First Push

Pyramids.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfe21201a801add7134c0267f2e2f49a234361e18a03eddb3bc4599a13946ef4
+size 1420238

Pyramids/Pyramids-1499931.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ecbf1dc8b6336de537adb1a3d5e7d986359f46247311886e241b08af2d5423fc
+size 1420238

Pyramids/Pyramids-1499931.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c01cc06938209a35b59cc6d3c6bdea09665fe5e1b2ff1ec36ecb3d12ab174bdd
+size 8655228

Pyramids/Pyramids-1999992.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b72c53ab1bab1669fe4d7205afec92046163747918a82b0550ea6557d0c024e5
+size 1420238

Pyramids/Pyramids-1999992.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:121e6c466bb5fbee552812ae7ae969380dab82b1bb23f35c54048812a6ed85e3
+size 8655228

Pyramids/Pyramids-2499972.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c7171140a376cb42f37eae7dba7dff37903a3f69bc2bd883c6318ac6f086513
+size 1420238

Pyramids/Pyramids-2499972.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f28a0a1f6f8a903a2fee21628877e3df708a54b4e39ed38b62c120b76e99953
+size 8655228

Pyramids/Pyramids-2999885.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfe21201a801add7134c0267f2e2f49a234361e18a03eddb3bc4599a13946ef4
+size 1420238

Pyramids/Pyramids-2999885.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c8a2018976a8d460f806acb7d39009f9ef47689e24410825d9f1350f49e21f3
+size 8655228

Pyramids/Pyramids-3000013.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfe21201a801add7134c0267f2e2f49a234361e18a03eddb3bc4599a13946ef4
+size 1420238

Pyramids/Pyramids-3000013.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65ed6c6dc15026127cd115f2e9a8b97f1ba2207a93ae89921031878263f73cff
+size 8655228

Pyramids/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5ff1c3de86b8abc7be9e500c010efc8ed6ca7e8997468a99a83fe6be052d7d5
+size 8654754

Pyramids/events.out.tfevents.1700148985.e29393940a73.6508.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4399ea15e33d49c45a8517fb9122fb7745360ae04e70ea7c75ee96b8fd11763e
+size 1008169

README.md

@@ -1,27 +1,35 @@
 ---
+library_name: ml-agents
 tags:
-- CartPole-v1
-- reinforce
+- Pyramids
+- deep-reinforcement-learning
 - reinforcement-learning
-- custom-implementation
-- deep-rl-class
-model-index:
-- name: Pixelcopter-PLE-v0
-  results:
-  - task:
-      type: reinforcement-learning
-      name: reinforcement-learning
-    dataset:
-      name: CartPole-v1
-      type: CartPole-v1
-    metrics:
-    - type: mean_reward
-      value: 160.50 +/- 8.90
-      name: mean_reward
-      verified: false
+- ML-Agents-Pyramids
 ---
 
-  # **Reinforce** Agent playing **CartPole-v1**
-  This is a trained model of a **Reinforce** agent playing **CartPole-v1** .
-  To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: https://huggingface.co/deep-rl-course/unit4/introduction
+  # **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: Sachavsn/Pixelcopter-PLE-v0
+  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}, "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 +1,91 @@
+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
+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] 55508 [Flags] 2 [Guid] 1650778015 [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  0.119 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: 1.067181 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]: 10132 frames, [32.0 KB-64.0 KB]: 32417 frames, [64.0 KB-128.0 KB]: 13718 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 7]
+      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_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]: 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 12989
+    [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 23.3 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: [16.0 KB-32.0 KB]: 56268 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":1700157742444,"processId":6532,"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": 0.1518215537071228,
+            "min": 0.12530633807182312,
+            "max": 1.4746869802474976,
+            "count": 100
+        },
+        "Pyramids.Policy.Entropy.sum": {
+            "value": 4561.93408203125,
+            "min": 3747.16064453125,
+            "max": 44736.10546875,
+            "count": 100
+        },
+        "Pyramids.Step.mean": {
+            "value": 2999885.0,
+            "min": 29952.0,
+            "max": 2999885.0,
+            "count": 100
+        },
+        "Pyramids.Step.sum": {
+            "value": 2999885.0,
+            "min": 29952.0,
+            "max": 2999885.0,
+            "count": 100
+        },
+        "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 0.7477790713310242,
+            "min": -0.16893930733203888,
+            "max": 0.7882753610610962,
+            "count": 100
+        },
+        "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 217.6037139892578,
+            "min": -40.03861618041992,
+            "max": 234.9060516357422,
+            "count": 100
+        },
+        "Pyramids.Policy.RndValueEstimate.mean": {
+            "value": 0.006888110190629959,
+            "min": -0.034016888588666916,
+            "max": 0.46843382716178894,
+            "count": 100
+        },
+        "Pyramids.Policy.RndValueEstimate.sum": {
+            "value": 2.0044400691986084,
+            "min": -10.058513641357422,
+            "max": 111.01881408691406,
+            "count": 100
+        },
+        "Pyramids.Losses.PolicyLoss.mean": {
+            "value": 0.06744729133911688,
+            "min": 0.06402229578400563,
+            "max": 0.07611466185127418,
+            "count": 100
+        },
+        "Pyramids.Losses.PolicyLoss.sum": {
+            "value": 0.9442620787476362,
+            "min": 0.4871366739468101,
+            "max": 1.0936850438883992,
+            "count": 100
+        },
+        "Pyramids.Losses.ValueLoss.mean": {
+            "value": 0.015692226984630533,
+            "min": 0.0005075364543951074,
+            "max": 0.017195445221386167,
+            "count": 100
+        },
+        "Pyramids.Losses.ValueLoss.sum": {
+            "value": 0.21969117778482747,
+            "min": 0.004567828089555967,
+            "max": 0.2579316783207925,
+            "count": 100
+        },
+        "Pyramids.Policy.LearningRate.mean": {
+            "value": 1.524356634771428e-06,
+            "min": 1.524356634771428e-06,
+            "max": 0.00029838354339596195,
+            "count": 100
+        },
+        "Pyramids.Policy.LearningRate.sum": {
+            "value": 2.134099288679999e-05,
+            "min": 2.134099288679999e-05,
+            "max": 0.003969285176904966,
+            "count": 100
+        },
+        "Pyramids.Policy.Epsilon.mean": {
+            "value": 0.10050808571428571,
+            "min": 0.10050808571428571,
+            "max": 0.19946118095238097,
+            "count": 100
+        },
+        "Pyramids.Policy.Epsilon.sum": {
+            "value": 1.4071132,
+            "min": 1.3962282666666668,
+            "max": 2.7230950333333337,
+            "count": 100
+        },
+        "Pyramids.Policy.Beta.mean": {
+            "value": 6.075776285714284e-05,
+            "min": 6.075776285714284e-05,
+            "max": 0.009946171977142856,
+            "count": 100
+        },
+        "Pyramids.Policy.Beta.sum": {
+            "value": 0.0008506086799999998,
+            "min": 0.0008506086799999998,
+            "max": 0.13231719382999999,
+            "count": 100
+        },
+        "Pyramids.Losses.RNDLoss.mean": {
+            "value": 0.006759076379239559,
+            "min": 0.006660886108875275,
+            "max": 0.4303519129753113,
+            "count": 100
+        },
+        "Pyramids.Losses.RNDLoss.sum": {
+            "value": 0.09462706744670868,
+            "min": 0.09325240552425385,
+            "max": 3.012463331222534,
+            "count": 100
+        },
+        "Pyramids.Environment.EpisodeLength.mean": {
+            "value": 247.3362831858407,
+            "min": 231.3709677419355,
+            "max": 999.0,
+            "count": 100
+        },
+        "Pyramids.Environment.EpisodeLength.sum": {
+            "value": 27949.0,
+            "min": 15984.0,
+            "max": 32930.0,
+            "count": 100
+        },
+        "Pyramids.Environment.CumulativeReward.mean": {
+            "value": 1.699553973115651,
+            "min": -1.0000000521540642,
+            "max": 1.767563475502862,
+            "count": 100
+        },
+        "Pyramids.Environment.CumulativeReward.sum": {
+            "value": 192.04959896206856,
+            "min": -31.999601677060127,
+            "max": 228.2193984389305,
+            "count": 100
+        },
+        "Pyramids.Policy.ExtrinsicReward.mean": {
+            "value": 1.699553973115651,
+            "min": -1.0000000521540642,
+            "max": 1.767563475502862,
+            "count": 100
+        },
+        "Pyramids.Policy.ExtrinsicReward.sum": {
+            "value": 192.04959896206856,
+            "min": -31.999601677060127,
+            "max": 228.2193984389305,
+            "count": 100
+        },
+        "Pyramids.Policy.RndReward.mean": {
+            "value": 0.017834546842892547,
+            "min": 0.017414834326759335,
+            "max": 8.30799985025078,
+            "count": 100
+        },
+        "Pyramids.Policy.RndReward.sum": {
+            "value": 2.015303793246858,
+            "min": 2.015303793246858,
+            "max": 132.9279976040125,
+            "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": "1700148984",
+        "python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "2.1.0+cu118",
+        "numpy_version": "1.23.5",
+        "end_time_seconds": "1700157742"
+    },
+    "total": 8757.640482693001,
+    "count": 1,
+    "self": 0.494850357003088,
+    "children": {
+        "run_training.setup": {
+            "total": 0.052286706999893795,
+            "count": 1,
+            "self": 0.052286706999893795
+        },
+        "TrainerController.start_learning": {
+            "total": 8757.093345628999,
+            "count": 1,
+            "self": 5.874912404779025,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 1.3936546800000542,
+                    "count": 1,
+                    "self": 1.3936546800000542
+                },
+                "TrainerController.advance": {
+                    "total": 8749.74517216022,
+                    "count": 193940,
+                    "self": 6.251621759165573,
+                    "children": {
+                        "env_step": {
+                            "total": 5849.800360995107,
+                            "count": 193940,
+                            "self": 5452.370816935354,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 393.91045222865273,
+                                    "count": 193940,
+                                    "self": 16.729529515847844,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 377.1809227128049,
+                                            "count": 187560,
+                                            "self": 377.1809227128049
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 3.519091831100468,
+                                    "count": 193940,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 8742.23770560066,
+                                            "count": 193940,
+                                            "is_parallel": true,
+                                            "self": 3719.20009524945,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.003926331000002392,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0013773359999049717,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.0025489950000974204,
+                                                                    "count": 8,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0025489950000974204
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.05148526700008915,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0005755269999099255,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.00029091100009281945,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00029091100009281945
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.04893202600010227,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.04893202600010227
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.0016868029999841383,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0003434739996919234,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.001343329000292215,
+                                                                            "count": 8,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.001343329000292215
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 5023.037610351211,
+                                                    "count": 193939,
+                                                    "is_parallel": true,
+                                                    "self": 114.31621535066915,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 64.94760058173188,
+                                                            "count": 193939,
+                                                            "is_parallel": true,
+                                                            "self": 64.94760058173188
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 4518.060588312846,
+                                                            "count": 193939,
+                                                            "is_parallel": true,
+                                                            "self": 4518.060588312846
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 325.71320610596285,
+                                                            "count": 193939,
+                                                            "is_parallel": true,
+                                                            "self": 70.00067494820951,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 255.71253115775335,
+                                                                    "count": 1551512,
+                                                                    "is_parallel": true,
+                                                                    "self": 255.71253115775335
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 2893.693189405947,
+                            "count": 193940,
+                            "self": 11.047403916343683,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 427.65439836461405,
+                                    "count": 193940,
+                                    "self": 427.1406205616124,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 0.5137778030016307,
+                                            "count": 6,
+                                            "self": 0.5137778030016307
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 2454.991387124989,
+                                    "count": 1390,
+                                    "self": 1001.8047621549204,
+                                    "children": {
+                                        "TorchPPOOptimizer.update": {
+                                            "total": 1453.1866249700688,
+                                            "count": 68439,
+                                            "self": 1453.1866249700688
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 1.2700002116616815e-06,
+                    "count": 1,
+                    "self": 1.2700002116616815e-06
+                },
+                "TrainerController._save_models": {
+                    "total": 0.07960511400051473,
+                    "count": 1,
+                    "self": 0.001685033999820007,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.07792008000069472,
+                            "count": 1,
+                            "self": 0.07792008000069472
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,65 @@
+{
+    "Pyramids": {
+        "checkpoints": [
+            {
+                "steps": 1499931,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1499931.onnx",
+                "reward": 1.4429999788602192,
+                "creation_time": 1700153007.145087,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-1499931.pt"
+                ]
+            },
+            {
+                "steps": 1999992,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-1999992.onnx",
+                "reward": null,
+                "creation_time": 1700154545.092122,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-1999992.pt"
+                ]
+            },
+            {
+                "steps": 2499972,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-2499972.onnx",
+                "reward": 1.753999963402748,
+                "creation_time": 1700156114.2180872,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-2499972.pt"
+                ]
+            },
+            {
+                "steps": 2999885,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-2999885.onnx",
+                "reward": 1.740600010752678,
+                "creation_time": 1700157741.9045608,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-2999885.pt"
+                ]
+            },
+            {
+                "steps": 3000013,
+                "file_path": "results/Pyramids Training/Pyramids/Pyramids-3000013.onnx",
+                "reward": 1.740600010752678,
+                "creation_time": 1700157742.0026205,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training/Pyramids/Pyramids-3000013.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 3000013,
+            "file_path": "results/Pyramids Training/Pyramids.onnx",
+            "reward": 1.740600010752678,
+            "creation_time": 1700157742.0026205,
+            "auxillary_file_paths": [
+                "results/Pyramids Training/Pyramids/Pyramids-3000013.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "1.1.0.dev0",
+        "torch_version": "2.1.0+cu118"
+    }
+}