First Push

Pyramids.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d123c7e3d45e0b75412e77a96ba9928ce46dd4d2b644916b90c2323d4be482a8
+size 1420238

Pyramids/Pyramids-1000074.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d123c7e3d45e0b75412e77a96ba9928ce46dd4d2b644916b90c2323d4be482a8
+size 1420238

Pyramids/Pyramids-1000074.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75c012bb78ada98f2d296219ba2964f799104d3ee886b21c28f27760485cf967
+size 8656731

Pyramids/Pyramids-499962.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4b23dfff941aefda0a83f5492a2cccaba77facbf8adb6bac6c38fe06d2ef02f
+size 1420238

Pyramids/Pyramids-499962.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:024e9b6285f43fcc0a33fded6e720b27ea154e6b8c066b249d0af2d00a486fc5
+size 8656650

Pyramids/Pyramids-999946.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d123c7e3d45e0b75412e77a96ba9928ce46dd4d2b644916b90c2323d4be482a8
+size 1420238

Pyramids/Pyramids-999946.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d35fd0df5fe5bc98e509a5026c3efe2b8992f0cec21bdeab14d7a2a125d7f72
+size 8656650

Pyramids/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20c169c1baa0b5fac8c45c3ade79311e186b081a78474a4106480861c01ab76c
+size 8656181

Pyramids/events.out.tfevents.1750406456.IAILABWATCHER.1822235.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:067949bb4f75eb0ead1db20aa02b79c79c6b588b34cbdcb1a22bf219194bb249
+size 305306

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: hanslab37/ppo-Pyramids
+  3. Step 2: Select your *.nn /*.onnx file
+  4. Click on Watch the agent play 👀
+  

config.json

@@ -0,0 +1 @@
+{"default_settings": null, "behaviors": {"Pyramids": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.01, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}, "rnd": {"gamma": 0.99, "strength": 0.01, "network_settings": {"normalize": false, "hidden_units": 64, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0001, "encoding_size": null}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 1000000, "time_horizon": 128, "summary_freq": 30000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./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: 1000000
+    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 +1,387 @@
+Mono path[0] = '/root/ReinforcementLearning/Huggingface/ml-agents/trained-envs-executables/linux/Pyramids/Pyramids_Data/Managed'
+Mono config path = '/root/ReinforcementLearning/Huggingface/ml-agents/trained-envs-executables/linux/Pyramids/Pyramids_Data/MonoBleedingEdge/etc'
+Found 4 interfaces on host : 0) 10.255.255.254 1) 172.31.183.199 2) 172.18.0.1 3) 172.17.0.1
+Multi-casting "[IP] 10.255.255.254 [Port] 55047 [Flags] 2 [Guid] 2752407344 [EditorId] 764847374 [Version] 1048832 [Id] LinuxPlayer(13,172.31.183.199) [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: /root/.config/unity3d/Unity Technologies
+PlayerPrefs - Creating folder: /root/.config/unity3d/Unity Technologies/UnityEnvironment
+Unable to load player prefs
+Initialize engine version: 2021.3.5f1 (40eb3a945986)
+[Subsystems] Discovering subsystems at path /root/ReinforcementLearning/Huggingface/ml-agents/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  0.071 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: 0.790600 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 10 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]: 3201 frames, [32.0 KB-64.0 KB]: 11721 frames, [64.0 KB-128.0 KB]: 3841 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_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 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 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 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_Profiler.Dispatcher]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 14]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 5]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 13]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 2]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 11]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 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 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 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 10
+      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 130 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_AUDIO_FMOD stream thread]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 15]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 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_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 19
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 0]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 4]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 14]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 7]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+[ALLOC_MEMORYPROFILER]
+  Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 18465 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 12569
+    [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]: 18763 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 3
+      Peak Allocated memory 30.5 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 18764 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 31.0 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]: 18763 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]: 18764 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]: 18465 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]: 18763 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]: 18764 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]: 18764 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]: 18764 frames
+  Requested Block Size 16.0 MB
+  Peak Block count 1
+  Peak Allocated memory 43.8 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":1750408807997,"processId":1822397,"allocatedMemory":2054916,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"NewDelete":73418},{"Thread":34964},{"Manager":26831},{"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":3537},{"DynamicArray":30868},{"HashMap":7680},{"Utility":8704},{"PoolAlloc":1160},{"TypeTree":1792},{"ScriptManager":80},{"RuntimeInitializeOnLoadManager":72},{"SpriteAtlas":112},{"GI":3272},{"Unet":16},{"Director":7760},{"WebRequest":720},{"VR":45473},{"SceneManager":424},{"Video":32},{"LazyScriptCache":32},{"NativeArray":384},{"Camera":25},{"Secure":1},{"SerializationCache":624},{"APIUpdating":5872},{"Subsystems":384},{"VirtualTexturing":57552},{"AssetReference":32}]}

run_logs/timers.json

@@ -0,0 +1,398 @@
+{
+    "name": "root",
+    "gauges": {
+        "Pyramids.Policy.Entropy.mean": {
+            "value": 0.3020292818546295,
+            "min": 0.30125200748443604,
+            "max": 1.4849423170089722,
+            "count": 33
+        },
+        "Pyramids.Policy.Entropy.sum": {
+            "value": 9075.3759765625,
+            "min": 9042.3798828125,
+            "max": 45047.2109375,
+            "count": 33
+        },
+        "Pyramids.Step.mean": {
+            "value": 989897.0,
+            "min": 29952.0,
+            "max": 989897.0,
+            "count": 33
+        },
+        "Pyramids.Step.sum": {
+            "value": 989897.0,
+            "min": 29952.0,
+            "max": 989897.0,
+            "count": 33
+        },
+        "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 0.6725330352783203,
+            "min": -0.13907623291015625,
+            "max": 0.7278995513916016,
+            "count": 33
+        },
+        "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 192.34445190429688,
+            "min": -33.65644836425781,
+            "max": 210.36297607421875,
+            "count": 33
+        },
+        "Pyramids.Policy.RndValueEstimate.mean": {
+            "value": 0.010753563605248928,
+            "min": -0.0007151158060878515,
+            "max": 0.433732807636261,
+            "count": 33
+        },
+        "Pyramids.Policy.RndValueEstimate.sum": {
+            "value": 3.075519323348999,
+            "min": -0.20452311635017395,
+            "max": 102.794677734375,
+            "count": 33
+        },
+        "Pyramids.Losses.PolicyLoss.mean": {
+            "value": 0.06579657682414618,
+            "min": 0.06500817533482665,
+            "max": 0.07416306532345837,
+            "count": 33
+        },
+        "Pyramids.Losses.PolicyLoss.sum": {
+            "value": 0.9211520755380465,
+            "min": 0.5191414572642086,
+            "max": 1.031899529938956,
+            "count": 33
+        },
+        "Pyramids.Losses.ValueLoss.mean": {
+            "value": 0.015968983531206443,
+            "min": 0.0004374867095154916,
+            "max": 0.018075849530370242,
+            "count": 33
+        },
+        "Pyramids.Losses.ValueLoss.sum": {
+            "value": 0.2235657694368902,
+            "min": 0.004812353804670408,
+            "max": 0.25306189342518337,
+            "count": 33
+        },
+        "Pyramids.Policy.LearningRate.mean": {
+            "value": 7.223969020614289e-06,
+            "min": 7.223969020614289e-06,
+            "max": 0.00029515063018788575,
+            "count": 33
+        },
+        "Pyramids.Policy.LearningRate.sum": {
+            "value": 0.00010113556628860005,
+            "min": 0.00010113556628860005,
+            "max": 0.0035074874308375996,
+            "count": 33
+        },
+        "Pyramids.Policy.Epsilon.mean": {
+            "value": 0.10240795714285718,
+            "min": 0.10240795714285718,
+            "max": 0.19838354285714285,
+            "count": 33
+        },
+        "Pyramids.Policy.Epsilon.sum": {
+            "value": 1.4337114000000004,
+            "min": 1.3886848,
+            "max": 2.6175660000000005,
+            "count": 33
+        },
+        "Pyramids.Policy.Beta.mean": {
+            "value": 0.0002505549185714287,
+            "min": 0.0002505549185714287,
+            "max": 0.00983851593142857,
+            "count": 33
+        },
+        "Pyramids.Policy.Beta.sum": {
+            "value": 0.003507768860000002,
+            "min": 0.003507768860000002,
+            "max": 0.11693932376,
+            "count": 33
+        },
+        "Pyramids.Losses.RNDLoss.mean": {
+            "value": 0.012262492440640926,
+            "min": 0.012262492440640926,
+            "max": 0.47736796736717224,
+            "count": 33
+        },
+        "Pyramids.Losses.RNDLoss.sum": {
+            "value": 0.17167489230632782,
+            "min": 0.17167489230632782,
+            "max": 3.341575860977173,
+            "count": 33
+        },
+        "Pyramids.Environment.EpisodeLength.mean": {
+            "value": 273.4056603773585,
+            "min": 258.0925925925926,
+            "max": 999.0,
+            "count": 33
+        },
+        "Pyramids.Environment.EpisodeLength.sum": {
+            "value": 28981.0,
+            "min": 15984.0,
+            "max": 32718.0,
+            "count": 33
+        },
+        "Pyramids.Environment.CumulativeReward.mean": {
+            "value": 1.7077169658018734,
+            "min": -1.0000000521540642,
+            "max": 1.7296754204128917,
+            "count": 33
+        },
+        "Pyramids.Environment.CumulativeReward.sum": {
+            "value": 181.01799837499857,
+            "min": -31.997201651334763,
+            "max": 197.18299792706966,
+            "count": 33
+        },
+        "Pyramids.Policy.ExtrinsicReward.mean": {
+            "value": 1.7077169658018734,
+            "min": -1.0000000521540642,
+            "max": 1.7296754204128917,
+            "count": 33
+        },
+        "Pyramids.Policy.ExtrinsicReward.sum": {
+            "value": 181.01799837499857,
+            "min": -31.997201651334763,
+            "max": 197.18299792706966,
+            "count": 33
+        },
+        "Pyramids.Policy.RndReward.mean": {
+            "value": 0.03478686358666548,
+            "min": 0.03478686358666548,
+            "max": 10.225412273779511,
+            "count": 33
+        },
+        "Pyramids.Policy.RndReward.sum": {
+            "value": 3.687407540186541,
+            "min": 3.687407540186541,
+            "max": 163.60659638047218,
+            "count": 33
+        },
+        "Pyramids.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 33
+        },
+        "Pyramids.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 33
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1750406448",
+        "python_version": "3.10.12 | packaged by conda-forge | (main, Jun 23 2023, 22:40:32) [GCC 12.3.0]",
+        "command_line_arguments": "/root/miniconda3/envs/stable-base/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./trained-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics",
+        "mlagents_version": "1.2.0.dev0",
+        "mlagents_envs_version": "1.2.0.dev0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "2.7.1+cu128",
+        "numpy_version": "1.23.5",
+        "end_time_seconds": "1750408808"
+    },
+    "total": 2311.9355525010033,
+    "count": 1,
+    "self": 0.9288067599700298,
+    "children": {
+        "run_training.setup": {
+            "total": 0.11956359501346014,
+            "count": 1,
+            "self": 0.11956359501346014
+        },
+        "TrainerController.start_learning": {
+            "total": 2310.8871821460198,
+            "count": 1,
+            "self": 1.355852116830647,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 13.314895067014731,
+                    "count": 1,
+                    "self": 13.314895067014731
+                },
+                "TrainerController.advance": {
+                    "total": 2296.1226301881834,
+                    "count": 64285,
+                    "self": 1.2122055814543273,
+                    "children": {
+                        "env_step": {
+                            "total": 1415.4235106999695,
+                            "count": 64285,
+                            "self": 1107.7691028590198,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 306.79488046793267,
+                                    "count": 64285,
+                                    "self": 4.274932955362601,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 302.51994751257007,
+                                            "count": 62545,
+                                            "self": 302.51994751257007
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 0.8595273730170447,
+                                    "count": 64285,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 2307.9945283712004,
+                                            "count": 64285,
+                                            "is_parallel": true,
+                                            "self": 1286.3969969660393,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.015067000000271946,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.013245048030512407,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.0018219519697595388,
+                                                                    "count": 8,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0018219519697595388
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.0376017980161123,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.00018978302250616252,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.0001850039989221841,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0001850039989221841
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.03657073699287139,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.03657073699287139
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.0006562740018125623,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00017474897322244942,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.0004815250285901129,
+                                                                            "count": 8,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.0004815250285901129
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 1021.5975314051611,
+                                                    "count": 64284,
+                                                    "is_parallel": true,
+                                                    "self": 14.317415886500385,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 10.98702951768064,
+                                                            "count": 64284,
+                                                            "is_parallel": true,
+                                                            "self": 10.98702951768064
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 954.0358871989592,
+                                                            "count": 64284,
+                                                            "is_parallel": true,
+                                                            "self": 954.0358871989592
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 42.257198802020866,
+                                                            "count": 64284,
+                                                            "is_parallel": true,
+                                                            "self": 11.2027663422341,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 31.054432459786767,
+                                                                    "count": 514272,
+                                                                    "is_parallel": true,
+                                                                    "self": 31.054432459786767
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 879.4869139067596,
+                            "count": 64285,
+                            "self": 2.637953189580003,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 152.32504985199193,
+                                    "count": 64285,
+                                    "self": 151.73665271201753,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 0.5883971399744041,
+                                            "count": 2,
+                                            "self": 0.5883971399744041
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 724.5239108651876,
+                                    "count": 450,
+                                    "self": 308.7191272043565,
+                                    "children": {
+                                        "TorchPPOOptimizer.update": {
+                                            "total": 415.80478366083116,
+                                            "count": 22779,
+                                            "self": 415.80478366083116
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 5.860056262463331e-07,
+                    "count": 1,
+                    "self": 5.860056262463331e-07
+                },
+                "TrainerController._save_models": {
+                    "total": 0.09380418798536994,
+                    "count": 1,
+                    "self": 0.0013707990001421422,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.0924333889852278,
+                            "count": 1,
+                            "self": 0.0924333889852278
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,47 @@
+{
+    "Pyramids": {
+        "checkpoints": [
+            {
+                "steps": 499962,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-499962.onnx",
+                "reward": 0.0540999174118042,
+                "creation_time": 1750407604.6143,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-499962.pt"
+                ]
+            },
+            {
+                "steps": 999946,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-999946.onnx",
+                "reward": 1.6753999978303908,
+                "creation_time": 1750408807.2172015,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-999946.pt"
+                ]
+            },
+            {
+                "steps": 1000074,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1000074.onnx",
+                "reward": 1.6753999978303908,
+                "creation_time": 1750408807.3346581,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-1000074.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 1000074,
+            "file_path": "results/Pyramids Training/Pyramids.onnx",
+            "reward": 1.6753999978303908,
+            "creation_time": 1750408807.3346581,
+            "auxillary_file_paths": [
+                "results/Pyramids Training/Pyramids/Pyramids-1000074.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "1.2.0.dev0",
+        "torch_version": "2.7.1+cu128"
+    }
+}