PPO agent

Pyramids.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd5dfca049738eaeb11e61b009be0128396e75a452822023c4281a64da87c490
+size 1417437

Pyramids/Pyramids-1499903.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f511e86d5dcd31d8accdacfb0517d06a351201d38c874e1edc69ff3f47ece7b
+size 1417437

Pyramids/Pyramids-1499903.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f984ff012cd6b41ab5bd3adba2bdc2d3b2bf3539e55cd9e66d73a15c6d84bb3a
+size 8651427

Pyramids/Pyramids-1505592.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd5dfca049738eaeb11e61b009be0128396e75a452822023c4281a64da87c490
+size 1417437

Pyramids/Pyramids-1505592.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27df8ecf8d332b761fbe73ab2e73b6fe9469031aac9beaaa3207cdf8c7752ba1
+size 8651427

Pyramids/Pyramids-499940.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41dc2a14ba9562729c3dd3874bec9e5b56a100e3d99bfca6e7b3099eb98d7a2f
+size 1417437

Pyramids/Pyramids-499940.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc26f930443a82942f02b95735352a5a258328629515f5004080d6feb0627cac
+size 8651427

Pyramids/Pyramids-999987.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bbee62504a83f65db948a6b5bd9135ad08bb790a47fb9005d1fc763c4f78006
+size 1417437

Pyramids/Pyramids-999987.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddf8e4c964ca3da9dd09ffd37845882fa38586f4d4a80ad5c299f17e5fe16d8e
+size 8651427

Pyramids/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27df8ecf8d332b761fbe73ab2e73b6fe9469031aac9beaaa3207cdf8c7752ba1
+size 8651427

Pyramids/events.out.tfevents.1675262508.c2acf5990f76.7838.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:748b5c55101bd26de2f15e9686f2cd3511cac54ca039c4cdf20ed820fa2399b8
+size 461330

README.md

@@ -0,0 +1,31 @@
+
+---
+      tags:
+      - unity-ml-agents
+      - ml-agents
+      - deep-reinforcement-learning
+      - reinforcement-learning
+      - ML-Agents-Pyramids
+      library_name: ml-agents
+---
+    
+  # **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://github.com/huggingface/ml-agents#get-started
+  We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
+
+
+  ### Resume the training
+  ```
+  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. Go to https://huggingface.co/spaces/unity/ML-Agents-Pyramids
+  2. Step 1: Write your model_id: Lakoc/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, "learning_rate_schedule": "linear", "beta_schedule": "linear", "epsilon_schedule": "linear"}, "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, "checkpoint_interval": 500000, "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 +1,88 @@
+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
+      learning_rate_schedule: linear
+      beta_schedule: linear
+      epsilon_schedule: linear
+    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
+    checkpoint_interval: 500000
+    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 +1,317 @@
+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] 55150 [Flags] 2 [Guid] 1549651452 [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:767:(parse_card) cannot find card '0'
+ALSA lib conf.c:4732:(_snd_config_evaluate) function snd_func_card_driver returned error: No such file or directory
+ALSA lib confmisc.c:392:(snd_func_concat) error evaluating strings
+ALSA lib conf.c:4732:(_snd_config_evaluate) function snd_func_concat returned error: No such file or directory
+ALSA lib confmisc.c:1246:(snd_func_refer) error evaluating name
+ALSA lib conf.c:4732:(_snd_config_evaluate) function snd_func_refer returned error: No such file or directory
+ALSA lib conf.c:5220:(snd_config_expand) Evaluate error: No such file or directory
+ALSA lib pcm.c:2642:(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:767:(parse_card) cannot find card '0'
+ALSA lib conf.c:4732:(_snd_config_evaluate) function snd_func_card_driver returned error: No such file or directory
+ALSA lib confmisc.c:392:(snd_func_concat) error evaluating strings
+ALSA lib conf.c:4732:(_snd_config_evaluate) function snd_func_concat returned error: No such file or directory
+ALSA lib confmisc.c:1246:(snd_func_refer) error evaluating name
+ALSA lib conf.c:4732:(_snd_config_evaluate) function snd_func_refer returned error: No such file or directory
+ALSA lib conf.c:5220:(snd_config_expand) Evaluate error: No such file or directory
+ALSA lib pcm.c:2642:(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  0.196 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: 3.281741 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]: 9413 frames, [32.0 KB-64.0 KB]: 14696 frames, [64.0 KB-128.0 KB]: 4140 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 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 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_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 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]
+      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 14]
+      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 9]
+      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]: 27951 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 12451
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 1.6 MB
+    [ALLOC_DEFAULT_MAIN]
+      Peak usage frame count: [8.0 MB-16.0 MB]: 1 frames, [16.0 MB-32.0 MB]: 28249 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 3
+      Peak Allocated memory 31.0 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 28250 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 22.7 MB
+      Peak Large allocation bytes 16.0 MB
+[ALLOC_TEMP_JOB_1_FRAME]
+  Initial Block Size 2.0 MB
+  Used Block Count 1
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_TEMP_JOB_2_FRAMES]
+  Initial Block Size 2.0 MB
+  Used Block Count 1
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_TEMP_JOB_4_FRAMES (JobTemp)]
+  Initial Block Size 2.0 MB
+  Used Block Count 2
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_TEMP_JOB_ASYNC (Background)]
+  Initial Block Size 1.0 MB
+  Used Block Count 3
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_GFX] Dual Thread Allocator
+  Peak main deferred allocation count 0
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 1.6 MB
+    [ALLOC_GFX_MAIN]
+      Peak usage frame count: [32.0 KB-64.0 KB]: 28249 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]: 28250 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 1.6 MB
+    [ALLOC_CACHEOBJECTS_MAIN]
+      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 27951 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]: 28249 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 1.6 MB
+    [ALLOC_TYPETREE_MAIN]
+      Peak usage frame count: [0-1.0 KB]: 28250 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]: 28250 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]: 28250 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":1675267025302,"processId":7858,"allocatedMemory":1957332,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"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 +1,405 @@
+{
+    "name": "root",
+    "gauges": {
+        "Pyramids.Policy.Entropy.mean": {
+            "value": 0.28421467542648315,
+            "min": 0.28421467542648315,
+            "max": 1.4405357837677002,
+            "count": 50
+        },
+        "Pyramids.Policy.Entropy.sum": {
+            "value": 8503.703125,
+            "min": 8503.703125,
+            "max": 43700.09375,
+            "count": 50
+        },
+        "Pyramids.Step.mean": {
+            "value": 1499903.0,
+            "min": 29952.0,
+            "max": 1499903.0,
+            "count": 50
+        },
+        "Pyramids.Step.sum": {
+            "value": 1499903.0,
+            "min": 29952.0,
+            "max": 1499903.0,
+            "count": 50
+        },
+        "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 0.6422605514526367,
+            "min": -0.12505429983139038,
+            "max": 0.6437637209892273,
+            "count": 50
+        },
+        "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 178.54843139648438,
+            "min": -30.013032913208008,
+            "max": 180.89759826660156,
+            "count": 50
+        },
+        "Pyramids.Policy.RndValueEstimate.mean": {
+            "value": 0.00918685831129551,
+            "min": -0.009508224204182625,
+            "max": 0.5712061524391174,
+            "count": 50
+        },
+        "Pyramids.Policy.RndValueEstimate.sum": {
+            "value": 2.5539464950561523,
+            "min": -2.6147615909576416,
+            "max": 135.3758544921875,
+            "count": 50
+        },
+        "Pyramids.Losses.PolicyLoss.mean": {
+            "value": 0.0669284677683858,
+            "min": 0.06261540081544727,
+            "max": 0.07318900337309796,
+            "count": 50
+        },
+        "Pyramids.Losses.PolicyLoss.sum": {
+            "value": 0.9369985487574013,
+            "min": 0.5105135901503255,
+            "max": 1.0654427599057432,
+            "count": 50
+        },
+        "Pyramids.Losses.ValueLoss.mean": {
+            "value": 0.015309359984322717,
+            "min": 2.626431715347892e-05,
+            "max": 0.017680035694779474,
+            "count": 50
+        },
+        "Pyramids.Losses.ValueLoss.sum": {
+            "value": 0.21433103978051804,
+            "min": 0.00036770044014870486,
+            "max": 0.24752049972691262,
+            "count": 50
+        },
+        "Pyramids.Policy.LearningRate.mean": {
+            "value": 0.00015146664236827855,
+            "min": 0.00015146664236827855,
+            "max": 0.00029838354339596195,
+            "count": 50
+        },
+        "Pyramids.Policy.LearningRate.sum": {
+            "value": 0.0021205329931558996,
+            "min": 0.0020886848037717336,
+            "max": 0.003801056332981266,
+            "count": 50
+        },
+        "Pyramids.Policy.Epsilon.mean": {
+            "value": 0.15048886428571429,
+            "min": 0.15048886428571429,
+            "max": 0.19946118095238097,
+            "count": 50
+        },
+        "Pyramids.Policy.Epsilon.sum": {
+            "value": 2.1068441,
+            "min": 1.3962282666666668,
+            "max": 2.667018733333334,
+            "count": 50
+        },
+        "Pyramids.Policy.Beta.mean": {
+            "value": 0.005053837542142857,
+            "min": 0.005053837542142857,
+            "max": 0.009946171977142856,
+            "count": 50
+        },
+        "Pyramids.Policy.Beta.sum": {
+            "value": 0.07075372559,
+            "min": 0.06962320384,
+            "max": 0.12671517146,
+            "count": 50
+        },
+        "Pyramids.Losses.RNDLoss.mean": {
+            "value": 0.008841591887176037,
+            "min": 0.008407366462051868,
+            "max": 0.5084035992622375,
+            "count": 50
+        },
+        "Pyramids.Losses.RNDLoss.sum": {
+            "value": 0.12378229200839996,
+            "min": 0.11770313233137131,
+            "max": 3.5588250160217285,
+            "count": 50
+        },
+        "Pyramids.Environment.EpisodeLength.mean": {
+            "value": 291.1188118811881,
+            "min": 289.969696969697,
+            "max": 999.0,
+            "count": 50
+        },
+        "Pyramids.Environment.EpisodeLength.sum": {
+            "value": 29403.0,
+            "min": 15984.0,
+            "max": 32467.0,
+            "count": 50
+        },
+        "Pyramids.Environment.CumulativeReward.mean": {
+            "value": 1.6098455259262925,
+            "min": -1.0000000521540642,
+            "max": 1.6696141258333668,
+            "count": 50
+        },
+        "Pyramids.Environment.CumulativeReward.sum": {
+            "value": 162.59439811855555,
+            "min": -31.998801663517952,
+            "max": 167.99539843201637,
+            "count": 50
+        },
+        "Pyramids.Policy.ExtrinsicReward.mean": {
+            "value": 1.6098455259262925,
+            "min": -1.0000000521540642,
+            "max": 1.6696141258333668,
+            "count": 50
+        },
+        "Pyramids.Policy.ExtrinsicReward.sum": {
+            "value": 162.59439811855555,
+            "min": -31.998801663517952,
+            "max": 167.99539843201637,
+            "count": 50
+        },
+        "Pyramids.Policy.RndReward.mean": {
+            "value": 0.026676239869972265,
+            "min": 0.026482453851400866,
+            "max": 10.544406680390239,
+            "count": 50
+        },
+        "Pyramids.Policy.RndReward.sum": {
+            "value": 2.694300226867199,
+            "min": 2.6217629312886856,
+            "max": 168.71050688624382,
+            "count": 50
+        },
+        "Pyramids.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 50
+        },
+        "Pyramids.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 50
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1675262501",
+        "python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]",
+        "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": "0.29.0.dev0",
+        "mlagents_envs_version": "0.29.0.dev0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "1.8.1+cu102",
+        "numpy_version": "1.21.6",
+        "end_time_seconds": "1675267025"
+    },
+    "total": 4523.411260270001,
+    "count": 1,
+    "self": 0.6396289430012985,
+    "children": {
+        "run_training.setup": {
+            "total": 0.18999339700008022,
+            "count": 1,
+            "self": 0.18999339700008022
+        },
+        "TrainerController.start_learning": {
+            "total": 4522.5816379299995,
+            "count": 1,
+            "self": 3.299644830998659,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 6.748880285999803,
+                    "count": 1,
+                    "self": 6.748880285999803
+                },
+                "TrainerController.advance": {
+                    "total": 4512.358936176001,
+                    "count": 95942,
+                    "self": 3.0160458228401694,
+                    "children": {
+                        "env_step": {
+                            "total": 2856.0333407072317,
+                            "count": 95942,
+                            "self": 2654.137594056332,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 199.7660629909958,
+                                    "count": 95942,
+                                    "self": 9.029875897853572,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 190.73618709314223,
+                                            "count": 94165,
+                                            "self": 42.13363956603712,
+                                            "children": {
+                                                "TorchPolicy.sample_actions": {
+                                                    "total": 148.60254752710512,
+                                                    "count": 94165,
+                                                    "self": 148.60254752710512
+                                                }
+                                            }
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 2.129683659903776,
+                                    "count": 95942,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 4513.928799117089,
+                                            "count": 95942,
+                                            "is_parallel": true,
+                                            "self": 2090.086618842244,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.003678712999999334,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.001608643000054144,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.00207006999994519,
+                                                                    "count": 8,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00207006999994519
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.08292716899995867,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0006813109998802247,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.0006417800000235729,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0006417800000235729
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.07926404499994533,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.07926404499994533
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.0023400330001095426,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0005988769999021315,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.0017411560002074111,
+                                                                            "count": 8,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.0017411560002074111
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 2423.8421802748444,
+                                                    "count": 95941,
+                                                    "is_parallel": true,
+                                                    "self": 59.7987793307002,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 39.34728622500961,
+                                                            "count": 95941,
+                                                            "is_parallel": true,
+                                                            "self": 39.34728622500961
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 2113.0560614410897,
+                                                            "count": 95941,
+                                                            "is_parallel": true,
+                                                            "self": 2113.0560614410897
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 211.6400532780449,
+                                                            "count": 95941,
+                                                            "is_parallel": true,
+                                                            "self": 54.18102753587914,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 157.45902574216575,
+                                                                    "count": 767528,
+                                                                    "is_parallel": true,
+                                                                    "self": 157.45902574216575
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 1653.3095496459293,
+                            "count": 95942,
+                            "self": 6.141486998865503,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 294.5213748260728,
+                                    "count": 95942,
+                                    "self": 294.0877338470734,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 0.43364097899939225,
+                                            "count": 3,
+                                            "self": 0.43364097899939225
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 1352.646687820991,
+                                    "count": 680,
+                                    "self": 363.6795565189875,
+                                    "children": {
+                                        "TorchPPOOptimizer.update": {
+                                            "total": 988.9671313020035,
+                                            "count": 34427,
+                                            "self": 988.9671313020035
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 1.97000008483883e-06,
+                    "count": 1,
+                    "self": 1.97000008483883e-06
+                },
+                "TrainerController._save_models": {
+                    "total": 0.17417466699953366,
+                    "count": 1,
+                    "self": 0.005935031999797502,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.16823963499973615,
+                            "count": 1,
+                            "self": 0.16823963499973615
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,56 @@
+{
+    "Pyramids": {
+        "checkpoints": [
+            {
+                "steps": 499940,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-499940.onnx",
+                "reward": -0.9992000460624695,
+                "creation_time": 1675263907.3630624,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-499940.pt"
+                ]
+            },
+            {
+                "steps": 999987,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-999987.onnx",
+                "reward": 1.5067499801516533,
+                "creation_time": 1675265375.4395335,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-999987.pt"
+                ]
+            },
+            {
+                "steps": 1499903,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1499903.onnx",
+                "reward": 1.7494999952614307,
+                "creation_time": 1675267004.5078547,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-1499903.pt"
+                ]
+            },
+            {
+                "steps": 1505592,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1505592.onnx",
+                "reward": null,
+                "creation_time": 1675267024.7337627,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-1505592.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 1505592,
+            "file_path": "results/Pyramids Training/Pyramids.onnx",
+            "reward": null,
+            "creation_time": 1675267024.7337627,
+            "auxillary_file_paths": [
+                "results/Pyramids Training/Pyramids/Pyramids-1505592.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "0.29.0.dev0",
+        "torch_version": "1.8.1+cu102"
+    }
+}