First training of PyramidsRND

Pyramids.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b6aa401c7ba518a38e00033e1cc8b640d759cba41c9e2d640b66fe2e3e78d85
+size 2471804

Pyramids/Pyramids-1500071.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4199b4e0229d36adb3755d7c9e0e4d6a07d16f2e1f3e3ba8c41351b886aaa4db
+size 2471804

Pyramids/Pyramids-1500071.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b96f210f673d2ab0bab65f58a4311da7f932f2ea74024d7aaa8d16b794e51d9
+size 14965499

Pyramids/Pyramids-1999909.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d3f260689422c690e74a9e0942bec25778b72f91b828c041b339c7aa0eb2d8e
+size 2471804

Pyramids/Pyramids-1999909.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91d0a00edae05cc61eca17dbd7b831983affcec704458d6087ab632ae8b4bf5c
+size 14965499

Pyramids/Pyramids-2499912.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71d2199434d58d1389cf81b7714bdac02ad4f767e60304fb9e2b466d86ec2547
+size 2471804

Pyramids/Pyramids-2499912.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b9fc186bbb055f0c4aa7dc9a0016c8ced42c69256603da44fe4840ffd4cc85d
+size 14965499

Pyramids/Pyramids-2999999.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b6aa401c7ba518a38e00033e1cc8b640d759cba41c9e2d640b66fe2e3e78d85
+size 2471804

Pyramids/Pyramids-2999999.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0eaf8935afe39ef6e3f91557caafdbee426171ccf8cd109c2a47c058a68ec2c2
+size 14965499

Pyramids/Pyramids-3000127.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b6aa401c7ba518a38e00033e1cc8b640d759cba41c9e2d640b66fe2e3e78d85
+size 2471804

Pyramids/Pyramids-3000127.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77a86ab4b5dd589ef99f79ddb783f1799640f4471b84d29ff5d53bec5b849343
+size 14965499

Pyramids/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ee6757196b89c1a82da78805f14e56dada7f4b7ad99426cb6a2ae4754059be2
+size 14964917

Pyramids/events.out.tfevents.1746507740.txshi-PC2024.64520.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:073c9a0e76907896040228bd8edf42f17dbe44181097569c3d3184e376995c8b
+size 462318

Pyramids/events.out.tfevents.1746508707.txshi-PC2024.65039.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d2bdb42edb0614e84f11c3ee93120227f76af8c3873b5e22c374f0a6ece65e0
+size 407501

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: tingxun/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": 1024, "buffer_size": 10240, "learning_rate": 0.0003, "beta": 0.01, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 5, "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": 3, "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": 3000000, "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": true, "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: 1024
+      buffer_size: 10240
+      learning_rate: 0.0003
+      beta: 0.01
+      epsilon: 0.2
+      lambd: 0.95
+      num_epoch: 5
+      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: 3
+      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: 3000000
+    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: true
+  force: false
+  train_model: false
+  inference: false
+  results_dir: results
+torch_settings:
+  device: null
+debug: false

run_logs/Player-0.log

@@ -0,0 +1,424 @@
+Mono path[0] = '/home/txshi/Projects/hf-rl/ch5/training-envs-executables/linux/Pyramids/Pyramids_Data/Managed'
+Mono config path = '/home/txshi/Projects/hf-rl/ch5/training-envs-executables/linux/Pyramids/Pyramids_Data/MonoBleedingEdge/etc'
+Found 1 interfaces on host : 0) 192.168.0.105
+Multi-casting "[IP] 192.168.0.105 [Port] 55284 [Flags] 2 [Guid] 2904565480 [EditorId] 764847374 [Version] 1048832 [Id] LinuxPlayer(13,192.168.0.105) [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/txshi/Projects/hf-rl/ch5/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  0.039 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: 0.385277 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 14 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]: 1082 frames, [32.0 KB-64.0 KB]: 17630 frames, [64.0 KB-128.0 KB]: 9433 frames, [2.0 MB-4.0 MB]: 1 frames
+      Initial Block Size 4.0 MB
+      Current Block Size 4.0 MB
+      Peak Allocated Bytes 2.0 MB
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 18]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 8]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 4]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 11]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 3]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_BatchDeleteObjects]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 21]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 25]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 13]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 2]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 22]
+      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 15]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 12]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Loading.PreloadManager]
+      Initial Block Size 256.0 KB
+      Current Block Size 320.0 KB
+      Peak Allocated Bytes 251.5 KB
+      Overflow Count 4
+    [ALLOC_TEMP_AUDIO_FMOD PulseAudio Mixer]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 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_Profiler.Dispatcher]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 17]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 5]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 13]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 2]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 11]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 6]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 0]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 5]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0.8 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_EnlightenWorker] x 14
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 9]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Loading.AsyncRead]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 128 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 10]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 16]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 6]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 1]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 20]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 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 26]
+      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 15]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 7]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 8]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 23]
+      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 24]
+      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 27
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 0]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 4]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 14]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 7]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 19]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+[ALLOC_MEMORYPROFILER]
+  Peak usage frame count: [0.5 MB-1.0 MB]: 39 frames, [1.0 MB-2.0 MB]: 28107 frames
+  Requested Block Size 1.0 MB
+  Peak Block count 2
+  Peak Allocated memory 1.1 MB
+  Peak Large allocation bytes 0 B
+[ALLOC_DEFAULT] Dual Thread Allocator
+  Peak main deferred allocation count 1802
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 1.4 MB
+    [ALLOC_DEFAULT_MAIN]
+      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 28145 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 2
+      Peak Allocated memory 25.3 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 28146 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 29.3 MB
+      Peak Large allocation bytes 16.0 MB
+[ALLOC_TEMP_JOB_1_FRAME]
+  Initial Block Size 2.0 MB
+  Used Block Count 1
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_TEMP_JOB_2_FRAMES]
+  Initial Block Size 2.0 MB
+  Used Block Count 1
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_TEMP_JOB_4_FRAMES (JobTemp)]
+  Initial Block Size 2.0 MB
+  Used Block Count 2
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_TEMP_JOB_ASYNC (Background)]
+  Initial Block Size 1.0 MB
+  Used Block Count 3
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_GFX] Dual Thread Allocator
+  Peak main deferred allocation count 0
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 1.4 MB
+    [ALLOC_GFX_MAIN]
+      Peak usage frame count: [32.0 KB-64.0 KB]: 28145 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]: 28146 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 1.4 MB
+    [ALLOC_CACHEOBJECTS_MAIN]
+      Peak usage frame count: [0.5 MB-1.0 MB]: 53 frames, [1.0 MB-2.0 MB]: 28093 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]: 28145 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 1.4 MB
+    [ALLOC_TYPETREE_MAIN]
+      Peak usage frame count: [0-1.0 KB]: 28146 frames
+      Requested Block Size 2.0 MB
+      Peak Block count 1
+      Peak Allocated memory 1.0 KB
+      Peak Large allocation bytes 0 B
+    [ALLOC_TYPETREE_THREAD]
+      Peak usage frame count: [1.0 KB-2.0 KB]: 28146 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]: 28146 frames
+  Requested Block Size 16.0 MB
+  Peak Block count 1
+  Peak Allocated memory 50.6 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":1746509653224,"processId":65080,"allocatedMemory":2002247,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"NewDelete":12801},{"Thread":35188},{"Manager":31311},{"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":3517},{"DynamicArray":30868},{"HashMap":7680},{"Utility":11968},{"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 +1,398 @@
+{
+    "name": "root",
+    "gauges": {
+        "Pyramids.Policy.Entropy.mean": {
+            "value": 0.14759185910224915,
+            "min": 0.14025941491127014,
+            "max": 0.33215630054473877,
+            "count": 50
+        },
+        "Pyramids.Policy.Entropy.sum": {
+            "value": 4484.43115234375,
+            "min": 4207.7822265625,
+            "max": 10171.9541015625,
+            "count": 50
+        },
+        "Pyramids.Step.mean": {
+            "value": 2999999.0,
+            "min": 1529929.0,
+            "max": 2999999.0,
+            "count": 50
+        },
+        "Pyramids.Step.sum": {
+            "value": 2999999.0,
+            "min": 1529929.0,
+            "max": 2999999.0,
+            "count": 50
+        },
+        "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 0.7630169987678528,
+            "min": 0.5922383666038513,
+            "max": 0.7677894830703735,
+            "count": 50
+        },
+        "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 225.0900115966797,
+            "min": 165.23451232910156,
+            "max": 228.03347778320312,
+            "count": 50
+        },
+        "Pyramids.Policy.RndValueEstimate.mean": {
+            "value": 0.015491118654608727,
+            "min": 0.008117031306028366,
+            "max": 0.0288896132260561,
+            "count": 50
+        },
+        "Pyramids.Policy.RndValueEstimate.sum": {
+            "value": 4.56988000869751,
+            "min": 2.370173215866089,
+            "max": 8.233539581298828,
+            "count": 50
+        },
+        "Pyramids.Environment.EpisodeLength.mean": {
+            "value": 242.82203389830508,
+            "min": 222.50746268656715,
+            "max": 325.75,
+            "count": 50
+        },
+        "Pyramids.Environment.EpisodeLength.sum": {
+            "value": 28653.0,
+            "min": 26537.0,
+            "max": 31592.0,
+            "count": 50
+        },
+        "Pyramids.Environment.CumulativeReward.mean": {
+            "value": 1.7571779478151919,
+            "min": 1.586324718850915,
+            "max": 1.777492522637346,
+            "count": 50
+        },
+        "Pyramids.Environment.CumulativeReward.sum": {
+            "value": 207.34699784219265,
+            "min": 145.8119983226061,
+            "max": 238.18399803340435,
+            "count": 50
+        },
+        "Pyramids.Policy.ExtrinsicReward.mean": {
+            "value": 1.7571779478151919,
+            "min": 1.586324718850915,
+            "max": 1.777492522637346,
+            "count": 50
+        },
+        "Pyramids.Policy.ExtrinsicReward.sum": {
+            "value": 207.34699784219265,
+            "min": 145.8119983226061,
+            "max": 238.18399803340435,
+            "count": 50
+        },
+        "Pyramids.Policy.RndReward.mean": {
+            "value": 0.028435185211646504,
+            "min": 0.026604726313148128,
+            "max": 0.06942069130084362,
+            "count": 50
+        },
+        "Pyramids.Policy.RndReward.sum": {
+            "value": 3.3553518549742876,
+            "min": 3.3553518549742876,
+            "max": 6.733807056181831,
+            "count": 50
+        },
+        "Pyramids.Losses.PolicyLoss.mean": {
+            "value": 0.019560502592163784,
+            "min": 0.019560502592163784,
+            "max": 0.0276279745134525,
+            "count": 50
+        },
+        "Pyramids.Losses.PolicyLoss.sum": {
+            "value": 0.05868150777649135,
+            "min": 0.04262920394539833,
+            "max": 0.08060212047537789,
+            "count": 50
+        },
+        "Pyramids.Losses.ValueLoss.mean": {
+            "value": 0.01643072345604499,
+            "min": 0.014319621746738752,
+            "max": 0.017897415434320767,
+            "count": 50
+        },
+        "Pyramids.Losses.ValueLoss.sum": {
+            "value": 0.04929217036813498,
+            "min": 0.030501069389283656,
+            "max": 0.0536922463029623,
+            "count": 50
+        },
+        "Pyramids.Policy.LearningRate.mean": {
+            "value": 1.6612994462666625e-06,
+            "min": 1.6612994462666625e-06,
+            "max": 0.00014845130051624998,
+            "count": 50
+        },
+        "Pyramids.Policy.LearningRate.sum": {
+            "value": 4.983898338799987e-06,
+            "min": 4.983898338799987e-06,
+            "max": 0.0004376169541277333,
+            "count": 50
+        },
+        "Pyramids.Policy.Epsilon.mean": {
+            "value": 0.10055373333333334,
+            "min": 0.10055373333333334,
+            "max": 0.14948375000000003,
+            "count": 50
+        },
+        "Pyramids.Policy.Epsilon.sum": {
+            "value": 0.3016612,
+            "min": 0.2090047333333333,
+            "max": 0.4458722666666667,
+            "count": 50
+        },
+        "Pyramids.Policy.Beta.mean": {
+            "value": 6.531795999999988e-05,
+            "min": 6.531795999999988e-05,
+            "max": 0.004953426625,
+            "count": 50
+        },
+        "Pyramids.Policy.Beta.sum": {
+            "value": 0.0001959538799999996,
+            "min": 0.0001959538799999996,
+            "max": 0.014602639439999999,
+            "count": 50
+        },
+        "Pyramids.Losses.RNDLoss.mean": {
+            "value": 0.011611025780439377,
+            "min": 0.01159887108951807,
+            "max": 0.02117346040904522,
+            "count": 50
+        },
+        "Pyramids.Losses.RNDLoss.sum": {
+            "value": 0.03483307734131813,
+            "min": 0.02372013032436371,
+            "max": 0.06352037936449051,
+            "count": 50
+        },
+        "Pyramids.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 50
+        },
+        "Pyramids.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 50
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1746508706",
+        "python_version": "3.10.12 | packaged by conda-forge | (main, Jun 23 2023, 22:40:32) [GCC 12.3.0]",
+        "command_line_arguments": "/home/txshi/miniconda3/envs/hf-rl-ch5/bin/mlagents-learn ./ml-agents/config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics --resume",
+        "mlagents_version": "1.2.0.dev0",
+        "mlagents_envs_version": "1.2.0.dev0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "2.7.0+cu126",
+        "numpy_version": "1.23.5",
+        "end_time_seconds": "1746509653"
+    },
+    "total": 946.4430587530005,
+    "count": 1,
+    "self": 0.1665285330018378,
+    "children": {
+        "run_training.setup": {
+            "total": 0.015372962998299045,
+            "count": 1,
+            "self": 0.015372962998299045
+        },
+        "TrainerController.start_learning": {
+            "total": 946.2611572570004,
+            "count": 1,
+            "self": 0.7353149860136909,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 1.3560721989997546,
+                    "count": 1,
+                    "self": 1.3560721989997546
+                },
+                "TrainerController.advance": {
+                    "total": 944.1236960439855,
+                    "count": 98280,
+                    "self": 0.6919071292486478,
+                    "children": {
+                        "env_step": {
+                            "total": 628.7653076611532,
+                            "count": 98280,
+                            "self": 501.679360544118,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 126.59082360999855,
+                                    "count": 98280,
+                                    "self": 2.55443194534746,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 124.03639166465109,
+                                            "count": 93817,
+                                            "self": 124.03639166465109
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 0.4951235070366238,
+                                    "count": 98280,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 945.3021435918654,
+                                            "count": 98280,
+                                            "is_parallel": true,
+                                            "self": 489.8738490467058,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.0006208550003066193,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0001753210017341189,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.0004455339985725004,
+                                                                    "count": 8,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0004455339985725004
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.012712784000541433,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.00012432600124157034,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.00013519099957193248,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00013519099957193248
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.012097856999389478,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.012097856999389478
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.00035541000033845194,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 8.841799717629328e-05,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.00026699200316215865,
+                                                                            "count": 8,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.00026699200316215865
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 455.4282945451596,
+                                                    "count": 98279,
+                                                    "is_parallel": true,
+                                                    "self": 10.6707104262332,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 6.716008393870652,
+                                                            "count": 98279,
+                                                            "is_parallel": true,
+                                                            "self": 6.716008393870652
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 409.69189717502195,
+                                                            "count": 98279,
+                                                            "is_parallel": true,
+                                                            "self": 409.69189717502195
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 28.349678550033786,
+                                                            "count": 98279,
+                                                            "is_parallel": true,
+                                                            "self": 6.308964319758161,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 22.040714230275626,
+                                                                    "count": 786232,
+                                                                    "is_parallel": true,
+                                                                    "self": 22.040714230275626
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 314.6664812535837,
+                            "count": 98280,
+                            "self": 1.5202239386580914,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 79.52096247990994,
+                                    "count": 98280,
+                                    "self": 79.37046390090836,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 0.15049857900157804,
+                                            "count": 3,
+                                            "self": 0.15049857900157804
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 233.62529483501567,
+                                    "count": 145,
+                                    "self": 185.6884477689655,
+                                    "children": {
+                                        "TorchPPOOptimizer.update": {
+                                            "total": 47.93684706605018,
+                                            "count": 7250,
+                                            "self": 47.93684706605018
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 4.420016921358183e-07,
+                    "count": 1,
+                    "self": 4.420016921358183e-07
+                },
+                "TrainerController._save_models": {
+                    "total": 0.04607358599969302,
+                    "count": 1,
+                    "self": 0.0011363630001142155,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.04493722299957881,
+                            "count": 1,
+                            "self": 0.04493722299957881
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,65 @@
+{
+    "Pyramids": {
+        "checkpoints": [
+            {
+                "steps": 1500071,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1500071.onnx",
+                "reward": 1.7218749783933163,
+                "creation_time": 1746508630.615688,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-1500071.pt"
+                ]
+            },
+            {
+                "steps": 1999909,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1999909.onnx",
+                "reward": 1.7648333211739857,
+                "creation_time": 1746509017.756823,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-1999909.pt"
+                ]
+            },
+            {
+                "steps": 2499912,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-2499912.onnx",
+                "reward": 1.807999986410141,
+                "creation_time": 1746509334.3545969,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-2499912.pt"
+                ]
+            },
+            {
+                "steps": 2999999,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-2999999.onnx",
+                "reward": 1.7807499803602695,
+                "creation_time": 1746509653.039553,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-2999999.pt"
+                ]
+            },
+            {
+                "steps": 3000127,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-3000127.onnx",
+                "reward": 1.7807499803602695,
+                "creation_time": 1746509653.0890658,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-3000127.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 3000127,
+            "file_path": "results/Pyramids Training/Pyramids.onnx",
+            "reward": 1.7807499803602695,
+            "creation_time": 1746509653.0890658,
+            "auxillary_file_paths": [
+                "results/Pyramids Training/Pyramids/Pyramids-3000127.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "1.2.0.dev0",
+        "torch_version": "2.7.0+cu126"
+    }
+}