.Losses.RNDLoss.mean": {
+            "value": 0.011276885867118835,
+            "min": 0.011276885867118835,
+            "max": 0.27956414222717285,
+            "count": 33
+        },
+        "Pyramids.Losses.RNDLoss.sum": {
+            "value": 0.1578764021396637,
+            "min": 0.1578764021396637,
+            "max": 1.95694899559021,
+            "count": 33
+        },
+        "Pyramids.Environment.EpisodeLength.mean": {
+            "value": 291.03,
+            "min": 291.03,
+            "max": 999.0,
+            "count": 33
+        },
+        "Pyramids.Environment.EpisodeLength.sum": {
+            "value": 29103.0,
+            "min": 15984.0,
+            "max": 32945.0,
+            "count": 33
+        },
+        "Pyramids.Environment.CumulativeReward.mean": {
+            "value": 1.6726222106754178,
+            "min": -1.0000000521540642,
+            "max": 1.6888265158144795,
+            "count": 33
+        },
+        "Pyramids.Environment.CumulativeReward.sum": {
+            "value": 165.58959885686636,
+            "min": -32.000001668930054,
+            "max": 174.69539833068848,
+            "count": 33
+        },
+        "Pyramids.Policy.ExtrinsicReward.mean": {
+            "value": 1.6726222106754178,
+            "min": -1.0000000521540642,
+            "max": 1.6888265158144795,
+            "count": 33
+        },
+        "Pyramids.Policy.ExtrinsicReward.sum": {
+            "value": 165.58959885686636,
+            "min": -32.000001668930054,
+            "max": 174.69539833068848,
+            "count": 33
+        },
+        "Pyramids.Policy.RndReward.mean": {
+            "value": 0.03288113874367984,
+            "min": 0.03288113874367984,
+            "max": 5.389898657798767,
+            "count": 33
+        },
+        "Pyramids.Policy.RndReward.sum": {
+            "value": 3.255232735624304,
+            "min": 3.255232735624304,
+            "max": 86.23837852478027,
+            "count": 33
+        },
+        "Pyramids.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 33
+        },
+        "Pyramids.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 33
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1757547514",
+        "python_version": "3.10.10 (main, Mar 21 2023, 18:45:11) [GCC 11.2.0]",
+        "command_line_arguments": "/home/ladong/Workspace/huggingface-rl/huggingface/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics",
+        "mlagents_version": "1.2.0.dev0",
+        "mlagents_envs_version": "1.2.0.dev0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "2.8.0+cu128",
+        "numpy_version": "1.23.5",
+        "end_time_seconds": "1757548661"
+    },
+    "total": 1146.3358237480006,
+    "count": 1,
+    "self": 0.3194760460010002,
+    "children": {
+        "run_training.setup": {
+            "total": 0.02376967199961655,
+            "count": 1,
+            "self": 0.02376967199961655
+        },
+        "TrainerController.start_learning": {
+            "total": 1145.99257803,
+            "count": 1,
+            "self": 0.9767570348940353,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 1.8665626120000525,
+                    "count": 1,
+                    "self": 1.8665626120000525
+                },
+                "TrainerController.advance": {
+                    "total": 1143.0914149681048,
+                    "count": 63961,
+                    "self": 1.0213735208162689,
+                    "children": {
+                        "env_step": {
+                            "total": 718.6054868112333,
+                            "count": 63961,
+                            "self": 612.8003210057941,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 105.1444154605615,
+                                    "count": 63961,
+                                    "self": 2.7217539872490306,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 102.42266147331247,
+                                            "count": 62547,
+                                            "self": 102.42266147331247
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 0.6607503448776697,
+                                    "count": 63961,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 1144.6578969987768,
+                                            "count": 63961,
+                                            "is_parallel": true,
+                                            "self": 598.9709585549026,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.0011753800008591497,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.00034511700505390763,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.0008302629958052421,
+                                                                    "count": 8,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0008302629958052421
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.02318030900096346,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.00021981999998388346,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.00019490500017127488,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00019490500017127488
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.022080583001297782,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.022080583001297782
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.0006850009995105211,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00018278799871040974,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.0005022130008001113,
+                                                                            "count": 8,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.0005022130008001113
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 545.6869384438742,
+                                                    "count": 63960,
+                                                    "is_parallel": true,
+                                                    "self": 15.305896251862578,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 10.50695718704992,
+                                                            "count": 63960,
+                                                            "is_parallel": true,
+                                                            "self": 10.50695718704992
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 475.508802784796,
+                                                            "count": 63960,
+                                                            "is_parallel": true,
+                                                            "self": 475.508802784796
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 44.36528222016568,
+                                                            "count": 63960,
+                                                            "is_parallel": true,
+                                                            "self": 9.725696526184038,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 34.639585693981644,
+                                                                    "count": 511680,
+                                                                    "is_parallel": true,
+                                                                    "self": 34.639585693981644
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 423.46455463605525,
+                            "count": 63961,
+                            "self": 1.6934744032205344,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 78.20843168784086,
+                                    "count": 63961,
+                                    "self": 78.07713529884131,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 0.13129638899954443,
+                                            "count": 2,
+                                            "self": 0.13129638899954443
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 343.56264854499386,
+                                    "count": 447,
+                                    "self": 187.90794703476058,
+                                    "children": {
+                                        "TorchPPOOptimizer.update": {
+                                            "total": 155.65470151023328,
+                                            "count": 22812,
+                                            "self": 155.65470151023328
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 7.210001058410853e-07,
+                    "count": 1,
+                    "self": 7.210001058410853e-07
+                },
+                "TrainerController._save_models": {
+                    "total": 0.057842694001010386,
+                    "count": 1,
+                    "self": 0.0008298360007756855,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.0570128580002347,
+                            "count": 1,
+                            "self": 0.0570128580002347
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,47 @@
+{
+    "Pyramids": {
+        "checkpoints": [
+            {
+                "steps": 499898,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-499898.onnx",
+                "reward": 1.355399939417839,
+                "creation_time": 1757548076.9557745,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-499898.pt"
+                ]
+            },
+            {
+                "steps": 999896,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-999896.onnx",
+                "reward": 1.6949999605615933,
+                "creation_time": 1757548660.8253355,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-999896.pt"
+                ]
+            },
+            {
+                "steps": 1000024,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1000024.onnx",
+                "reward": 1.6949999605615933,
+                "creation_time": 1757548660.890309,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-1000024.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 1000024,
+            "file_path": "results/Pyramids Training/Pyramids.onnx",
+            "reward": 1.6949999605615933,
+            "creation_time": 1757548660.890309,
+            "auxillary_file_paths": [
+                "results/Pyramids Training/Pyramids/Pyramids-1000024.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "1.2.0.dev0",
+        "torch_version": "2.8.0+cu128"
+    }
+}