First Push

Pyramids.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04d29183db860195ccc7919ce377757aa38fee962b5520b0450fb7e05c114361
+size 1420238

Pyramids/Pyramids-1499941.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53724c40a640abd99025a90031d417421056a1f6781d3a0153e0e300e4b16626
+size 1420238

Pyramids/Pyramids-1499941.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:359d3b94cd248b10bbe448cdc987416305fbc6e82586726198da1df7fa6fecda
+size 8656252

Pyramids/Pyramids-1999994.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11af29fef9a1c2893434f99c7dd127e9b044c243a969cbf46e1f8d63a12104de
+size 1420238

Pyramids/Pyramids-1999994.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2333f41639c7ce3b884a7273e6874c446d0175ab77ba072da85ed13791704519
+size 8656252

Pyramids/Pyramids-2499928.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f89a235d6ca08c1950b35c554fea98757462bff9bbb8c10f3ae9611081bfb35
+size 1420238

Pyramids/Pyramids-2499928.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2bcbc48071c2433d17626292813384ddedeab7748855397eab1ad9b5d6dca63
+size 8656252

Pyramids/Pyramids-2999996.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04d29183db860195ccc7919ce377757aa38fee962b5520b0450fb7e05c114361
+size 1420238

Pyramids/Pyramids-2999996.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1de1960ddafa480d7941b742d4da75d168784aa845f342a8d71dcf235649f72
+size 8656252

Pyramids/Pyramids-3000124.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04d29183db860195ccc7919ce377757aa38fee962b5520b0450fb7e05c114361
+size 1420238

Pyramids/Pyramids-3000124.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c46212527b088d4c09b929615a9a81e306feb90ab6fa55c9ddd2ca961aec0210
+size 8656252

Pyramids/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d014a1b53a0119a411e98982d9f16f2c1ef3e374ce6e001d199c2981dbf677b
+size 8655778

Pyramids/events.out.tfevents.1745310503.ippc-zq-System-Product-Name.1561030.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9fdadb1fac595a39485c46365016f45eedcc38745ff3f13975ffeaef6df071e
+size 998756

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: DengJunTTT/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": 3000000, "time_horizon": 128, "summary_freq": 30000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/Pyramids/Pyramids", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "Pyramids Training", "initialize_from": null, "load_model": false, "resume": false, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -0,0 +1,92 @@
+default_settings: null
+behaviors:
+  Pyramids:
+    trainer_type: ppo
+    hyperparameters:
+      batch_size: 128
+      buffer_size: 2048
+      learning_rate: 0.0003
+      beta: 0.01
+      epsilon: 0.2
+      lambd: 0.95
+      num_epoch: 3
+      shared_critic: false
+      learning_rate_schedule: linear
+      beta_schedule: linear
+      epsilon_schedule: linear
+    checkpoint_interval: 500000
+    network_settings:
+      normalize: false
+      hidden_units: 512
+      num_layers: 2
+      vis_encode_type: simple
+      memory: null
+      goal_conditioning_type: hyper
+      deterministic: false
+    reward_signals:
+      extrinsic:
+        gamma: 0.99
+        strength: 1.0
+        network_settings:
+          normalize: false
+          hidden_units: 128
+          num_layers: 2
+          vis_encode_type: simple
+          memory: null
+          goal_conditioning_type: hyper
+          deterministic: false
+      rnd:
+        gamma: 0.99
+        strength: 0.01
+        network_settings:
+          normalize: false
+          hidden_units: 64
+          num_layers: 3
+          vis_encode_type: simple
+          memory: null
+          goal_conditioning_type: hyper
+          deterministic: false
+        learning_rate: 0.0001
+        encoding_size: null
+    init_path: null
+    keep_checkpoints: 5
+    even_checkpoints: false
+    max_steps: 3000000
+    time_horizon: 128
+    summary_freq: 30000
+    threaded: false
+    self_play: null
+    behavioral_cloning: null
+env_settings:
+  env_path: ./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 +1,347 @@
+Mono path[0] = '/home/ippc-zq/DenJun/DengJun/hf_drl/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/Managed'
+Mono config path = '/home/ippc-zq/DenJun/DengJun/hf_drl/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/MonoBleedingEdge/etc'
+Found 1 interfaces on host : 0) 192.168.7.137
+Multi-casting "[IP] 192.168.7.137 [Port] 55151 [Flags] 2 [Guid] 337847989 [EditorId] 764847374 [Version] 1048832 [Id] LinuxPlayer(13,192.168.7.137) [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/ippc-zq/.config/unity3d/Unity Technologies
+PlayerPrefs - Creating folder: /home/ippc-zq/.config/unity3d/Unity Technologies/UnityEnvironment
+Unable to load player prefs
+Initialize engine version: 2021.3.5f1 (40eb3a945986)
+[Subsystems] Discovering subsystems at path /home/ippc-zq/DenJun/DengJun/hf_drl/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  0.076 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: 0.512000 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 6 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]: 3392 frames, [32.0 KB-64.0 KB]: 38411 frames, [64.0 KB-128.0 KB]: 14466 frames, [2.0 MB-4.0 MB]: 1 frames
+      Initial Block Size 4.0 MB
+      Current Block Size 4.0 MB
+      Peak Allocated Bytes 2.0 MB
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 8]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 10]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 4]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0.8 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 6]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 1]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 11]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 3]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_BatchDeleteObjects]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_AUDIO_FMOD stream thread]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 15]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 7]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 8]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 1]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 10]
+      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_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_AUDIO_FMOD PulseAudio Mixer]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Profiler.Dispatcher]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 1.9 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 3]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 12]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_AssetGarbageCollectorHelper] x 11
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 5]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 13]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 2]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 0]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 4]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 0]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 5]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 14]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 6]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_EnlightenWorker] x 6
+      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_Job.Worker 7]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Loading.AsyncRead]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 128 B
+      Overflow Count 0
+[ALLOC_MEMORYPROFILER]
+  Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 55971 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 12185
+    [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]: 56269 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 3
+      Peak Allocated memory 30.9 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 56270 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 26.7 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]: 56269 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]: 56270 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]: 55971 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]: 56269 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]: 56270 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]: 56270 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]: 56270 frames
+  Requested Block Size 16.0 MB
+  Peak Block count 1
+  Peak Allocated memory 34.7 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":1745312942614,"processId":1561055,"allocatedMemory":1980216,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"NewDelete":12801},{"Thread":34740},{"Manager":16207},{"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":3566},{"DynamicArray":30868},{"HashMap":7680},{"Utility":5440},{"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": 0.13707095384597778,
+            "min": 0.11631232500076294,
+            "max": 1.4741979837417603,
+            "count": 100
+        },
+        "Pyramids.Policy.Entropy.sum": {
+            "value": 4153.79833984375,
+            "min": 3454.0107421875,
+            "max": 44721.26953125,
+            "count": 100
+        },
+        "Pyramids.Step.mean": {
+            "value": 2999996.0,
+            "min": 29952.0,
+            "max": 2999996.0,
+            "count": 100
+        },
+        "Pyramids.Step.sum": {
+            "value": 2999996.0,
+            "min": 29952.0,
+            "max": 2999996.0,
+            "count": 100
+        },
+        "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 0.7104477882385254,
+            "min": -0.13911187648773193,
+            "max": 0.734244167804718,
+            "count": 100
+        },
+        "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 209.58209228515625,
+            "min": -33.525962829589844,
+            "max": 214.3992919921875,
+            "count": 100
+        },
+        "Pyramids.Policy.RndValueEstimate.mean": {
+            "value": 0.004477185662835836,
+            "min": -0.07881761342287064,
+            "max": 0.3197421431541443,
+            "count": 100
+        },
+        "Pyramids.Policy.RndValueEstimate.sum": {
+            "value": 1.3207697868347168,
+            "min": -21.359573364257812,
+            "max": 75.77888488769531,
+            "count": 100
+        },
+        "Pyramids.Losses.PolicyLoss.mean": {
+            "value": 0.06738436084508508,
+            "min": 0.06221204199846143,
+            "max": 0.07443871274180881,
+            "count": 100
+        },
+        "Pyramids.Losses.PolicyLoss.sum": {
+            "value": 1.0107654126762762,
+            "min": 0.5201176695916039,
+            "max": 1.0771193681353264,
+            "count": 100
+        },
+        "Pyramids.Losses.ValueLoss.mean": {
+            "value": 0.01687649020307326,
+            "min": 7.539750213428352e-05,
+            "max": 0.01729370055926709,
+            "count": 100
+        },
+        "Pyramids.Losses.ValueLoss.sum": {
+            "value": 0.2531473530460989,
+            "min": 0.0009801675277456858,
+            "max": 0.2564206355697631,
+            "count": 100
+        },
+        "Pyramids.Policy.LearningRate.mean": {
+            "value": 1.4963728345755552e-06,
+            "min": 1.4963728345755552e-06,
+            "max": 0.00029838354339596195,
+            "count": 100
+        },
+        "Pyramids.Policy.LearningRate.sum": {
+            "value": 2.244559251863333e-05,
+            "min": 2.244559251863333e-05,
+            "max": 0.0037577675474109,
+            "count": 100
+        },
+        "Pyramids.Policy.Epsilon.mean": {
+            "value": 0.1004987577777778,
+            "min": 0.1004987577777778,
+            "max": 0.19946118095238097,
+            "count": 100
+        },
+        "Pyramids.Policy.Epsilon.sum": {
+            "value": 1.5074813666666669,
+            "min": 1.3962282666666668,
+            "max": 2.7525891000000007,
+            "count": 100
+        },
+        "Pyramids.Policy.Beta.mean": {
+            "value": 5.9825902000000005e-05,
+            "min": 5.9825902000000005e-05,
+            "max": 0.009946171977142856,
+            "count": 100
+        },
+        "Pyramids.Policy.Beta.sum": {
+            "value": 0.0008973885300000001,
+            "min": 0.0008973885300000001,
+            "max": 0.12528365109,
+            "count": 100
+        },
+        "Pyramids.Losses.RNDLoss.mean": {
+            "value": 0.002623029053211212,
+            "min": 0.0022417742293328047,
+            "max": 0.4448506534099579,
+            "count": 100
+        },
+        "Pyramids.Losses.RNDLoss.sum": {
+            "value": 0.03934543579816818,
+            "min": 0.03138484060764313,
+            "max": 3.113954544067383,
+            "count": 100
+        },
+        "Pyramids.Environment.EpisodeLength.mean": {
+            "value": 253.21008403361344,
+            "min": 250.49107142857142,
+            "max": 999.0,
+            "count": 100
+        },
+        "Pyramids.Environment.EpisodeLength.sum": {
+            "value": 30132.0,
+            "min": 15984.0,
+            "max": 33002.0,
+            "count": 100
+        },
+        "Pyramids.Environment.CumulativeReward.mean": {
+            "value": 1.6973299836119016,
+            "min": -1.0000000521540642,
+            "max": 1.7133405248861056,
+            "count": 100
+        },
+        "Pyramids.Environment.CumulativeReward.sum": {
+            "value": 203.6795980334282,
+            "min": -32.000001668930054,
+            "max": 203.6795980334282,
+            "count": 100
+        },
+        "Pyramids.Policy.ExtrinsicReward.mean": {
+            "value": 1.6973299836119016,
+            "min": -1.0000000521540642,
+            "max": 1.7133405248861056,
+            "count": 100
+        },
+        "Pyramids.Policy.ExtrinsicReward.sum": {
+            "value": 203.6795980334282,
+            "min": -32.000001668930054,
+            "max": 203.6795980334282,
+            "count": 100
+        },
+        "Pyramids.Policy.RndReward.mean": {
+            "value": 0.006939750808578537,
+            "min": 0.00658107829778081,
+            "max": 10.403893576003611,
+            "count": 100
+        },
+        "Pyramids.Policy.RndReward.sum": {
+            "value": 0.8327700970294245,
+            "min": 0.7083868069839809,
+            "max": 166.46229721605778,
+            "count": 100
+        },
+        "Pyramids.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 100
+        },
+        "Pyramids.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 100
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1745310503",
+        "python_version": "3.10.12 | packaged by conda-forge | (main, Jun 23 2023, 22:40:32) [GCC 12.3.0]",
+        "command_line_arguments": "/home/ippc-zq/miniconda3/envs/hf_drl/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": "2.6.0+cu124",
+        "numpy_version": "1.23.5",
+        "end_time_seconds": "1745312942"
+    },
+    "total": 2439.341082864441,
+    "count": 1,
+    "self": 0.21803830564022064,
+    "children": {
+        "run_training.setup": {
+            "total": 0.015170782804489136,
+            "count": 1,
+            "self": 0.015170782804489136
+        },
+        "TrainerController.start_learning": {
+            "total": 2439.1078737759963,
+            "count": 1,
+            "self": 1.702069528400898,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 1.4264001185074449,
+                    "count": 1,
+                    "self": 1.4264001185074449
+                },
+                "TrainerController.advance": {
+                    "total": 2435.92876159586,
+                    "count": 193379,
+                    "self": 1.7260248772799969,
+                    "children": {
+                        "env_step": {
+                            "total": 1469.2598752379417,
+                            "count": 193379,
+                            "self": 1265.202232089825,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 202.9445812255144,
+                                    "count": 193379,
+                                    "self": 5.794512763619423,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 197.150068461895,
+                                            "count": 187566,
+                                            "self": 197.150068461895
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 1.1130619226023555,
+                                    "count": 193379,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 2436.4521194547415,
+                                            "count": 193379,
+                                            "is_parallel": true,
+                                            "self": 1298.8864110549912,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.0011889347806572914,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.00036335457116365433,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.0008255802094936371,
+                                                                    "count": 8,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0008255802094936371
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.018491373397409916,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.00030610524117946625,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.0002986127510666847,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0002986127510666847
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.01699640415608883,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.01699640415608883
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.0008902512490749359,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00019835308194160461,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.0006918981671333313,
+                                                                            "count": 8,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.0006918981671333313
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 1137.5657083997503,
+                                                    "count": 193378,
+                                                    "is_parallel": true,
+                                                    "self": 33.40197414159775,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 24.14669872354716,
+                                                            "count": 193378,
+                                                            "is_parallel": true,
+                                                            "self": 24.14669872354716
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 983.1190599706024,
+                                                            "count": 193378,
+                                                            "is_parallel": true,
+                                                            "self": 983.1190599706024
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 96.89797556400299,
+                                                            "count": 193378,
+                                                            "is_parallel": true,
+                                                            "self": 21.063353597186506,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 75.83462196681648,
+                                                                    "count": 1547024,
+                                                                    "is_parallel": true,
+                                                                    "self": 75.83462196681648
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 964.9428614806384,
+                            "count": 193379,
+                            "self": 3.6503547243773937,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 189.14197521377355,
+                                    "count": 193379,
+                                    "self": 188.79272856842726,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 0.3492466453462839,
+                                            "count": 6,
+                                            "self": 0.3492466453462839
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 772.1505315424874,
+                                    "count": 1388,
+                                    "self": 422.01692544762045,
+                                    "children": {
+                                        "TorchPPOOptimizer.update": {
+                                            "total": 350.133606094867,
+                                            "count": 68439,
+                                            "self": 350.133606094867
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 5.494803190231323e-07,
+                    "count": 1,
+                    "self": 5.494803190231323e-07
+                },
+                "TrainerController._save_models": {
+                    "total": 0.0506419837474823,
+                    "count": 1,
+                    "self": 0.0010500717908143997,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.0495919119566679,
+                            "count": 1,
+                            "self": 0.0495919119566679
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,65 @@
+{
+    "Pyramids": {
+        "checkpoints": [
+            {
+                "steps": 1499941,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1499941.onnx",
+                "reward": 1.5717500001192093,
+                "creation_time": 1745311690.8873,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-1499941.pt"
+                ]
+            },
+            {
+                "steps": 1999994,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1999994.onnx",
+                "reward": 1.6626666287581127,
+                "creation_time": 1745312104.4972334,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-1999994.pt"
+                ]
+            },
+            {
+                "steps": 2499928,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-2499928.onnx",
+                "reward": 1.8189999759197235,
+                "creation_time": 1745312521.0176418,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-2499928.pt"
+                ]
+            },
+            {
+                "steps": 2999996,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-2999996.onnx",
+                "reward": 1.68299999833107,
+                "creation_time": 1745312942.3674743,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-2999996.pt"
+                ]
+            },
+            {
+                "steps": 3000124,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-3000124.onnx",
+                "reward": 1.68299999833107,
+                "creation_time": 1745312942.4237304,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-3000124.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 3000124,
+            "file_path": "results/Pyramids Training/Pyramids.onnx",
+            "reward": 1.68299999833107,
+            "creation_time": 1745312942.4237304,
+            "auxillary_file_paths": [
+                "results/Pyramids Training/Pyramids/Pyramids-3000124.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "1.2.0.dev0",
+        "torch_version": "2.6.0+cu124"
+    }
+}