Push ppo-PyramidsRND

Pyramids.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7bd7760f3d559881aa9651d10221e3fc94473e9f00e31296e20b57338574a63
+size 1420238

Pyramids/Pyramids-1499956.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c24d74e4523c2e12d659e747ac731dd80895c3a9be247e863c49e86b6cb0952b
+size 1420238

Pyramids/Pyramids-1499956.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5e029c534bdd215cba5652385a521434ec4b38364b14e2f3027bfbdc98782e8
+size 8656252

Pyramids/Pyramids-1999953.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e11a85795c19630ff29cf4ea1bdc248ee4f218feae8ce6b6731054b761f4e1e3
+size 1420238

Pyramids/Pyramids-1999953.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ae672a2cba0ba717aec9f68b56b832170b55715bd0069a7d17fb4ccb3d1a11a
+size 8656252

Pyramids/Pyramids-2499896.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4d8d78db9b5dfd4a5a11ab2937a270270d14b21690fcf5e97864be9387b8170
+size 1420238

Pyramids/Pyramids-2499896.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8467fbe363f1e5f2e140d4345e25c5755e2cc2fd7ef32f5db507c4068cfd7039
+size 8656252

Pyramids/Pyramids-2999887.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7bd7760f3d559881aa9651d10221e3fc94473e9f00e31296e20b57338574a63
+size 1420238

Pyramids/Pyramids-2999887.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37979629d11ee295b29a2473fa980d1aa987a1b667ff2e81f0f5533b0b914867
+size 8656252

Pyramids/Pyramids-3000015.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7bd7760f3d559881aa9651d10221e3fc94473e9f00e31296e20b57338574a63
+size 1420238

Pyramids/Pyramids-3000015.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54ce19d5d2ab8808c711804a0ea42444edb1ee11f7b2056d3a05a6f5d58e12db
+size 8656252

Pyramids/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:636603173625599fee520eb4b0ee9997696dd06a5122b094264dd6a005b1f3fc
+size 8655778

Pyramids/events.out.tfevents.1722240639.fe3c151aad13.4055.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:439064e93329c5e97321bc9e727ed7277f775b3a43dd2d432564383cf5c1860b
+size 877968

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

config.json

@@ -0,0 +1 @@
+{"default_settings": null, "behaviors": {"Pyramids": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.01, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}, "rnd": {"gamma": 0.99, "strength": 0.01, "network_settings": {"normalize": false, "hidden_units": 64, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0001, "encoding_size": null}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 3000000, "time_horizon": 128, "summary_freq": 30000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./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 +1,367 @@
+Mono path[0] = '/content/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/Managed'
+Mono config path = '/content/ml-agents/training-envs-executables/linux/Pyramids/Pyramids_Data/MonoBleedingEdge/etc'
+Found 1 interfaces on host : 0) 172.28.0.12
+Multi-casting "[IP] 172.28.0.12 [Port] 55257 [Flags] 2 [Guid] 1014602327 [EditorId] 764847374 [Version] 1048832 [Id] LinuxPlayer(13,172.28.0.12) [Debug] 0 [PackageName] LinuxPlayer [ProjectName] UnityEnvironment" to [225.0.0.222:54997]...
+Preloaded 'lib_burst_generated.so'
+Preloaded 'libgrpc_csharp_ext.x64.so'
+PlayerPrefs - Creating folder: /root/.config/unity3d/Unity Technologies
+PlayerPrefs - Creating folder: /root/.config/unity3d/Unity Technologies/UnityEnvironment
+Unable to load player prefs
+Initialize engine version: 2021.3.5f1 (40eb3a945986)
+[Subsystems] Discovering subsystems at path /content/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
+ALSA lib confmisc.c:855:(parse_card) cannot find card '0'
+ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_card_inum returned error: No such file or directory
+ALSA lib confmisc.c:422:(snd_func_concat) error evaluating strings
+ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_concat returned error: No such file or directory
+ALSA lib confmisc.c:1334:(snd_func_refer) error evaluating name
+ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_refer returned error: No such file or directory
+ALSA lib conf.c:5701:(snd_config_expand) Evaluate error: No such file or directory
+ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM default
+FMOD failed to initialize the output device.: "Error initializing output device. " (60)
+Forced to initialize FMOD to to the device driver's system output rate 48000, this may impact performance and/or give inconsistent experiences compared to selected sample rate 48000
+ALSA lib confmisc.c:855:(parse_card) cannot find card '0'
+ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_card_inum returned error: No such file or directory
+ALSA lib confmisc.c:422:(snd_func_concat) error evaluating strings
+ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_concat returned error: No such file or directory
+ALSA lib confmisc.c:1334:(snd_func_refer) error evaluating name
+ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_refer returned error: No such file or directory
+ALSA lib conf.c:5701:(snd_config_expand) Evaluate error: No such file or directory
+ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM default
+FMOD failed to initialize the output device.: "Error initializing output device. " (60)
+FMOD initialized on nosound output
+Begin MonoManager ReloadAssembly
+- Completed reload, in  0.094 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: 0.857337 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]: 8338 frames, [32.0 KB-64.0 KB]: 31148 frames, [64.0 KB-128.0 KB]: 16781 frames, [2.0 MB-4.0 MB]: 1 frames
+      Initial Block Size 4.0 MB
+      Current Block Size 4.0 MB
+      Peak Allocated Bytes 2.0 MB
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 8]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 10]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 4]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 6]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_AUDIO_FMOD mixer 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 1]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 11]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 3]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_BatchDeleteObjects]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_AUDIO_FMOD stream thread]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 2]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 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 251.5 KB
+      Overflow Count 4
+    [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_Profiler.Dispatcher]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 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 6]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 5]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 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 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 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 0.8 KB
+      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]: 55969 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 11181
+    [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
+      Requested Block Size 16.0 MB
+      Peak Block count 3
+      Peak Allocated memory 29.9 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 56268 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 27.4 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]: 56267 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]: 56268 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]: 55969 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]: 56267 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]: 56268 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]: 56268 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]: 56268 frames
+  Requested Block Size 16.0 MB
+  Peak Block count 1
+  Peak Allocated memory 35.2 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":1722245862979,"processId":4136,"allocatedMemory":1980093,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"NewDelete":12801},{"Thread":34740},{"Manager":16203},{"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":3447},{"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": 0.18535521626472473,
+            "min": 0.17403636872768402,
+            "max": 1.4797165393829346,
+            "count": 100
+        },
+        "Pyramids.Policy.Entropy.sum": {
+            "value": 5590.3134765625,
+            "min": 5249.81591796875,
+            "max": 44888.6796875,
+            "count": 100
+        },
+        "Pyramids.Step.mean": {
+            "value": 2999887.0,
+            "min": 29922.0,
+            "max": 2999887.0,
+            "count": 100
+        },
+        "Pyramids.Step.sum": {
+            "value": 2999887.0,
+            "min": 29922.0,
+            "max": 2999887.0,
+            "count": 100
+        },
+        "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 0.8328748345375061,
+            "min": -0.1038481667637825,
+            "max": 0.9149202704429626,
+            "count": 100
+        },
+        "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 247.36383056640625,
+            "min": -25.131256103515625,
+            "max": 287.28497314453125,
+            "count": 100
+        },
+        "Pyramids.Policy.RndValueEstimate.mean": {
+            "value": 0.014337725937366486,
+            "min": -0.06541164219379425,
+            "max": 0.35815566778182983,
+            "count": 100
+        },
+        "Pyramids.Policy.RndValueEstimate.sum": {
+            "value": 4.258304595947266,
+            "min": -17.661144256591797,
+            "max": 84.88289642333984,
+            "count": 100
+        },
+        "Pyramids.Losses.PolicyLoss.mean": {
+            "value": 0.07103111432565473,
+            "min": 0.06337840792613596,
+            "max": 0.07297746869827175,
+            "count": 100
+        },
+        "Pyramids.Losses.PolicyLoss.sum": {
+            "value": 1.065466714884821,
+            "min": 0.5108422808879023,
+            "max": 1.0730015888533957,
+            "count": 100
+        },
+        "Pyramids.Losses.ValueLoss.mean": {
+            "value": 0.013715189750636533,
+            "min": 0.00026187829616438767,
+            "max": 0.017055366827471437,
+            "count": 100
+        },
+        "Pyramids.Losses.ValueLoss.sum": {
+            "value": 0.205727846259548,
+            "min": 0.003142539553972652,
+            "max": 0.23877513558460015,
+            "count": 100
+        },
+        "Pyramids.Policy.LearningRate.mean": {
+            "value": 1.519166160311104e-06,
+            "min": 1.519166160311104e-06,
+            "max": 0.0002984114005295333,
+            "count": 100
+        },
+        "Pyramids.Policy.LearningRate.sum": {
+            "value": 2.278749240466656e-05,
+            "min": 2.278749240466656e-05,
+            "max": 0.0039695695768101665,
+            "count": 100
+        },
+        "Pyramids.Policy.Epsilon.mean": {
+            "value": 0.10050635555555557,
+            "min": 0.10050635555555557,
+            "max": 0.19947046666666668,
+            "count": 100
+        },
+        "Pyramids.Policy.Epsilon.sum": {
+            "value": 1.5075953333333334,
+            "min": 1.3962932666666668,
+            "max": 2.8124718666666673,
+            "count": 100
+        },
+        "Pyramids.Policy.Beta.mean": {
+            "value": 6.0584919999999754e-05,
+            "min": 6.0584919999999754e-05,
+            "max": 0.009947099619999998,
+            "count": 100
+        },
+        "Pyramids.Policy.Beta.sum": {
+            "value": 0.0009087737999999964,
+            "min": 0.0009087737999999964,
+            "max": 0.13232666434999998,
+            "count": 100
+        },
+        "Pyramids.Losses.RNDLoss.mean": {
+            "value": 0.0063836174085736275,
+            "min": 0.006180214695632458,
+            "max": 0.3896730840206146,
+            "count": 100
+        },
+        "Pyramids.Losses.RNDLoss.sum": {
+            "value": 0.09575425833463669,
+            "min": 0.08652300387620926,
+            "max": 2.7277116775512695,
+            "count": 100
+        },
+        "Pyramids.Environment.EpisodeLength.mean": {
+            "value": 221.85714285714286,
+            "min": 196.81045751633988,
+            "max": 999.0,
+            "count": 100
+        },
+        "Pyramids.Environment.EpisodeLength.sum": {
+            "value": 27954.0,
+            "min": 16721.0,
+            "max": 32323.0,
+            "count": 100
+        },
+        "Pyramids.Environment.CumulativeReward.mean": {
+            "value": 1.7465763624141535,
+            "min": -0.999903277524056,
+            "max": 1.7946824220990814,
+            "count": 100
+        },
+        "Pyramids.Environment.CumulativeReward.sum": {
+            "value": 221.8151980265975,
+            "min": -30.997001603245735,
+            "max": 273.873198479414,
+            "count": 100
+        },
+        "Pyramids.Policy.ExtrinsicReward.mean": {
+            "value": 1.7465763624141535,
+            "min": -0.999903277524056,
+            "max": 1.7946824220990814,
+            "count": 100
+        },
+        "Pyramids.Policy.ExtrinsicReward.sum": {
+            "value": 221.8151980265975,
+            "min": -30.997001603245735,
+            "max": 273.873198479414,
+            "count": 100
+        },
+        "Pyramids.Policy.RndReward.mean": {
+            "value": 0.01449265299299269,
+            "min": 0.013690494294619613,
+            "max": 7.311247367192717,
+            "count": 100
+        },
+        "Pyramids.Policy.RndReward.sum": {
+            "value": 1.8405669301100716,
+            "min": 1.8405669301100716,
+            "max": 124.29120524227619,
+            "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": "1722240639",
+        "python_version": "3.10.12 (main, Mar 22 2024, 16:50:05) [GCC 11.4.0]",
+        "command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics",
+        "mlagents_version": "1.1.0.dev0",
+        "mlagents_envs_version": "1.1.0.dev0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "2.3.1+cu121",
+        "numpy_version": "1.23.5",
+        "end_time_seconds": "1722245863"
+    },
+    "total": 5223.930010196001,
+    "count": 1,
+    "self": 0.3725842540006852,
+    "children": {
+        "run_training.setup": {
+            "total": 0.05449650799994288,
+            "count": 1,
+            "self": 0.05449650799994288
+        },
+        "TrainerController.start_learning": {
+            "total": 5223.502929434,
+            "count": 1,
+            "self": 4.22077262915991,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 2.0454575560000876,
+                    "count": 1,
+                    "self": 2.0454575560000876
+                },
+                "TrainerController.advance": {
+                    "total": 5217.149424316841,
+                    "count": 195608,
+                    "self": 4.059529022582865,
+                    "children": {
+                        "env_step": {
+                            "total": 3460.5996767411093,
+                            "count": 195608,
+                            "self": 3082.0289851512716,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 375.96389581699225,
+                                    "count": 195608,
+                                    "self": 13.558149060980782,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 362.40574675601147,
+                                            "count": 187559,
+                                            "self": 362.40574675601147
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 2.6067957728456577,
+                                    "count": 195608,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 5216.689421653077,
+                                            "count": 195608,
+                                            "is_parallel": true,
+                                            "self": 2441.499131032131,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.0020848729999443094,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.000647403999778362,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.0014374690001659474,
+                                                                    "count": 8,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0014374690001659474
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.03822499900002185,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.00044477200003711914,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.00033218499993381556,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00033218499993381556
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.03629049100004522,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.03629049100004522
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.0011575510000056966,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00026954099996601144,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.0008880100000396851,
+                                                                            "count": 8,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.0008880100000396851
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 2775.190290620946,
+                                                    "count": 195607,
+                                                    "is_parallel": true,
+                                                    "self": 68.2026290299359,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 42.8606724801208,
+                                                            "count": 195607,
+                                                            "is_parallel": true,
+                                                            "self": 42.8606724801208
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 2470.3606953088242,
+                                                            "count": 195607,
+                                                            "is_parallel": true,
+                                                            "self": 2470.3606953088242
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 193.76629380206532,
+                                                            "count": 195607,
+                                                            "is_parallel": true,
+                                                            "self": 42.12759774883557,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 151.63869605322975,
+                                                                    "count": 1564856,
+                                                                    "is_parallel": true,
+                                                                    "self": 151.63869605322975
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 1752.4902185531487,
+                            "count": 195608,
+                            "self": 8.561444220089697,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 359.38304962905727,
+                                    "count": 195608,
+                                    "self": 358.8474447750573,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 0.5356048539999847,
+                                            "count": 6,
+                                            "self": 0.5356048539999847
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 1384.5457247040017,
+                                    "count": 1402,
+                                    "self": 820.6991755719698,
+                                    "children": {
+                                        "TorchPPOOptimizer.update": {
+                                            "total": 563.8465491320319,
+                                            "count": 68394,
+                                            "self": 563.8465491320319
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 1.1339998309267685e-06,
+                    "count": 1,
+                    "self": 1.1339998309267685e-06
+                },
+                "TrainerController._save_models": {
+                    "total": 0.08727379799984192,
+                    "count": 1,
+                    "self": 0.0015812700003152713,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.08569252799952665,
+                            "count": 1,
+                            "self": 0.08569252799952665
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,65 @@
+{
+    "Pyramids": {
+        "checkpoints": [
+            {
+                "steps": 1499956,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1499956.onnx",
+                "reward": 1.7122222152021196,
+                "creation_time": 1722243178.895838,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-1499956.pt"
+                ]
+            },
+            {
+                "steps": 1999953,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1999953.onnx",
+                "reward": 1.7682856832231795,
+                "creation_time": 1722244076.4197812,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-1999953.pt"
+                ]
+            },
+            {
+                "steps": 2499896,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-2499896.onnx",
+                "reward": 1.5819999665021895,
+                "creation_time": 1722244978.9291039,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-2499896.pt"
+                ]
+            },
+            {
+                "steps": 2999887,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-2999887.onnx",
+                "reward": 1.7115000188350677,
+                "creation_time": 1722245862.567703,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-2999887.pt"
+                ]
+            },
+            {
+                "steps": 3000015,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-3000015.onnx",
+                "reward": 1.7115000188350677,
+                "creation_time": 1722245862.6660206,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-3000015.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 3000015,
+            "file_path": "results/Pyramids Training/Pyramids.onnx",
+            "reward": 1.7115000188350677,
+            "creation_time": 1722245862.6660206,
+            "auxillary_file_paths": [
+                "results/Pyramids Training/Pyramids/Pyramids-3000015.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "1.1.0.dev0",
+        "torch_version": "2.3.1+cu121"
+    }
+}