First training of Pyramids with PPO

Pyramids.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3395dfc05a3eb245da447c483971f7847b23dc78d8ba60e6d7e23333f993321b
+size 1420238

Pyramids/Pyramids-1000053.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3395dfc05a3eb245da447c483971f7847b23dc78d8ba60e6d7e23333f993321b
+size 1420238

Pyramids/Pyramids-1000053.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad2767f820f58074d6ccc23183524268be17f00b49de10c3d41dd3503272b159
+size 8656252

Pyramids/Pyramids-499925.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed6ecde9b9ca38030fb9b64aceed79da67a1b16111a20768db1b51033ce4053b
+size 1420238

Pyramids/Pyramids-499925.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a765f15c74638b59fc523f0dd32e9641b93bf0217de9469a6b1712b508bae483
+size 8656173

Pyramids/Pyramids-999925.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3395dfc05a3eb245da447c483971f7847b23dc78d8ba60e6d7e23333f993321b
+size 1420238

Pyramids/Pyramids-999925.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd2bdd30d699794f323d5219a4f3e2ec7e538cfb742d992fe30c28f52a749171
+size 8656173

Pyramids/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:278a2e9d11e0f557d47c982fad4a0cc22ea05974cf9d1a1c3cd0d4f6152ac321
+size 8655778

Pyramids/events.out.tfevents.1704273360.a76fab4c855c.7877.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74e71ff7272e9cf7fa5a5b82672655cb6f779a5805b5a4345c3aa7b3a780f499
+size 207715

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: tresbien1/ppo-Pyramids
+  3. Step 2: Select your *.nn /*.onnx file
+  4. Click on Watch the agent play 👀
+  

config.json

@@ -0,0 +1 @@
+{"default_settings": null, "behaviors": {"Pyramids": {"trainer_type": "ppo", "hyperparameters": {"batch_size": 128, "buffer_size": 2048, "learning_rate": 0.0003, "beta": 0.01, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "shared_critic": false, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.95, "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": 0.94, "strength": 0.01, "network_settings": {"normalize": false, "hidden_units": 64, "num_layers": 3, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "learning_rate": 0.0001, "encoding_size": null}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 1000000, "time_horizon": 128, "summary_freq": 50000, "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-2", "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: 0.95
+        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: 0.94
+        strength: 0.01
+        network_settings:
+          normalize: false
+          hidden_units: 64
+          num_layers: 3
+          vis_encode_type: simple
+          memory: null
+          goal_conditioning_type: hyper
+          deterministic: false
+        learning_rate: 0.0001
+        encoding_size: null
+    init_path: null
+    keep_checkpoints: 5
+    even_checkpoints: false
+    max_steps: 1000000
+    time_horizon: 128
+    summary_freq: 50000
+    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-2
+  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 +1,314 @@
+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] 55334 [Flags] 2 [Guid] 1589326979 [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'
+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  0.192 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: 1.130649 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 1 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]: 7292 frames, [32.0 KB-64.0 KB]: 10155 frames, [64.0 KB-128.0 KB]: 1317 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_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 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 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_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_Profiler.Dispatcher]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 240 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]
+      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_Background Job.Worker 0]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 4]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 0]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0.8 KB
+      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_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_EnlightenWorker]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Loading.AsyncRead]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 128 B
+      Overflow Count 0
+[ALLOC_MEMORYPROFILER]
+  Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 18466 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 11658
+    [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]: 18764 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 3
+      Peak Allocated memory 30.9 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 18765 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 23.6 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]: 18764 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]: 18765 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]: 18466 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]: 18764 frames, [4.0 MB-8.0 MB]: 1 frames
+      Requested Block Size 4.0 MB
+      Peak Block count 2
+      Peak Allocated memory 4.6 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]: 18765 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]: 18765 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: [16.0 KB-32.0 KB]: 18765 frames
+  Requested Block Size 16.0 MB
+  Peak Block count 1
+  Peak Allocated memory 29.2 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":1704275352635,"processId":7898,"allocatedMemory":1970133,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"NewDelete":12801},{"Thread":34460},{"Manager":10603},{"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":1360},{"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": 0.5983927845954895,
+            "min": 0.5983927845954895,
+            "max": 1.343400001525879,
+            "count": 20
+        },
+        "Pyramids.Policy.Entropy.sum": {
+            "value": 29986.66015625,
+            "min": 29986.66015625,
+            "max": 67234.484375,
+            "count": 20
+        },
+        "Pyramids.Step.mean": {
+            "value": 999925.0,
+            "min": 49878.0,
+            "max": 999925.0,
+            "count": 20
+        },
+        "Pyramids.Step.sum": {
+            "value": 999925.0,
+            "min": 49878.0,
+            "max": 999925.0,
+            "count": 20
+        },
+        "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
+            "value": -0.013876122422516346,
+            "min": -0.030839893966913223,
+            "max": -0.00945535209029913,
+            "count": 20
+        },
+        "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
+            "value": -5.5782012939453125,
+            "min": -12.3051176071167,
+            "max": -3.81050705909729,
+            "count": 20
+        },
+        "Pyramids.Policy.RndValueEstimate.mean": {
+            "value": 0.0029050002340227365,
+            "min": -0.00022533306037075818,
+            "max": 0.08890791237354279,
+            "count": 20
+        },
+        "Pyramids.Policy.RndValueEstimate.sum": {
+            "value": 1.167810082435608,
+            "min": -0.09035855531692505,
+            "max": 35.47425842285156,
+            "count": 20
+        },
+        "Pyramids.Losses.PolicyLoss.mean": {
+            "value": 0.06579226099424805,
+            "min": 0.06512104197606153,
+            "max": 0.07199981855150664,
+            "count": 20
+        },
+        "Pyramids.Losses.PolicyLoss.sum": {
+            "value": 1.513222002867705,
+            "min": 0.8930364629323959,
+            "max": 1.6477607740883151,
+            "count": 20
+        },
+        "Pyramids.Losses.ValueLoss.mean": {
+            "value": 0.0009892530458551413,
+            "min": 0.0001602431029824168,
+            "max": 0.0037391359524955254,
+            "count": 20
+        },
+        "Pyramids.Losses.ValueLoss.sum": {
+            "value": 0.02275282005466825,
+            "min": 0.0035253482656131697,
+            "max": 0.04860876738244183,
+            "count": 20
+        },
+        "Pyramids.Policy.LearningRate.mean": {
+            "value": 7.53210618498261e-06,
+            "min": 7.53210618498261e-06,
+            "max": 0.0002917810642781077,
+            "count": 20
+        },
+        "Pyramids.Policy.LearningRate.sum": {
+            "value": 0.00017323844225460003,
+            "min": 0.00017323844225460003,
+            "max": 0.005768409877196799,
+            "count": 20
+        },
+        "Pyramids.Policy.Epsilon.mean": {
+            "value": 0.1025106695652174,
+            "min": 0.1025106695652174,
+            "max": 0.19726035384615387,
+            "count": 20
+        },
+        "Pyramids.Policy.Epsilon.sum": {
+            "value": 2.3577454,
+            "min": 2.3577454,
+            "max": 4.1228032,
+            "count": 20
+        },
+        "Pyramids.Policy.Beta.mean": {
+            "value": 0.00026081588956521746,
+            "min": 0.00026081588956521746,
+            "max": 0.00972630934923077,
+            "count": 20
+        },
+        "Pyramids.Policy.Beta.sum": {
+            "value": 0.005998765460000001,
+            "min": 0.005998765460000001,
+            "max": 0.19230803968000001,
+            "count": 20
+        },
+        "Pyramids.Losses.RNDLoss.mean": {
+            "value": 0.01551153976470232,
+            "min": 0.01551153976470232,
+            "max": 0.3107236623764038,
+            "count": 20
+        },
+        "Pyramids.Losses.RNDLoss.sum": {
+            "value": 0.35676541924476624,
+            "min": 0.35676541924476624,
+            "max": 4.039407730102539,
+            "count": 20
+        },
+        "Pyramids.Environment.EpisodeLength.mean": {
+            "value": 972.5098039215686,
+            "min": 946.2692307692307,
+            "max": 996.0416666666666,
+            "count": 20
+        },
+        "Pyramids.Environment.EpisodeLength.sum": {
+            "value": 49598.0,
+            "min": 47237.0,
+            "max": 56043.0,
+            "count": 20
+        },
+        "Pyramids.Environment.CumulativeReward.mean": {
+            "value": -0.7378627939843664,
+            "min": -0.9552083844318986,
+            "max": -0.6432923601510433,
+            "count": 20
+        },
+        "Pyramids.Environment.CumulativeReward.sum": {
+            "value": -37.631002493202686,
+            "min": -50.088402941823006,
+            "max": -33.45120272785425,
+            "count": 20
+        },
+        "Pyramids.Policy.ExtrinsicReward.mean": {
+            "value": -0.7378627939843664,
+            "min": -0.9552083844318986,
+            "max": -0.6432923601510433,
+            "count": 20
+        },
+        "Pyramids.Policy.ExtrinsicReward.sum": {
+            "value": -37.631002493202686,
+            "min": -50.088402941823006,
+            "max": -33.45120272785425,
+            "count": 20
+        },
+        "Pyramids.Policy.RndReward.mean": {
+            "value": 0.15703592533428296,
+            "min": 0.15624511372656202,
+            "max": 4.615633514864991,
+            "count": 20
+        },
+        "Pyramids.Policy.RndReward.sum": {
+            "value": 8.00883219204843,
+            "min": 8.00883219204843,
+            "max": 221.55040871351957,
+            "count": 20
+        },
+        "Pyramids.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 20
+        },
+        "Pyramids.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 20
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1704273359",
+        "python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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-2 --no-graphics",
+        "mlagents_version": "1.1.0.dev0",
+        "mlagents_envs_version": "1.1.0.dev0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "2.1.2+cu121",
+        "numpy_version": "1.23.5",
+        "end_time_seconds": "1704275352"
+    },
+    "total": 1993.154926618,
+    "count": 1,
+    "self": 0.48554877099991245,
+    "children": {
+        "run_training.setup": {
+            "total": 0.06937176099995668,
+            "count": 1,
+            "self": 0.06937176099995668
+        },
+        "TrainerController.start_learning": {
+            "total": 1992.6000060860001,
+            "count": 1,
+            "self": 1.4480502969940972,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 2.673110766000036,
+                    "count": 1,
+                    "self": 2.673110766000036
+                },
+                "TrainerController.advance": {
+                    "total": 1988.394409740006,
+                    "count": 63030,
+                    "self": 1.4689806919566308,
+                    "children": {
+                        "env_step": {
+                            "total": 1358.9817631640058,
+                            "count": 63030,
+                            "self": 1225.942064266986,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 132.17192505101366,
+                                    "count": 63030,
+                                    "self": 4.719373328042593,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 127.45255172297107,
+                                            "count": 62550,
+                                            "self": 127.45255172297107
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 0.8677738460060027,
+                                    "count": 63030,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 1987.4621567540394,
+                                            "count": 63030,
+                                            "is_parallel": true,
+                                            "self": 880.5503308880463,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.0022598160001052747,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0005843530000220198,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.0016754630000832549,
+                                                                    "count": 8,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0016754630000832549
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.05077610300008928,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0006098310000197671,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.00048121800000444637,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00048121800000444637
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.047941176999984236,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.047941176999984236
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.001743877000080829,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00037161100021876337,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.0013722659998620657,
+                                                                            "count": 8,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.0013722659998620657
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 1106.911825865993,
+                                                    "count": 63029,
+                                                    "is_parallel": true,
+                                                    "self": 34.95583143394447,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 24.578581023000424,
+                                                            "count": 63029,
+                                                            "is_parallel": true,
+                                                            "self": 24.578581023000424
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 948.7428121660562,
+                                                            "count": 63029,
+                                                            "is_parallel": true,
+                                                            "self": 948.7428121660562
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 98.63460124299195,
+                                                            "count": 63029,
+                                                            "is_parallel": true,
+                                                            "self": 19.71788833404821,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 78.91671290894374,
+                                                                    "count": 504232,
+                                                                    "is_parallel": true,
+                                                                    "self": 78.91671290894374
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 627.9436658840436,
+                            "count": 63030,
+                            "self": 2.6710124700555298,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 124.30694764398822,
+                                    "count": 63030,
+                                    "self": 124.06981375898795,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 0.23713388500027577,
+                                            "count": 2,
+                                            "self": 0.23713388500027577
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 500.9657057699999,
+                                    "count": 442,
+                                    "self": 298.7058735060057,
+                                    "children": {
+                                        "TorchPPOOptimizer.update": {
+                                            "total": 202.2598322639942,
+                                            "count": 22710,
+                                            "self": 202.2598322639942
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 8.469996828353032e-07,
+                    "count": 1,
+                    "self": 8.469996828353032e-07
+                },
+                "TrainerController._save_models": {
+                    "total": 0.08443443600026512,
+                    "count": 1,
+                    "self": 0.001465669000026537,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.08296876700023859,
+                            "count": 1,
+                            "self": 0.08296876700023859
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,47 @@
+{
+    "Pyramids": {
+        "checkpoints": [
+            {
+                "steps": 499925,
+                "file_path": "results/Pyramids Training-2/Pyramids/Pyramids-499925.onnx",
+                "reward": -0.9996000528335571,
+                "creation_time": 1704274353.265112,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training-2/Pyramids/Pyramids-499925.pt"
+                ]
+            },
+            {
+                "steps": 999925,
+                "file_path": "results/Pyramids Training-2/Pyramids/Pyramids-999925.onnx",
+                "reward": 0.16050000116229057,
+                "creation_time": 1704275352.109694,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training-2/Pyramids/Pyramids-999925.pt"
+                ]
+            },
+            {
+                "steps": 1000053,
+                "file_path": "results/Pyramids Training-2/Pyramids/Pyramids-1000053.onnx",
+                "reward": 0.16050000116229057,
+                "creation_time": 1704275352.2048194,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training-2/Pyramids/Pyramids-1000053.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 1000053,
+            "file_path": "results/Pyramids Training-2/Pyramids.onnx",
+            "reward": 0.16050000116229057,
+            "creation_time": 1704275352.2048194,
+            "auxillary_file_paths": [
+                "results/Pyramids Training-2/Pyramids/Pyramids-1000053.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "1.1.0.dev0",
+        "torch_version": "2.1.2+cu121"
+    }
+}