Second Push

Pyramids.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:906f4651a64f7d3b7ec036c4cdc32734fb2d62cfbaa5c66bafec740c17142ab9
+size 1420238

Pyramids/Pyramids-1000042.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:906f4651a64f7d3b7ec036c4cdc32734fb2d62cfbaa5c66bafec740c17142ab9
+size 1420238

Pyramids/Pyramids-1000042.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18206511c257d1f560218d46e0b2fbf36908a2d8409c5ece60610fd7ab63843e
+size 8656731

Pyramids/Pyramids-499996.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fecdb2abc14f52976562363abccde99060418ce4851869024b55c217f8faa17
+size 1420238

Pyramids/Pyramids-499996.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7993771480ae8738d2529fbbb79ec21dcc0de56d317b354222bc3082eac3d85c
+size 8656650

Pyramids/Pyramids-999914.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:906f4651a64f7d3b7ec036c4cdc32734fb2d62cfbaa5c66bafec740c17142ab9
+size 1420238

Pyramids/Pyramids-999914.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41d6594cf17b07b0248c437720a7ff491a0ba167fae15c167d6936816c68fc6f
+size 8656650

Pyramids/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3266f1305b4bda7738f14c1724dfa00aeacc46ce5d830eef5aa54782a03ccfc2
+size 8656181

Pyramids/events.out.tfevents.1765606752.zhongzhongbo.10615.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3753a12385eda9ca9f7375ce335dc1534484b4bf9bd5dc03a33d90b12a0031c
+size 808507

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: zhongzhongbo/ppo-Pyramids-Training
+  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": 10000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/Pyramids/Pyramids", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "Pyramids Training", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -0,0 +1,92 @@
+default_settings: null
+behaviors:
+  Pyramids:
+    trainer_type: ppo
+    hyperparameters:
+      batch_size: 128
+      buffer_size: 2048
+      learning_rate: 0.0003
+      beta: 0.01
+      epsilon: 0.2
+      lambd: 0.95
+      num_epoch: 3
+      shared_critic: false
+      learning_rate_schedule: linear
+      beta_schedule: linear
+      epsilon_schedule: linear
+    checkpoint_interval: 500000
+    network_settings:
+      normalize: false
+      hidden_units: 512
+      num_layers: 2
+      vis_encode_type: simple
+      memory: null
+      goal_conditioning_type: hyper
+      deterministic: false
+    reward_signals:
+      extrinsic:
+        gamma: 0.99
+        strength: 1.0
+        network_settings:
+          normalize: false
+          hidden_units: 128
+          num_layers: 2
+          vis_encode_type: simple
+          memory: null
+          goal_conditioning_type: hyper
+          deterministic: false
+      rnd:
+        gamma: 0.99
+        strength: 0.01
+        network_settings:
+          normalize: false
+          hidden_units: 64
+          num_layers: 3
+          vis_encode_type: simple
+          memory: null
+          goal_conditioning_type: hyper
+          deterministic: false
+        learning_rate: 0.0001
+        encoding_size: null
+    init_path: null
+    keep_checkpoints: 5
+    even_checkpoints: false
+    max_steps: 1000000
+    time_horizon: 128
+    summary_freq: 10000
+    threaded: false
+    self_play: null
+    behavioral_cloning: null
+env_settings:
+  env_path: ./training-envs-executables/linux/Pyramids/Pyramids
+  env_args: null
+  base_port: 5005
+  num_envs: 1
+  num_areas: 1
+  timeout_wait: 60
+  seed: -1
+  max_lifetime_restarts: 10
+  restarts_rate_limit_n: 1
+  restarts_rate_limit_period_s: 60
+engine_settings:
+  width: 84
+  height: 84
+  quality_level: 5
+  time_scale: 20
+  target_frame_rate: -1
+  capture_frame_rate: 60
+  no_graphics: true
+  no_graphics_monitor: false
+environment_parameters: null
+checkpoint_settings:
+  run_id: Pyramids Training
+  initialize_from: null
+  load_model: false
+  resume: false
+  force: false
+  train_model: false
+  inference: false
+  results_dir: results
+torch_settings:
+  device: null
+debug: false

run_logs/Player-0.log

@@ -0,0 +1,423 @@
+Mono path[0] = '/home/zhongzhongbo/Project/Colab_DRL/unit5/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/Managed'
+Mono config path = '/home/zhongzhongbo/Project/Colab_DRL/unit5/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/MonoBleedingEdge/etc'
+Found 3 interfaces on host : 0) 10.255.255.254 1) 172.17.24.110 2) 26.79.144.10
+Multi-casting "[IP] 10.255.255.254 [Port] 55093 [Flags] 2 [Guid] 3892702906 [EditorId] 764847374 [Version] 1048832 [Id] LinuxPlayer(13,172.17.24.110) [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/zhongzhongbo/.config/unity3d/Unity Technologies
+PlayerPrefs - Creating folder: /home/zhongzhongbo/.config/unity3d/Unity Technologies/UnityEnvironment
+Unable to load player prefs
+Initialize engine version: 2021.3.5f1 (40eb3a945986)
+[Subsystems] Discovering subsystems at path /home/zhongzhongbo/Project/Colab_DRL/unit5/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/UnitySubsystems
+Forcing GfxDevice: Null
+GfxDevice: creating device client; threaded=0; jobified=0
+NullGfxDevice:
+    Version:  NULL 1.0 [1.0]
+    Renderer: Null Device
+    Vendor:   Unity Technologies
+Begin MonoManager ReloadAssembly
+- Completed reload, in  0.061 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: 0.679542 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]: 3158 frames, [32.0 KB-64.0 KB]: 12898 frames, [64.0 KB-128.0 KB]: 2709 frames, [2.0 MB-4.0 MB]: 1 frames
+      Initial Block Size 4.0 MB
+      Current Block Size 4.0 MB
+      Peak Allocated Bytes 2.0 MB
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 18]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 8]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 4]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 11]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 3]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_BatchDeleteObjects]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 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 14]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 3]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Profiler.Dispatcher]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 3.8 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 17]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 5]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 13]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 2]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 11]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 6]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 5]
+      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_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_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 134 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 0.8 KB
+      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]: 18467 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 11048
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 2.2 MB
+      Failed Allocations. Bucket layout:
+        16B: 26 Subsections = 8874 buckets. Failed count: 0
+        32B: 27 Subsections = 6912 buckets. Failed count: 0
+        48B: 59 Subsections = 12083 buckets. Failed count: 0
+        64B: 42 Subsections = 7168 buckets. Failed count: 0
+        80B: 46 Subsections = 6729 buckets. Failed count: 140
+        96B: 51 Subsections = 6528 buckets. Failed count: 148
+        112B: 3 Subsections = 341 buckets. Failed count: 0
+        128B: 2 Subsections = 204 buckets. Failed count: 0
+    [ALLOC_DEFAULT_MAIN]
+      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 18765 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 3
+      Peak Allocated memory 30.3 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 18766 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 31.2 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 2.2 MB
+      Failed Allocations. Bucket layout:
+        16B: 26 Subsections = 8874 buckets. Failed count: 0
+        32B: 27 Subsections = 6912 buckets. Failed count: 0
+        48B: 59 Subsections = 12083 buckets. Failed count: 0
+        64B: 42 Subsections = 7168 buckets. Failed count: 0
+        80B: 46 Subsections = 6729 buckets. Failed count: 140
+        96B: 51 Subsections = 6528 buckets. Failed count: 148
+        112B: 3 Subsections = 341 buckets. Failed count: 0
+        128B: 2 Subsections = 204 buckets. Failed count: 0
+    [ALLOC_GFX_MAIN]
+      Peak usage frame count: [32.0 KB-64.0 KB]: 18765 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]: 18766 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 2.2 MB
+      Failed Allocations. Bucket layout:
+        16B: 26 Subsections = 8874 buckets. Failed count: 0
+        32B: 27 Subsections = 6912 buckets. Failed count: 0
+        48B: 59 Subsections = 12083 buckets. Failed count: 0
+        64B: 42 Subsections = 7168 buckets. Failed count: 0
+        80B: 46 Subsections = 6729 buckets. Failed count: 140
+        96B: 51 Subsections = 6528 buckets. Failed count: 148
+        112B: 3 Subsections = 341 buckets. Failed count: 0
+        128B: 2 Subsections = 204 buckets. Failed count: 0
+    [ALLOC_CACHEOBJECTS_MAIN]
+      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 18467 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]: 18765 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 2.2 MB
+      Failed Allocations. Bucket layout:
+        16B: 26 Subsections = 8874 buckets. Failed count: 0
+        32B: 27 Subsections = 6912 buckets. Failed count: 0
+        48B: 59 Subsections = 12083 buckets. Failed count: 0
+        64B: 42 Subsections = 7168 buckets. Failed count: 0
+        80B: 46 Subsections = 6729 buckets. Failed count: 140
+        96B: 51 Subsections = 6528 buckets. Failed count: 148
+        112B: 3 Subsections = 341 buckets. Failed count: 0
+        128B: 2 Subsections = 204 buckets. Failed count: 0
+    [ALLOC_TYPETREE_MAIN]
+      Peak usage frame count: [0-1.0 KB]: 18766 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]: 18766 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]: 18766 frames
+  Requested Block Size 16.0 MB
+  Peak Block count 1
+  Peak Allocated memory 44.4 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":1765610802851,"processId":10682,"allocatedMemory":2446281,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"NewDelete":464723},{"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":3597},{"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": 0.39600932598114014,
+            "min": 0.39600932598114014,
+            "max": 1.5923776626586914,
+            "count": 100
+        },
+        "Pyramids.Policy.Entropy.sum": {
+            "value": 3934.748779296875,
+            "min": 3934.748779296875,
+            "max": 16305.947265625,
+            "count": 100
+        },
+        "Pyramids.Step.mean": {
+            "value": 999914.0,
+            "min": 9984.0,
+            "max": 999914.0,
+            "count": 100
+        },
+        "Pyramids.Step.sum": {
+            "value": 999914.0,
+            "min": 9984.0,
+            "max": 999914.0,
+            "count": 100
+        },
+        "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 0.5497878789901733,
+            "min": -0.1009390577673912,
+            "max": 0.5919233560562134,
+            "count": 100
+        },
+        "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 51.130271911621094,
+            "min": -8.157323837280273,
+            "max": 55.04887390136719,
+            "count": 100
+        },
+        "Pyramids.Policy.RndValueEstimate.mean": {
+            "value": -0.018666034564375877,
+            "min": -0.020374121144413948,
+            "max": 0.27049723267555237,
+            "count": 100
+        },
+        "Pyramids.Policy.RndValueEstimate.sum": {
+            "value": -1.7359412908554077,
+            "min": -1.833670973777771,
+            "max": 21.910276412963867,
+            "count": 100
+        },
+        "Pyramids.Losses.PolicyLoss.mean": {
+            "value": 0.06798527051772302,
+            "min": 0.05804310069652274,
+            "max": 0.08321485996926097,
+            "count": 100
+        },
+        "Pyramids.Losses.PolicyLoss.sum": {
+            "value": 0.3399263525886151,
+            "min": 0.1467036777272976,
+            "max": 0.3856322744646676,
+            "count": 100
+        },
+        "Pyramids.Losses.ValueLoss.mean": {
+            "value": 0.016657138171528158,
+            "min": 0.00013730430139025941,
+            "max": 0.016657138171528158,
+            "count": 100
+        },
+        "Pyramids.Losses.ValueLoss.sum": {
+            "value": 0.08328569085764079,
+            "min": 0.0005516500210525806,
+            "max": 0.08328569085764079,
+            "count": 100
+        },
+        "Pyramids.Policy.LearningRate.mean": {
+            "value": 1.3340195553600019e-06,
+            "min": 1.3340195553600019e-06,
+            "max": 0.0002981568006144,
+            "count": 100
+        },
+        "Pyramids.Policy.LearningRate.sum": {
+            "value": 6.670097776800009e-06,
+            "min": 6.670097776800009e-06,
+            "max": 0.001387917037361,
+            "count": 100
+        },
+        "Pyramids.Policy.Epsilon.mean": {
+            "value": 0.10044464,
+            "min": 0.10044464,
+            "max": 0.1993856,
+            "count": 100
+        },
+        "Pyramids.Policy.Epsilon.sum": {
+            "value": 0.5022232,
+            "min": 0.39717119999999995,
+            "max": 0.962639,
+            "count": 100
+        },
+        "Pyramids.Policy.Beta.mean": {
+            "value": 5.441953600000006e-05,
+            "min": 5.441953600000006e-05,
+            "max": 0.00993862144,
+            "count": 100
+        },
+        "Pyramids.Policy.Beta.sum": {
+            "value": 0.0002720976800000003,
+            "min": 0.0002720976800000003,
+            "max": 0.046267636099999995,
+            "count": 100
+        },
+        "Pyramids.Losses.RNDLoss.mean": {
+            "value": 0.01027862448245287,
+            "min": 0.009723183698952198,
+            "max": 0.5842149257659912,
+            "count": 100
+        },
+        "Pyramids.Losses.RNDLoss.sum": {
+            "value": 0.05139312148094177,
+            "min": 0.03976733610033989,
+            "max": 1.1684298515319824,
+            "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
+        },
+        "Pyramids.Environment.EpisodeLength.mean": {
+            "value": 359.7741935483871,
+            "min": 303.0,
+            "max": 999.0,
+            "count": 98
+        },
+        "Pyramids.Environment.EpisodeLength.sum": {
+            "value": 11153.0,
+            "min": 303.0,
+            "max": 15984.0,
+            "count": 98
+        },
+        "Pyramids.Environment.CumulativeReward.mean": {
+            "value": 1.5111290072241137,
+            "min": -1.0000000521540642,
+            "max": 1.6969999372959137,
+            "count": 98
+        },
+        "Pyramids.Environment.CumulativeReward.sum": {
+            "value": 46.844999223947525,
+            "min": -16.000000834465027,
+            "max": 46.844999223947525,
+            "count": 98
+        },
+        "Pyramids.Policy.ExtrinsicReward.mean": {
+            "value": 1.5111290072241137,
+            "min": -1.0000000521540642,
+            "max": 1.6969999372959137,
+            "count": 98
+        },
+        "Pyramids.Policy.ExtrinsicReward.sum": {
+            "value": 46.844999223947525,
+            "min": -16.000000834465027,
+            "max": 46.844999223947525,
+            "count": 98
+        },
+        "Pyramids.Policy.RndReward.mean": {
+            "value": 0.03793983065125142,
+            "min": 0.03636770726855806,
+            "max": 6.536046816036105,
+            "count": 98
+        },
+        "Pyramids.Policy.RndReward.sum": {
+            "value": 1.176134750188794,
+            "min": 0.3488286882638931,
+            "max": 104.57674905657768,
+            "count": 98
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1765606750",
+        "python_version": "3.10.19 (main, Oct 21 2025, 16:43:05) [GCC 11.2.0]",
+        "command_line_arguments": "/home/zhongzhongbo/miniconda3/envs/rl_env/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics",
+        "mlagents_version": "1.2.0.dev0",
+        "mlagents_envs_version": "1.2.0.dev0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "2.8.0+cu128",
+        "numpy_version": "1.23.5",
+        "end_time_seconds": "1765610803"
+    },
+    "total": 4052.2028248120023,
+    "count": 1,
+    "self": 1.3038348230020347,
+    "children": {
+        "run_training.setup": {
+            "total": 0.022352104000674444,
+            "count": 1,
+            "self": 0.022352104000674444
+        },
+        "TrainerController.start_learning": {
+            "total": 4050.8766378849996,
+            "count": 1,
+            "self": 1.1107233865259332,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 2.8613487699985853,
+                    "count": 1,
+                    "self": 2.8613487699985853
+                },
+                "TrainerController.advance": {
+                    "total": 4046.7158305214743,
+                    "count": 63697,
+                    "self": 1.0549588737230806,
+                    "children": {
+                        "env_step": {
+                            "total": 1734.3984053880304,
+                            "count": 63697,
+                            "self": 900.1793539389637,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 833.4672123150976,
+                                    "count": 63697,
+                                    "self": 4.557526960828909,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 828.9096853542687,
+                                            "count": 62551,
+                                            "self": 828.9096853542687
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 0.7518391339690425,
+                                    "count": 63697,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 4047.7813636611536,
+                                            "count": 63697,
+                                            "is_parallel": true,
+                                            "self": 3221.650677175625,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.0013396100002864841,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.00043138800174347125,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.0009082219985430129,
+                                                                    "count": 8,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0009082219985430129
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.0263196859996242,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0001886059999378631,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.00016504099949088413,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00016504099949088413
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.025359100000059698,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.025359100000059698
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.0006069390001357533,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00012697400052275043,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.0004799649996130029,
+                                                                            "count": 8,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.0004799649996130029
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 826.1306864855287,
+                                                    "count": 63696,
+                                                    "is_parallel": true,
+                                                    "self": 11.68650920420805,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 8.740673940024863,
+                                                            "count": 63696,
+                                                            "is_parallel": true,
+                                                            "self": 8.740673940024863
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 775.2746680870277,
+                                                            "count": 63696,
+                                                            "is_parallel": true,
+                                                            "self": 775.2746680870277
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 30.42883525426805,
+                                                            "count": 63696,
+                                                            "is_parallel": true,
+                                                            "self": 7.246144479184295,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 23.182690775083756,
+                                                                    "count": 509568,
+                                                                    "is_parallel": true,
+                                                                    "self": 23.182690775083756
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 2311.262466259721,
+                            "count": 63697,
+                            "self": 2.1345862784801284,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 274.3112951072035,
+                                    "count": 63697,
+                                    "self": 273.71047753620223,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 0.6008175710012438,
+                                            "count": 2,
+                                            "self": 0.6008175710012438
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 2034.8165848740373,
+                                    "count": 457,
+                                    "self": 645.6293013871036,
+                                    "children": {
+                                        "TorchPPOOptimizer.update": {
+                                            "total": 1389.1872834869337,
+                                            "count": 22767,
+                                            "self": 1389.1872834869337
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 6.070004019420594e-07,
+                    "count": 1,
+                    "self": 6.070004019420594e-07
+                },
+                "TrainerController._save_models": {
+                    "total": 0.18873460000031628,
+                    "count": 1,
+                    "self": 0.0014435439989028964,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.18729105600141338,
+                            "count": 1,
+                            "self": 0.18729105600141338
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,47 @@
+{
+    "Pyramids": {
+        "checkpoints": [
+            {
+                "steps": 499996,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-499996.onnx",
+                "reward": 1.4350000023841858,
+                "creation_time": 1765608761.1255586,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-499996.pt"
+                ]
+            },
+            {
+                "steps": 999914,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-999914.onnx",
+                "reward": null,
+                "creation_time": 1765610801.6499305,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-999914.pt"
+                ]
+            },
+            {
+                "steps": 1000042,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1000042.onnx",
+                "reward": null,
+                "creation_time": 1765610801.868744,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-1000042.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 1000042,
+            "file_path": "results/Pyramids Training/Pyramids.onnx",
+            "reward": null,
+            "creation_time": 1765610801.868744,
+            "auxillary_file_paths": [
+                "results/Pyramids Training/Pyramids/Pyramids-1000042.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "1.2.0.dev0",
+        "torch_version": "2.8.0+cu128"
+    }
+}