First Push

Pyramids.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:632a922a212c73cce4361c01e53d7421b31e65197bbe88879893d2d472245d66
+size 1420238

Pyramids/Pyramids-1499969.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fdd0345a154bcdf3ad28a5dd9c267495e78179cc12e03a57c83356637f1594fe
+size 1420238

Pyramids/Pyramids-1499969.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a0a55a2bb40127a711b2438df4e1796e99a29c7fbcd5eda62892a023624a04e
+size 8656252

Pyramids/Pyramids-1999943.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:962bd9acdad93682ba32f1aacba8f23b46bfab0a7d408a37a3428237c0d1eb4b
+size 1420238

Pyramids/Pyramids-1999943.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68301bb6c9992058dfca8e2877837f353c71390a35b3692127b33325de61ae11
+size 8656252

Pyramids/Pyramids-2499990.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2e4282a2864f8e53101c0dd1e653d54a68ec77ed174789cba78225af6d5bdff
+size 1420238

Pyramids/Pyramids-2499990.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55cac89fd6bb3195097a0f57696e26affc1bfcafbc7675eca719e6cb7cf14e57
+size 8656252

Pyramids/Pyramids-2999995.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:632a922a212c73cce4361c01e53d7421b31e65197bbe88879893d2d472245d66
+size 1420238

Pyramids/Pyramids-2999995.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:807ffa11c707a8251726e25429c87e8635bc0ad1ed8843944c33b66a306e8e1d
+size 8656252

Pyramids/Pyramids-3000093.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:632a922a212c73cce4361c01e53d7421b31e65197bbe88879893d2d472245d66
+size 1420238

Pyramids/Pyramids-3000093.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6fd8a38315c4bc04df33adf522444f3a7d8bf72e37e00de747474c5a99eefe7
+size 8656252

Pyramids/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d758b635aead3b72f543e2d6ed72a8eb7ad3e804ecc49b690d8192a3df5e754
+size 8655778

Pyramids/events.out.tfevents.1712438015.joeny-dev.10431.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e2bcaa178d47e6ab5642fc278beab2029f53df777451594aa0779a1e4b7fd49
+size 915010

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: joen2010/ppo-PyramidsRND
+  3. Step 2: Select your *.nn /*.onnx file
+  4. Click on Watch the agent play 👀
+  

config.json

@@ -0,0 +1 @@
+{"default_settings": null, "behaviors": {"Pyramids": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.01, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}, "rnd": {"gamma": 0.99, "strength": 0.01, "network_settings": {"normalize": false, "hidden_units": 64, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0001, "encoding_size": null}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 3000000, "time_horizon": 128, "summary_freq": 30000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "trained-envs-executables/linux/Pyramids/Pyramids", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "Pyramids Training", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -0,0 +1,92 @@
+default_settings: null
+behaviors:
+  Pyramids:
+    trainer_type: ppo
+    hyperparameters:
+      batch_size: 128
+      buffer_size: 2048
+      learning_rate: 0.0003
+      beta: 0.01
+      epsilon: 0.2
+      lambd: 0.95
+      num_epoch: 3
+      shared_critic: false
+      learning_rate_schedule: linear
+      beta_schedule: linear
+      epsilon_schedule: linear
+    checkpoint_interval: 500000
+    network_settings:
+      normalize: false
+      hidden_units: 512
+      num_layers: 2
+      vis_encode_type: simple
+      memory: null
+      goal_conditioning_type: hyper
+      deterministic: false
+    reward_signals:
+      extrinsic:
+        gamma: 0.99
+        strength: 1.0
+        network_settings:
+          normalize: false
+          hidden_units: 128
+          num_layers: 2
+          vis_encode_type: simple
+          memory: null
+          goal_conditioning_type: hyper
+          deterministic: false
+      rnd:
+        gamma: 0.99
+        strength: 0.01
+        network_settings:
+          normalize: false
+          hidden_units: 64
+          num_layers: 3
+          vis_encode_type: simple
+          memory: null
+          goal_conditioning_type: hyper
+          deterministic: false
+        learning_rate: 0.0001
+        encoding_size: null
+    init_path: null
+    keep_checkpoints: 5
+    even_checkpoints: false
+    max_steps: 3000000
+    time_horizon: 128
+    summary_freq: 30000
+    threaded: false
+    self_play: null
+    behavioral_cloning: null
+env_settings:
+  env_path: trained-envs-executables/linux/Pyramids/Pyramids
+  env_args: null
+  base_port: 5005
+  num_envs: 1
+  num_areas: 1
+  timeout_wait: 60
+  seed: -1
+  max_lifetime_restarts: 10
+  restarts_rate_limit_n: 1
+  restarts_rate_limit_period_s: 60
+engine_settings:
+  width: 84
+  height: 84
+  quality_level: 5
+  time_scale: 20
+  target_frame_rate: -1
+  capture_frame_rate: 60
+  no_graphics: true
+  no_graphics_monitor: false
+environment_parameters: null
+checkpoint_settings:
+  run_id: Pyramids Training
+  initialize_from: null
+  load_model: false
+  resume: false
+  force: false
+  train_model: false
+  inference: false
+  results_dir: results
+torch_settings:
+  device: null
+debug: false

run_logs/Player-0.log

@@ -0,0 +1,363 @@
+Mono path[0] = '/home/joeny/projects/rl-learning/trained-envs-executables/linux/Pyramids/Pyramids_Data/Managed'
+Mono config path = '/home/joeny/projects/rl-learning/trained-envs-executables/linux/Pyramids/Pyramids_Data/MonoBleedingEdge/etc'
+Found 1 interfaces on host : 0) 192.168.1.83
+Multi-casting "[IP] 192.168.1.83 [Port] 55443 [Flags] 2 [Guid] 4017808438 [EditorId] 764847374 [Version] 1048832 [Id] LinuxPlayer(13,192.168.1.83) [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/joeny/.config/unity3d/Unity Technologies
+PlayerPrefs - Creating folder: /home/joeny/.config/unity3d/Unity Technologies/UnityEnvironment
+Unable to load player prefs
+Initialize engine version: 2021.3.5f1 (40eb3a945986)
+[Subsystems] Discovering subsystems at path /home/joeny/projects/rl-learning/trained-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  0.067 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: 0.580189 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 4 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]: 7808 frames, [32.0 KB-64.0 KB]: 33078 frames, [64.0 KB-128.0 KB]: 15380 frames, [2.0 MB-4.0 MB]: 1 frames
+      Initial Block Size 4.0 MB
+      Current Block Size 4.0 MB
+      Peak Allocated Bytes 2.0 MB
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 8]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 10]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 4]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 6]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 1]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 11]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 3]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_BatchDeleteObjects]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_AUDIO_FMOD stream thread]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 2]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 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 1]
+      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_Profiler.Dispatcher]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0.9 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 3]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 12]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_AssetGarbageCollectorHelper] x 7
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 5]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 13]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 2]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 0]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 4]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 0]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 5]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 14]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 6]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0.8 KB
+      Overflow Count 0
+    [ALLOC_TEMP_EnlightenWorker] x 4
+      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 9]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Loading.AsyncRead]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 128 B
+      Overflow Count 0
+[ALLOC_MEMORYPROFILER]
+  Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 55968 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 19967
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 2.4 MB
+      Failed Allocations. Bucket layout:
+        16B: 6 Subsections = 2048 buckets. Failed count: 1331373
+        32B: 37 Subsections = 9472 buckets. Failed count: 2402
+        48B: 56 Subsections = 11468 buckets. Failed count: 1907
+        64B: 44 Subsections = 7509 buckets. Failed count: 366
+        80B: 14 Subsections = 2048 buckets. Failed count: 1473979
+        96B: 14 Subsections = 1792 buckets. Failed count: 1752480
+        112B: 3 Subsections = 341 buckets. Failed count: 0
+        128B: 82 Subsections = 8396 buckets. Failed count: 16798
+    [ALLOC_DEFAULT_MAIN]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 56248 frames, [32.0 MB-64.0 MB]: 19 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 3
+      Peak Allocated memory 35.9 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 56267 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 24.3 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 2.4 MB
+      Failed Allocations. Bucket layout:
+        16B: 6 Subsections = 2048 buckets. Failed count: 1331373
+        32B: 37 Subsections = 9472 buckets. Failed count: 2402
+        48B: 56 Subsections = 11468 buckets. Failed count: 1907
+        64B: 44 Subsections = 7509 buckets. Failed count: 366
+        80B: 14 Subsections = 2048 buckets. Failed count: 1473979
+        96B: 14 Subsections = 1792 buckets. Failed count: 1752480
+        112B: 3 Subsections = 341 buckets. Failed count: 0
+        128B: 82 Subsections = 8396 buckets. Failed count: 16798
+    [ALLOC_GFX_MAIN]
+      Peak usage frame count: [32.0 KB-64.0 KB]: 56266 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]: 56267 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 67.7 KB
+      Peak Large allocation bytes 0 B
+[ALLOC_CACHEOBJECTS] Dual Thread Allocator
+  Peak main deferred allocation count 1
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 2.4 MB
+      Failed Allocations. Bucket layout:
+        16B: 6 Subsections = 2048 buckets. Failed count: 1331373
+        32B: 37 Subsections = 9472 buckets. Failed count: 2402
+        48B: 56 Subsections = 11468 buckets. Failed count: 1907
+        64B: 44 Subsections = 7509 buckets. Failed count: 366
+        80B: 14 Subsections = 2048 buckets. Failed count: 1473979
+        96B: 14 Subsections = 1792 buckets. Failed count: 1752480
+        112B: 3 Subsections = 341 buckets. Failed count: 0
+        128B: 82 Subsections = 8396 buckets. Failed count: 16798
+    [ALLOC_CACHEOBJECTS_MAIN]
+      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 55968 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]: 56266 frames, [4.0 MB-8.0 MB]: 1 frames
+      Requested Block Size 4.0 MB
+      Peak Block count 2
+      Peak Allocated memory 4.7 MB
+      Peak Large allocation bytes 0 B
+[ALLOC_TYPETREE] Dual Thread Allocator
+  Peak main deferred allocation count 0
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 2.4 MB
+      Failed Allocations. Bucket layout:
+        16B: 6 Subsections = 2048 buckets. Failed count: 1331373
+        32B: 37 Subsections = 9472 buckets. Failed count: 2402
+        48B: 56 Subsections = 11468 buckets. Failed count: 1907
+        64B: 44 Subsections = 7509 buckets. Failed count: 366
+        80B: 14 Subsections = 2048 buckets. Failed count: 1473979
+        96B: 14 Subsections = 1792 buckets. Failed count: 1752480
+        112B: 3 Subsections = 341 buckets. Failed count: 0
+        128B: 82 Subsections = 8396 buckets. Failed count: 16798
+    [ALLOC_TYPETREE_MAIN]
+      Peak usage frame count: [0-1.0 KB]: 56267 frames
+      Requested Block Size 2.0 MB
+      Peak Block count 1
+      Peak Allocated memory 1.1 KB
+      Peak Large allocation bytes 0 B
+    [ALLOC_TYPETREE_THREAD]
+      Peak usage frame count: [1.0 KB-2.0 KB]: 56267 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: [16.0 KB-32.0 KB]: 56267 frames
+  Requested Block Size 16.0 MB
+  Peak Block count 1
+  Peak Allocated memory 31.4 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":1712441530788,"processId":10460,"allocatedMemory":1976496,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"NewDelete":12929},{"Thread":34628},{"Manager":13967},{"VertexData":12},{"Geometry":280},{"Texture":16},{"Shader":69173},{"Material":24},{"GfxDevice":35248},{"Animation":304},{"Audio":3976},{"Physics":288},{"Serialization":216},{"Input":9222},{"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":3520},{"DynamicArray":30868},{"HashMap":7680},{"Utility":3808},{"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":520},{"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": 0.14446556568145752,
+            "min": 0.14446556568145752,
+            "max": 1.444345235824585,
+            "count": 100
+        },
+        "Pyramids.Policy.Entropy.sum": {
+            "value": 4329.34423828125,
+            "min": 4329.34423828125,
+            "max": 43815.65625,
+            "count": 100
+        },
+        "Pyramids.Step.mean": {
+            "value": 2999995.0,
+            "min": 29952.0,
+            "max": 2999995.0,
+            "count": 100
+        },
+        "Pyramids.Step.sum": {
+            "value": 2999995.0,
+            "min": 29952.0,
+            "max": 2999995.0,
+            "count": 100
+        },
+        "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 0.7704235315322876,
+            "min": -0.10181490331888199,
+            "max": 0.8655116558074951,
+            "count": 100
+        },
+        "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 228.8157958984375,
+            "min": -24.537391662597656,
+            "max": 263.11553955078125,
+            "count": 100
+        },
+        "Pyramids.Policy.RndValueEstimate.mean": {
+            "value": 0.016733018681406975,
+            "min": 0.0011387375416234136,
+            "max": 0.555656373500824,
+            "count": 100
+        },
+        "Pyramids.Policy.RndValueEstimate.sum": {
+            "value": 4.9697065353393555,
+            "min": 0.3108753561973572,
+            "max": 131.69056701660156,
+            "count": 100
+        },
+        "Pyramids.Losses.PolicyLoss.mean": {
+            "value": 0.06988161647585038,
+            "min": 0.06204224426050851,
+            "max": 0.07483950753770285,
+            "count": 100
+        },
+        "Pyramids.Losses.PolicyLoss.sum": {
+            "value": 0.9783426306619054,
+            "min": 0.4822765194875156,
+            "max": 1.0786946713342331,
+            "count": 100
+        },
+        "Pyramids.Losses.ValueLoss.mean": {
+            "value": 0.01392988887444629,
+            "min": 0.00039698107112373356,
+            "max": 0.02598050595420415,
+            "count": 100
+        },
+        "Pyramids.Losses.ValueLoss.sum": {
+            "value": 0.19501844424224804,
+            "min": 0.00555773499573227,
+            "max": 0.26956557048833935,
+            "count": 100
+        },
+        "Pyramids.Policy.LearningRate.mean": {
+            "value": 1.5683637629595244e-06,
+            "min": 1.5683637629595244e-06,
+            "max": 0.00029838354339596195,
+            "count": 100
+        },
+        "Pyramids.Policy.LearningRate.sum": {
+            "value": 2.1957092681433342e-05,
+            "min": 2.1957092681433342e-05,
+            "max": 0.0039275268908244,
+            "count": 100
+        },
+        "Pyramids.Policy.Epsilon.mean": {
+            "value": 0.10052275476190477,
+            "min": 0.10052275476190477,
+            "max": 0.19946118095238097,
+            "count": 100
+        },
+        "Pyramids.Policy.Epsilon.sum": {
+            "value": 1.4073185666666668,
+            "min": 1.3897045333333333,
+            "max": 2.7973922,
+            "count": 100
+        },
+        "Pyramids.Policy.Beta.mean": {
+            "value": 6.222320071428574e-05,
+            "min": 6.222320071428574e-05,
+            "max": 0.009946171977142856,
+            "count": 100
+        },
+        "Pyramids.Policy.Beta.sum": {
+            "value": 0.0008711248100000005,
+            "min": 0.0008711248100000005,
+            "max": 0.13092664244000002,
+            "count": 100
+        },
+        "Pyramids.Losses.RNDLoss.mean": {
+            "value": 0.008425016887485981,
+            "min": 0.008099747821688652,
+            "max": 0.6463526487350464,
+            "count": 100
+        },
+        "Pyramids.Losses.RNDLoss.sum": {
+            "value": 0.11795023083686829,
+            "min": 0.11600933969020844,
+            "max": 4.524468421936035,
+            "count": 100
+        },
+        "Pyramids.Environment.EpisodeLength.mean": {
+            "value": 222.0597014925373,
+            "min": 207.645390070922,
+            "max": 999.0,
+            "count": 100
+        },
+        "Pyramids.Environment.EpisodeLength.sum": {
+            "value": 29756.0,
+            "min": 15984.0,
+            "max": 32511.0,
+            "count": 100
+        },
+        "Pyramids.Environment.CumulativeReward.mean": {
+            "value": 1.761954872175715,
+            "min": -1.0000000521540642,
+            "max": 1.7871785570468222,
+            "count": 100
+        },
+        "Pyramids.Environment.CumulativeReward.sum": {
+            "value": 234.3399979993701,
+            "min": -32.000001668930054,
+            "max": 251.8519984483719,
+            "count": 100
+        },
+        "Pyramids.Policy.ExtrinsicReward.mean": {
+            "value": 1.761954872175715,
+            "min": -1.0000000521540642,
+            "max": 1.7871785570468222,
+            "count": 100
+        },
+        "Pyramids.Policy.ExtrinsicReward.sum": {
+            "value": 234.3399979993701,
+            "min": -32.000001668930054,
+            "max": 251.8519984483719,
+            "count": 100
+        },
+        "Pyramids.Policy.RndReward.mean": {
+            "value": 0.019676849928105082,
+            "min": 0.017501125833372988,
+            "max": 15.005290312692523,
+            "count": 100
+        },
+        "Pyramids.Policy.RndReward.sum": {
+            "value": 2.617021040437976,
+            "min": 2.4676587425055914,
+            "max": 240.08464500308037,
+            "count": 100
+        },
+        "Pyramids.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 100
+        },
+        "Pyramids.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 100
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1712438014",
+        "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
+        "command_line_arguments": "/home/joeny/.local/bin/mlagents-learn ./ml-agents/config/ppo/PyramidsRND.yaml --env=trained-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics",
+        "mlagents_version": "1.1.0.dev0",
+        "mlagents_envs_version": "1.1.0.dev0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "2.2.1+cu121",
+        "numpy_version": "1.23.5",
+        "end_time_seconds": "1712441530"
+    },
+    "total": 3516.1791991659993,
+    "count": 1,
+    "self": 0.2688839359998383,
+    "children": {
+        "run_training.setup": {
+            "total": 0.03330624399950466,
+            "count": 1,
+            "self": 0.03330624399950466
+        },
+        "TrainerController.start_learning": {
+            "total": 3515.877008986,
+            "count": 1,
+            "self": 3.147021408013643,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 1.5705331240005762,
+                    "count": 1,
+                    "self": 1.5705331240005762
+                },
+                "TrainerController.advance": {
+                    "total": 3511.0439016629844,
+                    "count": 194833,
+                    "self": 3.0325700815346863,
+                    "children": {
+                        "env_step": {
+                            "total": 2382.5480493187533,
+                            "count": 194833,
+                            "self": 2118.9429423037627,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 261.4096492479948,
+                                    "count": 194833,
+                                    "self": 8.231087012253738,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 253.17856223574108,
+                                            "count": 187554,
+                                            "self": 253.17856223574108
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 2.195457766995787,
+                                    "count": 194833,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 3511.8801136623697,
+                                            "count": 194833,
+                                            "is_parallel": true,
+                                            "self": 1610.1382468191578,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.0011475289993541082,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.000341423000463692,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.0008061059988904162,
+                                                                    "count": 8,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0008061059988904162
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.0254131720002988,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0005840149988216581,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.00019179200080543524,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00019179200080543524
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.023148442000092473,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.023148442000092473
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.0014889230005792342,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0002428700017844676,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.0012460529987947666,
+                                                                            "count": 8,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.0012460529987947666
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 1901.741866843212,
+                                                    "count": 194832,
+                                                    "is_parallel": true,
+                                                    "self": 61.07512853609114,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 32.398689086351624,
+                                                            "count": 194832,
+                                                            "is_parallel": true,
+                                                            "self": 32.398689086351624
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 1653.8236376497634,
+                                                            "count": 194832,
+                                                            "is_parallel": true,
+                                                            "self": 1653.8236376497634
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 154.44441157100573,
+                                                            "count": 194832,
+                                                            "is_parallel": true,
+                                                            "self": 31.70061374753186,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 122.74379782347387,
+                                                                    "count": 1558656,
+                                                                    "is_parallel": true,
+                                                                    "self": 122.74379782347387
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 1125.4632822626963,
+                            "count": 194833,
+                            "self": 5.892573370757418,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 220.0148202569244,
+                                    "count": 194833,
+                                    "self": 219.5871394479209,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 0.4276808090035047,
+                                            "count": 6,
+                                            "self": 0.4276808090035047
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 899.5558886350145,
+                                    "count": 1392,
+                                    "self": 520.4894827230446,
+                                    "children": {
+                                        "TorchPPOOptimizer.update": {
+                                            "total": 379.0664059119699,
+                                            "count": 68403,
+                                            "self": 379.0664059119699
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 5.830006557516754e-07,
+                    "count": 1,
+                    "self": 5.830006557516754e-07
+                },
+                "TrainerController._save_models": {
+                    "total": 0.11555220800073585,
+                    "count": 1,
+                    "self": 0.0009456030020373873,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.11460660499869846,
+                            "count": 1,
+                            "self": 0.11460660499869846
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,65 @@
+{
+    "Pyramids": {
+        "checkpoints": [
+            {
+                "steps": 1499969,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1499969.onnx",
+                "reward": 1.817727255550298,
+                "creation_time": 1712439723.3151164,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-1499969.pt"
+                ]
+            },
+            {
+                "steps": 1999943,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1999943.onnx",
+                "reward": 1.7869999557733536,
+                "creation_time": 1712440320.4849904,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-1999943.pt"
+                ]
+            },
+            {
+                "steps": 2499990,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-2499990.onnx",
+                "reward": 1.803555558125178,
+                "creation_time": 1712440926.0802062,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-2499990.pt"
+                ]
+            },
+            {
+                "steps": 2999995,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-2999995.onnx",
+                "reward": 1.8155000042170286,
+                "creation_time": 1712441530.4176033,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-2999995.pt"
+                ]
+            },
+            {
+                "steps": 3000093,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-3000093.onnx",
+                "reward": 1.8252222256528006,
+                "creation_time": 1712441530.5386484,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-3000093.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 3000093,
+            "file_path": "results/Pyramids Training/Pyramids.onnx",
+            "reward": 1.8252222256528006,
+            "creation_time": 1712441530.5386484,
+            "auxillary_file_paths": [
+                "results/Pyramids Training/Pyramids/Pyramids-3000093.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "1.1.0.dev0",
+        "torch_version": "2.2.1+cu121"
+    }
+}