First Push

Pyramids.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5266d129a2aa14f9a83e950c816d5312d1eaece9e74fb49a86c0712d69132182
+size 1420238

Pyramids/Pyramids-1499967.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5af4cac094cbc88abf43134684b146b18f0ae99258c81ee6909a9a932cdc62c1
+size 1420238

Pyramids/Pyramids-1499967.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2b744361fe6eb2442bec7420a11e010ff7c738cbbc450043eabd3c07696c6cd
+size 8655228

Pyramids/Pyramids-1999875.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:947d4e2cabb13f590af8738260b9158ca98cb7299eb37a8611e4478abafdb893
+size 1420238

Pyramids/Pyramids-1999875.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4766d4863892d3973d220fdb1fc4b74cbe302b08c72a4c8f8ffb6567c34df75
+size 8655228

Pyramids/Pyramids-2499913.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab677f0ff6ec67ab8ec421cbff11879b3696ef3ac1840b07eb9deaea12797d05
+size 1420238

Pyramids/Pyramids-2499913.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0a0c2c4b3481149f82703793b3bcbf9e6c90fb2e1b8af373492d07163c84f53
+size 8655228

Pyramids/Pyramids-2999968.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5266d129a2aa14f9a83e950c816d5312d1eaece9e74fb49a86c0712d69132182
+size 1420238

Pyramids/Pyramids-2999968.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:749fb44424a24e50bb8afa094aba93884012bc9285edef04c144910ed5128cec
+size 8655228

Pyramids/Pyramids-3000096.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5266d129a2aa14f9a83e950c816d5312d1eaece9e74fb49a86c0712d69132182
+size 1420238

Pyramids/Pyramids-3000096.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7ae45adc76f41abaf7ddaae1141fa105b97850ab283f3db7273c4cfa71c8fa9
+size 8655228

Pyramids/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:784fce1378e1fbea3d33b0dea2d8af945503fb900f3ccb15eec7ffcea40dc8d7
+size 8654754

Pyramids/events.out.tfevents.1693497344.yaohua-NUC12DCMi7.19861.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8eab761f71d82ed459ba5039621f5dc15886e5ff95fa732576db679f4f580009
+size 933817

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: yaohuacn/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, "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}, "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 +1,90 @@
+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
+  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
+environment_parameters: null
+checkpoint_settings:
+  run_id: Pyramids Training
+  initialize_from: null
+  load_model: false
+  resume: false
+  force: false
+  train_model: false
+  inference: false
+  results_dir: results
+torch_settings:
+  device: null
+debug: false

run_logs/Player-0.log

@@ -0,0 +1,387 @@
+Mono path[0] = '/home/yaohua/CODING/DRL/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/Managed'
+Mono config path = '/home/yaohua/CODING/DRL/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/MonoBleedingEdge/etc'
+Found 3 interfaces on host : 0) 192.168.3.23 1) 172.18.0.1 2) 172.17.0.1
+Multi-casting "[IP] 192.168.3.23 [Port] 55143 [Flags] 2 [Guid] 219796881 [EditorId] 764847374 [Version] 1048832 [Id] LinuxPlayer(13,192.168.3.23) [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/yaohua/.config/unity3d/Unity Technologies
+PlayerPrefs - Creating folder: /home/yaohua/.config/unity3d/Unity Technologies/UnityEnvironment
+Unable to load player prefs
+Initialize engine version: 2021.3.5f1 (40eb3a945986)
+[Subsystems] Discovering subsystems at path /home/yaohua/CODING/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  0.047 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: 0.592744 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]: 11225 frames, [32.0 KB-64.0 KB]: 29710 frames, [64.0 KB-128.0 KB]: 15333 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 17]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 3]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Profiler.Dispatcher]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 3.8 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 14]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 5]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 13]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 2]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 11]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 0]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 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 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 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 128 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 10]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 16]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 6]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 1]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_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]: 55970 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 12321
+    [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]: 56267 frames, [32.0 MB-64.0 MB]: 1 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 3
+      Peak Allocated memory 32.4 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 56269 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 28.0 MB
+      Peak Large allocation bytes 16.0 MB
+[ALLOC_TEMP_JOB_1_FRAME]
+  Initial Block Size 2.0 MB
+  Used Block Count 1
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_TEMP_JOB_2_FRAMES]
+  Initial Block Size 2.0 MB
+  Used Block Count 1
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_TEMP_JOB_4_FRAMES (JobTemp)]
+  Initial Block Size 2.0 MB
+  Used Block Count 2
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_TEMP_JOB_ASYNC (Background)]
+  Initial Block Size 1.0 MB
+  Used Block Count 3
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_GFX] Dual Thread Allocator
+  Peak main deferred allocation count 0
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 1.7 MB
+    [ALLOC_GFX_MAIN]
+      Peak usage frame count: [32.0 KB-64.0 KB]: 56268 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]: 56269 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]: 55970 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]: 56268 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]: 56269 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]: 56269 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]: 56269 frames
+  Requested Block Size 16.0 MB
+  Peak Block count 1
+  Peak Allocated memory 43.8 KB
+  Peak Large allocation bytes 0 B
+    [ALLOC_PROFILER_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 396 B
+##utp:{"type":"MemoryLeaks","version":2,"phase":"Immediate","time":1693500008133,"processId":19928,"allocatedMemory":1994290,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"NewDelete":12801},{"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":3528},{"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": 0.16162443161010742,
+            "min": 0.15789465606212616,
+            "max": 1.5367339849472046,
+            "count": 100
+        },
+        "Pyramids.Policy.Entropy.sum": {
+            "value": 4869.4208984375,
+            "min": 4754.52392578125,
+            "max": 46618.36328125,
+            "count": 100
+        },
+        "Pyramids.Step.mean": {
+            "value": 2999968.0,
+            "min": 29952.0,
+            "max": 2999968.0,
+            "count": 100
+        },
+        "Pyramids.Step.sum": {
+            "value": 2999968.0,
+            "min": 29952.0,
+            "max": 2999968.0,
+            "count": 100
+        },
+        "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 0.8118285536766052,
+            "min": -0.11502286791801453,
+            "max": 0.8630164861679077,
+            "count": 100
+        },
+        "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 243.54856872558594,
+            "min": -27.835533142089844,
+            "max": 258.9049377441406,
+            "count": 100
+        },
+        "Pyramids.Policy.RndValueEstimate.mean": {
+            "value": -0.022703945636749268,
+            "min": -0.04616357758641243,
+            "max": 0.20310497283935547,
+            "count": 100
+        },
+        "Pyramids.Policy.RndValueEstimate.sum": {
+            "value": -6.811183929443359,
+            "min": -13.110455513000488,
+            "max": 48.74519348144531,
+            "count": 100
+        },
+        "Pyramids.Losses.PolicyLoss.mean": {
+            "value": 0.06751976936218507,
+            "min": 0.06459627301678882,
+            "max": 0.07357598580176397,
+            "count": 100
+        },
+        "Pyramids.Losses.PolicyLoss.sum": {
+            "value": 0.9452767710705909,
+            "min": 0.494947158982248,
+            "max": 1.0926436143744664,
+            "count": 100
+        },
+        "Pyramids.Losses.ValueLoss.mean": {
+            "value": 0.011672002123391612,
+            "min": 0.0007036268415791142,
+            "max": 0.016515563614006124,
+            "count": 100
+        },
+        "Pyramids.Losses.ValueLoss.sum": {
+            "value": 0.16340802972748256,
+            "min": 0.00767740097599644,
+            "max": 0.2316692368137107,
+            "count": 100
+        },
+        "Pyramids.Policy.LearningRate.mean": {
+            "value": 1.4294352378404776e-06,
+            "min": 1.4294352378404776e-06,
+            "max": 0.00029838354339596195,
+            "count": 100
+        },
+        "Pyramids.Policy.LearningRate.sum": {
+            "value": 2.0012093329766686e-05,
+            "min": 2.0012093329766686e-05,
+            "max": 0.003927291590902833,
+            "count": 100
+        },
+        "Pyramids.Policy.Epsilon.mean": {
+            "value": 0.10047644523809525,
+            "min": 0.10047644523809525,
+            "max": 0.19946118095238097,
+            "count": 100
+        },
+        "Pyramids.Policy.Epsilon.sum": {
+            "value": 1.4066702333333334,
+            "min": 1.3897045333333333,
+            "max": 2.7674720000000006,
+            "count": 100
+        },
+        "Pyramids.Policy.Beta.mean": {
+            "value": 5.759687928571435e-05,
+            "min": 5.759687928571435e-05,
+            "max": 0.009946171977142856,
+            "count": 100
+        },
+        "Pyramids.Policy.Beta.sum": {
+            "value": 0.0008063563100000009,
+            "min": 0.0008063563100000009,
+            "max": 0.13091880695000002,
+            "count": 100
+        },
+        "Pyramids.Losses.RNDLoss.mean": {
+            "value": 0.005666096694767475,
+            "min": 0.005666096694767475,
+            "max": 0.3774621784687042,
+            "count": 100
+        },
+        "Pyramids.Losses.RNDLoss.sum": {
+            "value": 0.0793253555893898,
+            "min": 0.0793253555893898,
+            "max": 2.642235279083252,
+            "count": 100
+        },
+        "Pyramids.Environment.EpisodeLength.mean": {
+            "value": 214.74436090225564,
+            "min": 214.74436090225564,
+            "max": 999.0,
+            "count": 100
+        },
+        "Pyramids.Environment.EpisodeLength.sum": {
+            "value": 28561.0,
+            "min": 15984.0,
+            "max": 34359.0,
+            "count": 100
+        },
+        "Pyramids.Environment.CumulativeReward.mean": {
+            "value": 1.7551669014015592,
+            "min": -1.0000000521540642,
+            "max": 1.7694384534771626,
+            "count": 100
+        },
+        "Pyramids.Environment.CumulativeReward.sum": {
+            "value": 233.43719788640738,
+            "min": -32.000001668930054,
+            "max": 237.95739808678627,
+            "count": 100
+        },
+        "Pyramids.Policy.ExtrinsicReward.mean": {
+            "value": 1.7551669014015592,
+            "min": -1.0000000521540642,
+            "max": 1.7694384534771626,
+            "count": 100
+        },
+        "Pyramids.Policy.ExtrinsicReward.sum": {
+            "value": 233.43719788640738,
+            "min": -32.000001668930054,
+            "max": 237.95739808678627,
+            "count": 100
+        },
+        "Pyramids.Policy.RndReward.mean": {
+            "value": 0.012531701085379581,
+            "min": 0.012531701085379581,
+            "max": 7.303899978287518,
+            "count": 100
+        },
+        "Pyramids.Policy.RndReward.sum": {
+            "value": 1.6667162443554844,
+            "min": 1.6667162443554844,
+            "max": 116.86239965260029,
+            "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": "1693497343",
+        "python_version": "3.10.12 (main, Jul  5 2023, 18:54:27) [GCC 11.2.0]",
+        "command_line_arguments": "/home/yaohua/miniconda3/envs/drl/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics",
+        "mlagents_version": "0.31.0.dev0",
+        "mlagents_envs_version": "0.31.0.dev0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "2.1.0.dev20230830",
+        "numpy_version": "1.21.2",
+        "end_time_seconds": "1693500008"
+    },
+    "total": 2664.4789828110006,
+    "count": 1,
+    "self": 0.21767440300209273,
+    "children": {
+        "run_training.setup": {
+            "total": 0.011569790998692042,
+            "count": 1,
+            "self": 0.011569790998692042
+        },
+        "TrainerController.start_learning": {
+            "total": 2664.249738617,
+            "count": 1,
+            "self": 3.3313670061725134,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 1.0220517290017597,
+                    "count": 1,
+                    "self": 1.0220517290017597
+                },
+                "TrainerController.advance": {
+                    "total": 2659.864983788828,
+                    "count": 194780,
+                    "self": 2.862759061896213,
+                    "children": {
+                        "env_step": {
+                            "total": 1742.7104669646633,
+                            "count": 194780,
+                            "self": 1573.8326645859033,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 166.86263520575085,
+                                    "count": 194780,
+                                    "self": 8.07827265209744,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 158.7843625536534,
+                                            "count": 187562,
+                                            "self": 158.7843625536534
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 2.015167173009104,
+                                    "count": 194780,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 2660.5570696709274,
+                                            "count": 194780,
+                                            "is_parallel": true,
+                                            "self": 1266.3296328622127,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.0008461830002488568,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.00025939800252672285,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.000586784997722134,
+                                                                    "count": 8,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.000586784997722134
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.019954175000748364,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.00018957599968416616,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.00017926000145962462,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00017926000145962462
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.018965930999911507,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.018965930999911507
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.0006194079996930668,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0002009269992413465,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.0004184810004517203,
+                                                                            "count": 8,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.0004184810004517203
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 1394.2274368087146,
+                                                    "count": 194779,
+                                                    "is_parallel": true,
+                                                    "self": 34.919017709424224,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 22.9513969758882,
+                                                            "count": 194779,
+                                                            "is_parallel": true,
+                                                            "self": 22.9513969758882
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 1236.4488385992954,
+                                                            "count": 194779,
+                                                            "is_parallel": true,
+                                                            "self": 1236.4488385992954
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 99.90818352410679,
+                                                            "count": 194779,
+                                                            "is_parallel": true,
+                                                            "self": 23.39289753889898,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 76.51528598520781,
+                                                                    "count": 1558232,
+                                                                    "is_parallel": true,
+                                                                    "self": 76.51528598520781
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 914.2917577622684,
+                            "count": 194780,
+                            "self": 6.194111263965169,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 171.4765753683223,
+                                    "count": 194780,
+                                    "self": 171.29447548532335,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 0.18209988299895485,
+                                            "count": 6,
+                                            "self": 0.18209988299895485
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 736.6210711299809,
+                                    "count": 1392,
+                                    "self": 414.6348139058009,
+                                    "children": {
+                                        "TorchPPOOptimizer.update": {
+                                            "total": 321.98625722418,
+                                            "count": 68442,
+                                            "self": 321.98625722418
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 5.319998308550566e-07,
+                    "count": 1,
+                    "self": 5.319998308550566e-07
+                },
+                "TrainerController._save_models": {
+                    "total": 0.031335560997831635,
+                    "count": 1,
+                    "self": 0.00083905099745607,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.030496510000375565,
+                            "count": 1,
+                            "self": 0.030496510000375565
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,65 @@
+{
+    "Pyramids": {
+        "checkpoints": [
+            {
+                "steps": 1499967,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1499967.onnx",
+                "reward": 1.622000016272068,
+                "creation_time": 1693498578.018935,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-1499967.pt"
+                ]
+            },
+            {
+                "steps": 1999875,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1999875.onnx",
+                "reward": null,
+                "creation_time": 1693499014.9808686,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-1999875.pt"
+                ]
+            },
+            {
+                "steps": 2499913,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-2499913.onnx",
+                "reward": null,
+                "creation_time": 1693499511.4924798,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-2499913.pt"
+                ]
+            },
+            {
+                "steps": 2999968,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-2999968.onnx",
+                "reward": 1.756999984383583,
+                "creation_time": 1693500007.9153824,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-2999968.pt"
+                ]
+            },
+            {
+                "steps": 3000096,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-3000096.onnx",
+                "reward": 1.756999984383583,
+                "creation_time": 1693500007.9528816,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-3000096.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 3000096,
+            "file_path": "results/Pyramids Training/Pyramids.onnx",
+            "reward": 1.756999984383583,
+            "creation_time": 1693500007.9528816,
+            "auxillary_file_paths": [
+                "results/Pyramids Training/Pyramids/Pyramids-3000096.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "0.31.0.dev0",
+        "torch_version": "2.1.0.dev20230830"
+    }
+}