defaultish_parameters

Pyramids.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96891ce684d7da08f007b5ee257ef4dd244e780b48db73501c3774ae5939e1d6
+size 1420238

Pyramids/Pyramids-1048626.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96891ce684d7da08f007b5ee257ef4dd244e780b48db73501c3774ae5939e1d6
+size 1420238

Pyramids/Pyramids-1048626.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10ec6003a64257f07f934bfb59f971b13a4bc90fdd6d5ea611270cf10c436996
+size 10002044

Pyramids/Pyramids-499897.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6bc021d0912a49c295838c09fcb2e7f488b7d721159a09e007f7bcb51acdae3d
+size 1420238

Pyramids/Pyramids-499897.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8aacff6ba49241e2fa8df767bdd7a04296cea70913b2bb71157340bbec321f97
+size 10001965

Pyramids/Pyramids-999894.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d8fdf05dac937297aa067b71dbedb7d4f7ef5500a79ec4214e9f7d1b338011a
+size 1420238

Pyramids/Pyramids-999894.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbc74fc2518c6e9d264ddb1e817e08da6520989b7891a90ef6adbe0064c9b91b
+size 10001965

Pyramids/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fd7ae826fac5a1ab9f4ceb603c0f4b545dc3d4ab0433d57da45dc6660294669
+size 10001506

Pyramids/events.out.tfevents.1738510302.hrichter-5950x.21284.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:988d5155201839d64c7fe19639b5213182c772f6bbbf190cdeeb30e8e0de7d2d
+size 289587

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: knoffel/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}}, "curiosity": {"gamma": 0.99, "strength": 0.02, "network_settings": {"normalize": false, "hidden_units": 256, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0003, "encoding_size": null}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 1048576, "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": true, "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
+      curiosity:
+        gamma: 0.99
+        strength: 0.02
+        network_settings:
+          normalize: false
+          hidden_units: 256
+          num_layers: 2
+          vis_encode_type: simple
+          memory: null
+          goal_conditioning_type: hyper
+          deterministic: false
+        learning_rate: 0.0003
+        encoding_size: null
+    init_path: null
+    keep_checkpoints: 5
+    even_checkpoints: false
+    max_steps: 1048576
+    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: true
+  train_model: false
+  inference: false
+  results_dir: results
+torch_settings:
+  device: null
+debug: false

run_logs/Player-0.log

@@ -0,0 +1,447 @@
+Mono path[0] = '/home/hrichter/projects/hf_rl_course/training-envs-executables/linux/Pyramids/Pyramids_Data/Managed'
+Mono config path = '/home/hrichter/projects/hf_rl_course/training-envs-executables/linux/Pyramids/Pyramids_Data/MonoBleedingEdge/etc'
+Found 3 interfaces on host : 0) 192.168.101.72 1) 10.113.249.15 2) 172.17.0.1
+Multi-casting "[IP] 192.168.101.72 [Port] 55186 [Flags] 2 [Guid] 652531144 [EditorId] 764847374 [Version] 1048832 [Id] LinuxPlayer(13,192.168.101.72) [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/hrichter/.config/unity3d/Unity Technologies
+PlayerPrefs - Creating folder: /home/hrichter/.config/unity3d/Unity Technologies/UnityEnvironment
+Unable to load player prefs
+Initialize engine version: 2021.3.5f1 (40eb3a945986)
+[Subsystems] Discovering subsystems at path /home/hrichter/projects/hf_rl_course/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  0.058 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: 0.500290 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 16 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]: 15850 frames, [32.0 KB-64.0 KB]: 2584 frames, [64.0 KB-128.0 KB]: 1241 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 0.8 KB
+      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_Job.Worker 27]
+      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 251.6 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_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 17]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 3]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 5]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 13]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 2]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Profiler.Dispatcher]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 3.8 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 11]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 6]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 0]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 5]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 9]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_EnlightenWorker] x 16
+      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_Job.Worker 30]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 29]
+      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 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 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 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 31
+      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 28]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 7]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 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]: 299 frames, [1.0 MB-2.0 MB]: 19377 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 12810
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 1.7 MB
+    [ALLOC_DEFAULT_MAIN]
+      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 19675 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 3
+      Peak Allocated memory 31.3 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 19676 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 30.8 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 1.7 MB
+    [ALLOC_GFX_MAIN]
+      Peak usage frame count: [32.0 KB-64.0 KB]: 19675 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]: 19676 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 1.7 MB
+    [ALLOC_CACHEOBJECTS_MAIN]
+      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 19377 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]: 19675 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 1.7 MB
+    [ALLOC_TYPETREE_MAIN]
+      Peak usage frame count: [0-1.0 KB]: 19676 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]: 19676 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]: 19676 frames
+  Requested Block Size 16.0 MB
+  Peak Block count 1
+  Peak Allocated memory 54.4 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":1738511213892,"processId":21381,"allocatedMemory":2006255,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"NewDelete":12801},{"Thread":35300},{"Manager":33551},{"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":3541},{"DynamicArray":30868},{"HashMap":7680},{"Utility":13600},{"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 +1,410 @@
+{
+    "name": "root",
+    "gauges": {
+        "Pyramids.Policy.Entropy.mean": {
+            "value": 0.4543474614620209,
+            "min": 0.4543474614620209,
+            "max": 1.5112195014953613,
+            "count": 34
+        },
+        "Pyramids.Policy.Entropy.sum": {
+            "value": 13608.615234375,
+            "min": 13608.615234375,
+            "max": 45844.35546875,
+            "count": 34
+        },
+        "Pyramids.Step.mean": {
+            "value": 1019962.0,
+            "min": 29952.0,
+            "max": 1019962.0,
+            "count": 34
+        },
+        "Pyramids.Step.sum": {
+            "value": 1019962.0,
+            "min": 29952.0,
+            "max": 1019962.0,
+            "count": 34
+        },
+        "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
+            "value": -0.06637323647737503,
+            "min": -0.0984974354505539,
+            "max": 0.05833796411752701,
+            "count": 34
+        },
+        "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
+            "value": -15.995950698852539,
+            "min": -23.44239044189453,
+            "max": 13.82609748840332,
+            "count": 34
+        },
+        "Pyramids.Policy.CuriosityValueEstimate.mean": {
+            "value": 0.172653928399086,
+            "min": 0.172653928399086,
+            "max": 0.6127722263336182,
+            "count": 34
+        },
+        "Pyramids.Policy.CuriosityValueEstimate.sum": {
+            "value": 41.609596252441406,
+            "min": 41.609596252441406,
+            "max": 147.06533813476562,
+            "count": 34
+        },
+        "Pyramids.Losses.PolicyLoss.mean": {
+            "value": 0.06753937733212566,
+            "min": 0.06403414026754138,
+            "max": 0.07400685542682015,
+            "count": 34
+        },
+        "Pyramids.Losses.PolicyLoss.sum": {
+            "value": 0.9455512826497593,
+            "min": 0.5008653629779944,
+            "max": 1.0311151000042789,
+            "count": 34
+        },
+        "Pyramids.Losses.ValueLoss.mean": {
+            "value": 0.0010010373539647926,
+            "min": 0.00022825133976742587,
+            "max": 0.004660744971986814,
+            "count": 34
+        },
+        "Pyramids.Losses.ValueLoss.sum": {
+            "value": 0.014014522955507097,
+            "min": 0.0025107647374416845,
+            "max": 0.04636992843615743,
+            "count": 34
+        },
+        "Pyramids.Policy.LearningRate.mean": {
+            "value": 1.2229129802526743e-05,
+            "min": 1.2229129802526743e-05,
+            "max": 0.0002953752805594308,
+            "count": 34
+        },
+        "Pyramids.Policy.LearningRate.sum": {
+            "value": 0.00017120781723537441,
+            "min": 0.00017120781723537441,
+            "max": 0.0029310438478633875,
+            "count": 34
+        },
+        "Pyramids.Policy.Epsilon.mean": {
+            "value": 0.10407634462629045,
+            "min": 0.10407634462629045,
+            "max": 0.19845842633928573,
+            "count": 34
+        },
+        "Pyramids.Policy.Epsilon.sum": {
+            "value": 1.4570688247680663,
+            "min": 1.3304809570312501,
+            "max": 2.2465369224548337,
+            "count": 34
+        },
+        "Pyramids.Policy.Beta.mean": {
+            "value": 0.0004172268281664167,
+            "min": 0.0004172268281664167,
+            "max": 0.009845996791294642,
+            "count": 34
+        },
+        "Pyramids.Policy.Beta.sum": {
+            "value": 0.005841175594329834,
+            "min": 0.005841175594329834,
+            "max": 0.09772375270843506,
+            "count": 34
+        },
+        "Pyramids.Losses.CuriosityForwardLoss.mean": {
+            "value": 0.07906412933783538,
+            "min": 0.07906412933783538,
+            "max": 0.46284705355812367,
+            "count": 34
+        },
+        "Pyramids.Losses.CuriosityForwardLoss.sum": {
+            "value": 1.1068978107296954,
+            "min": 1.1068978107296954,
+            "max": 3.2399293749068656,
+            "count": 34
+        },
+        "Pyramids.Losses.CuriosityInverseLoss.mean": {
+            "value": 0.07675328405852935,
+            "min": 0.07675328405852935,
+            "max": 0.7302169783074525,
+            "count": 34
+        },
+        "Pyramids.Losses.CuriosityInverseLoss.sum": {
+            "value": 1.074545976819411,
+            "min": 1.074545976819411,
+            "max": 5.111518848152167,
+            "count": 34
+        },
+        "Pyramids.Environment.EpisodeLength.mean": {
+            "value": 983.34375,
+            "min": 902.3333333333334,
+            "max": 999.0,
+            "count": 34
+        },
+        "Pyramids.Environment.EpisodeLength.sum": {
+            "value": 31467.0,
+            "min": 15984.0,
+            "max": 31977.0,
+            "count": 34
+        },
+        "Pyramids.Environment.CumulativeReward.mean": {
+            "value": -0.8589000543579459,
+            "min": -1.0000000521540642,
+            "max": -0.4543032689440635,
+            "count": 34
+        },
+        "Pyramids.Environment.CumulativeReward.sum": {
+            "value": -27.48480173945427,
+            "min": -32.000001668930054,
+            "max": -14.083401337265968,
+            "count": 34
+        },
+        "Pyramids.Policy.ExtrinsicReward.mean": {
+            "value": -0.8589000543579459,
+            "min": -1.0000000521540642,
+            "max": -0.4543032689440635,
+            "count": 34
+        },
+        "Pyramids.Policy.ExtrinsicReward.sum": {
+            "value": -27.48480173945427,
+            "min": -32.000001668930054,
+            "max": -14.083401337265968,
+            "count": 34
+        },
+        "Pyramids.Policy.CuriosityReward.mean": {
+            "value": 1.652078541344963,
+            "min": 1.652078541344963,
+            "max": 7.098222507163882,
+            "count": 34
+        },
+        "Pyramids.Policy.CuriosityReward.sum": {
+            "value": 52.86651332303882,
+            "min": 43.25800512731075,
+            "max": 227.14312022924423,
+            "count": 34
+        },
+        "Pyramids.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 34
+        },
+        "Pyramids.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 34
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1738510301",
+        "python_version": "3.10.16 (main, Dec  4 2024, 08:53:38) [GCC 13.2.0]",
+        "command_line_arguments": "/home/hrichter/projects/hf_rl_course/.venv/bin/mlagents-learn ml-agents/config/ppo/Pyramids.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics --force",
+        "mlagents_version": "1.2.0.dev0",
+        "mlagents_envs_version": "1.2.0.dev0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "2.5.1+cu124",
+        "numpy_version": "1.23.5",
+        "end_time_seconds": "1738511213"
+    },
+    "total": 912.3542327689997,
+    "count": 1,
+    "self": 0.21796088999963104,
+    "children": {
+        "run_training.setup": {
+            "total": 0.015217674000268744,
+            "count": 1,
+            "self": 0.015217674000268744
+        },
+        "TrainerController.start_learning": {
+            "total": 912.1210542049998,
+            "count": 1,
+            "self": 0.6126094490464311,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 1.3287241719999656,
+                    "count": 1,
+                    "self": 1.3287241719999656
+                },
+                "TrainerController.advance": {
+                    "total": 910.1381253989539,
+                    "count": 66017,
+                    "self": 0.5998701820549286,
+                    "children": {
+                        "env_step": {
+                            "total": 485.25273342594437,
+                            "count": 66017,
+                            "self": 444.6313050909266,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 40.23746882602245,
+                                    "count": 66017,
+                                    "self": 1.9413799550957265,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 38.296088870926724,
+                                            "count": 65585,
+                                            "self": 38.296088870926724
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 0.3839595089953036,
+                                    "count": 66017,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 911.1650806679077,
+                                            "count": 66017,
+                                            "is_parallel": true,
+                                            "self": 511.17713061890663,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.0009802099998523772,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.000247952999870904,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.0007322569999814732,
+                                                                    "count": 8,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0007322569999814732
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.020602015999884316,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.00018806199932441814,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.00019271200017101364,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00019271200017101364
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.019664047000333085,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.019664047000333085
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.000557195000055799,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00013419100014289143,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.0004230039999129076,
+                                                                            "count": 8,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.0004230039999129076
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 399.98795004900103,
+                                                    "count": 66016,
+                                                    "is_parallel": true,
+                                                    "self": 11.616755930049294,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 8.229266628003643,
+                                                            "count": 66016,
+                                                            "is_parallel": true,
+                                                            "self": 8.229266628003643
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 346.46593935402007,
+                                                            "count": 66016,
+                                                            "is_parallel": true,
+                                                            "self": 346.46593935402007
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 33.67598813692803,
+                                                            "count": 66016,
+                                                            "is_parallel": true,
+                                                            "self": 7.211483213929569,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 26.464504922998458,
+                                                                    "count": 528128,
+                                                                    "is_parallel": true,
+                                                                    "self": 26.464504922998458
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 424.2855217909546,
+                            "count": 66017,
+                            "self": 1.111752062913638,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 60.70824232404675,
+                                    "count": 66017,
+                                    "self": 60.62343418304681,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 0.0848081409999395,
+                                            "count": 2,
+                                            "self": 0.0848081409999395
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 362.4655274039942,
+                                    "count": 445,
+                                    "self": 237.48609379300842,
+                                    "children": {
+                                        "TorchPPOOptimizer.update": {
+                                            "total": 124.97943361098578,
+                                            "count": 23931,
+                                            "self": 124.97943361098578
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 5.699998837371822e-07,
+                    "count": 1,
+                    "self": 5.699998837371822e-07
+                },
+                "TrainerController._save_models": {
+                    "total": 0.0415946149996671,
+                    "count": 1,
+                    "self": 0.0010204019999946468,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.040574212999672454,
+                            "count": 1,
+                            "self": 0.040574212999672454
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,47 @@
+{
+    "Pyramids": {
+        "checkpoints": [
+            {
+                "steps": 499897,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-499897.onnx",
+                "reward": -1.0000000521540642,
+                "creation_time": 1738510731.9819715,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-499897.pt"
+                ]
+            },
+            {
+                "steps": 999894,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-999894.onnx",
+                "reward": null,
+                "creation_time": 1738511171.0059083,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-999894.pt"
+                ]
+            },
+            {
+                "steps": 1048626,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1048626.onnx",
+                "reward": 0.022899948060512543,
+                "creation_time": 1738511213.7234762,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-1048626.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 1048626,
+            "file_path": "results/Pyramids Training/Pyramids.onnx",
+            "reward": 0.022899948060512543,
+            "creation_time": 1738511213.7234762,
+            "auxillary_file_paths": [
+                "results/Pyramids Training/Pyramids/Pyramids-1048626.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "1.2.0.dev0",
+        "torch_version": "2.5.1+cu124"
+    }
+}