Push trained Pyramids agent with RND

Pyramids.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d149cde5d5f144eb248d02a376412f9e08ed2cff3755076ccfe8130f79b14df
+size 1420238

Pyramids/Pyramids-1000076.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d149cde5d5f144eb248d02a376412f9e08ed2cff3755076ccfe8130f79b14df
+size 1420238

Pyramids/Pyramids-1000076.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e3ed19114fbbecce74d77d978d8362bf8388eaa9f62acd3ef3219aaab016ec0
+size 8656079

Pyramids/Pyramids-199893.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9521de7d3413f74f384ee37a868c7cabe2fd8911bdc0c8fde2fd8a6091b7f1a
+size 1420238

Pyramids/Pyramids-199893.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53de70e9f156cac7cd76dd1ac868d7c47579d53a57e7de6e1bc91b185e8f24d2
+size 8656000

Pyramids/Pyramids-299951.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f95c80879cad9b2c7b8161e4a73466ec5f2d56b54799bd9d9e654b18dde1bb26
+size 1420238

Pyramids/Pyramids-299951.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:707b55bef3dfb9950cf7cff3f9355864e2d3b9fd699de60175e16d7de19cbca2
+size 8656000

Pyramids/Pyramids-399927.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b164a75f8def710daee95e2fcca51cb498ccae644421bf393c9e9117465f55c
+size 1420238

Pyramids/Pyramids-399927.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a557f80812661fb153036a3ccea7319d6399e31beffc7572353c1aa82b1caf86
+size 8656000

Pyramids/Pyramids-499945.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b93a836f75d934f242a3203f4ede23f82f5e23a2cdcbd0973a33ace4dab771ab
+size 1420238

Pyramids/Pyramids-499945.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b11738f374f57b6f919ff31928f6b5a0aba3207b57d70d7623f3802952845df1
+size 8656000

Pyramids/Pyramids-599997.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e103d15a0faffabe7a4ea8c4a11753043007a7b74d9c344079c12db082fe975
+size 1420238

Pyramids/Pyramids-599997.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5df6954ec6e939d75f8756a2e0b63ed1cfefa87736ee186e7b3b9778647041d1
+size 8656000

Pyramids/Pyramids-699963.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbd3527afa00b78e7ccec69f971ee1f0ef4078c2cb9b9b67e548a23b43bc1e87
+size 1420238

Pyramids/Pyramids-699963.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47125fadde0006694586d3d2f18ff005052c8a6289126063d1eb6b87d61579e7
+size 8656000

Pyramids/Pyramids-799893.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6779bba0e581b72a979080dcee4d9a8854c3dac1a00066913272d235038eecde
+size 1420238

Pyramids/Pyramids-799893.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2775940da487d22f07ec9b4c1a9db5691bdfa4257a6606f3690eac2ee5199d28
+size 8656000

Pyramids/Pyramids-899921.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a75256a75bb53d304caa7d4dd2487ee334bebcbee6a52c7d3c12a21787bee18
+size 1420238

Pyramids/Pyramids-899921.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4877dba0d1d2cdfba76d755f0d96df7d4b028cde999dff1c0371b0c210dee39
+size 8656000

Pyramids/Pyramids-999996.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d149cde5d5f144eb248d02a376412f9e08ed2cff3755076ccfe8130f79b14df
+size 1420238

Pyramids/Pyramids-999996.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d17984e2c84a4e58906745bdb82eb838dd208bbbe41151b36c49fa1e6e3a57bf
+size 8656000

Pyramids/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10114ec5da36f76008c334dae104cbddf40f629f89e71e61a413814431cd193e
+size 8655605

Pyramids/events.out.tfevents.1787394187.pop-os.4838.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81ef56ed9f7324c45b2183827f3ac4681c2f49f56396c557946aa1f713a834f8
+size 461927

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: Atharva1232/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": 100000, "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": 10, "even_checkpoints": false, "max_steps": 1000000, "time_horizon": 128, "summary_freq": 20000, "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": "Pyramids1", "initialize_from": null, "load_model": false, "resume": false, "force": true, "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: 100000
+    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: 10
+    even_checkpoints: false
+    max_steps: 1000000
+    time_horizon: 128
+    summary_freq: 20000
+    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: Pyramids1
+  initialize_from: null
+  load_model: false
+  resume: false
+  force: true
+  train_model: false
+  inference: false
+  results_dir: results
+torch_settings:
+  device: null
+debug: false

run_logs/Player-0.log

@@ -0,0 +1,344 @@
+Mono path[0] = '/home/atharva/Desktop/hf/training-envs-executables/linux/Pyramids/Pyramids_Data/Managed'
+Mono config path = '/home/atharva/Desktop/hf/training-envs-executables/linux/Pyramids/Pyramids_Data/MonoBleedingEdge/etc'
+Found 2 interfaces on host : 0) 192.168.0.111 1) 100.73.109.92
+Multi-casting "[IP] 192.168.0.111 [Port] 55266 [Flags] 2 [Guid] 1472830420 [EditorId] 764847374 [Version] 1048832 [Id] LinuxPlayer(13,192.168.0.111) [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 /home/atharva/Desktop/hf/training-envs-executables/linux/Pyramids/Pyramids_Data/UnitySubsystems
+Forcing GfxDevice: Null
+GfxDevice: creating device client; threaded=0; jobified=0
+NullGfxDevice:
+    Version:  NULL 1.0 [1.0]
+    Renderer: Null Device
+    Vendor:   Unity Technologies
+Begin MonoManager ReloadAssembly
+- Completed reload, in  0.114 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: 1.756514 ms
+ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+requesting resize 84 x 84
+Setting up 6 worker threads for Enlighten.
+PlayerConnection::CleanupMemory Statistics:
+[ALLOC_TEMP_TLS] TLS Allocator
+  StackAllocators : 
+    [ALLOC_TEMP_MAIN]
+      Peak usage frame count: [16.0 KB-32.0 KB]: 4099 frames, [32.0 KB-64.0 KB]: 12052 frames, [64.0 KB-128.0 KB]: 2616 frames, [2.0 MB-4.0 MB]: 1 frames
+      Initial Block Size 4.0 MB
+      Current Block Size 4.0 MB
+      Peak Allocated Bytes 2.0 MB
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 8]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 10]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 4]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 6]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 1]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 11]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 3]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_BatchDeleteObjects]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_AUDIO_FMOD stream thread]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 2]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 7]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 8]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 1]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 10]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Loading.PreloadManager]
+      Initial Block Size 256.0 KB
+      Current Block Size 320.0 KB
+      Peak Allocated Bytes 251.5 KB
+      Overflow Count 4
+    [ALLOC_TEMP_Background Job.Worker 15]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_AUDIO_FMOD PulseAudio Mixer]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Profiler.Dispatcher]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 3]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 12]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_AssetGarbageCollectorHelper] x 11
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 5]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 13]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 2]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 0]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 4]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 0]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 6]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 5]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 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] x 6
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 9]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0.8 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 7]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_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]: 18469 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 12318
+    [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]: 18767 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 3
+      Peak Allocated memory 30.6 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 18768 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 27.3 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]: 18767 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]: 18768 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]: 18469 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]: 18767 frames, [2.0 MB-4.0 MB]: 1 frames
+      Requested Block Size 4.0 MB
+      Peak Block count 1
+      Peak Allocated memory 3.9 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]: 18768 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]: 18768 frames
+      Requested Block Size 2.0 MB
+      Peak Block count 1
+      Peak Allocated memory 1.9 KB
+      Peak Large allocation bytes 0 B
+[ALLOC_PROFILER]
+  Peak usage frame count: [32.0 KB-64.0 KB]: 18768 frames
+  Requested Block Size 16.0 MB
+  Peak Block count 1
+  Peak Allocated memory 35.2 KB
+  Peak Large allocation bytes 0 B
+    [ALLOC_PROFILER_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 396 B
+##utp:{"type":"MemoryLeaks","version":2,"phase":"Immediate","time":1787395087555,"processId":4958,"allocatedMemory":1980153,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"NewDelete":12801},{"Thread":34740},{"Manager":16207},{"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":3503},{"DynamicArray":30868},{"HashMap":7680},{"Utility":5440},{"PoolAlloc":1160},{"TypeTree":1792},{"ScriptManager":80},{"RuntimeInitializeOnLoadManager":72},{"SpriteAtlas":112},{"GI":3272},{"Unet":16},{"Director":7760},{"WebRequest":720},{"VR":45473},{"SceneManager":424},{"Video":32},{"LazyScriptCache":32},{"NativeArray":384},{"Camera":25},{"Secure":1},{"SerializationCache":624},{"APIUpdating":5872},{"Subsystems":384},{"VirtualTexturing":57552},{"AssetReference":32}]}

run_logs/timers.json

@@ -0,0 +1,398 @@
+{
+    "name": "root",
+    "gauges": {
+        "Pyramids.Policy.Entropy.mean": {
+            "value": 0.551590085029602,
+            "min": 0.551590085029602,
+            "max": 1.577091097831726,
+            "count": 50
+        },
+        "Pyramids.Policy.Entropy.sum": {
+            "value": 10987.6748046875,
+            "min": 10987.6748046875,
+            "max": 31693.22265625,
+            "count": 50
+        },
+        "Pyramids.Step.mean": {
+            "value": 999996.0,
+            "min": 19968.0,
+            "max": 999996.0,
+            "count": 50
+        },
+        "Pyramids.Step.sum": {
+            "value": 999996.0,
+            "min": 19968.0,
+            "max": 999996.0,
+            "count": 50
+        },
+        "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 0.5138071179389954,
+            "min": -0.1796068400144577,
+            "max": 0.5138071179389954,
+            "count": 50
+        },
+        "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 95.56812286376953,
+            "min": -28.55748748779297,
+            "max": 95.56812286376953,
+            "count": 50
+        },
+        "Pyramids.Policy.RndValueEstimate.mean": {
+            "value": 0.06619288772344589,
+            "min": -0.0223530363291502,
+            "max": 0.21983985602855682,
+            "count": 50
+        },
+        "Pyramids.Policy.RndValueEstimate.sum": {
+            "value": 12.311877250671387,
+            "min": -3.9788405895233154,
+            "max": 34.95453643798828,
+            "count": 50
+        },
+        "Pyramids.Losses.PolicyLoss.mean": {
+            "value": 0.06523274813338906,
+            "min": 0.06457026638263078,
+            "max": 0.07381447452698248,
+            "count": 50
+        },
+        "Pyramids.Losses.PolicyLoss.sum": {
+            "value": 0.5870947332005015,
+            "min": 0.29177958178822344,
+            "max": 0.7300669412795161,
+            "count": 50
+        },
+        "Pyramids.Losses.ValueLoss.mean": {
+            "value": 0.016980483297461265,
+            "min": 0.0001669898494954476,
+            "max": 0.017262498813107853,
+            "count": 50
+        },
+        "Pyramids.Losses.ValueLoss.sum": {
+            "value": 0.1528243496771514,
+            "min": 0.0013359187959635808,
+            "max": 0.1607116995876947,
+            "count": 50
+        },
+        "Pyramids.Policy.LearningRate.mean": {
+            "value": 2.939599020166669e-06,
+            "min": 2.939599020166669e-06,
+            "max": 0.0002969568010144,
+            "count": 50
+        },
+        "Pyramids.Policy.LearningRate.sum": {
+            "value": 2.645639118150002e-05,
+            "min": 2.645639118150002e-05,
+            "max": 0.0022392214535929,
+            "count": 50
+        },
+        "Pyramids.Policy.Epsilon.mean": {
+            "value": 0.10097983333333334,
+            "min": 0.10097983333333334,
+            "max": 0.19898559999999998,
+            "count": 50
+        },
+        "Pyramids.Policy.Epsilon.sum": {
+            "value": 0.9088185000000001,
+            "min": 0.7959423999999999,
+            "max": 1.7299627,
+            "count": 50
+        },
+        "Pyramids.Policy.Beta.mean": {
+            "value": 0.0001078853500000001,
+            "min": 0.0001078853500000001,
+            "max": 0.00989866144,
+            "count": 50
+        },
+        "Pyramids.Policy.Beta.sum": {
+            "value": 0.0009709681500000008,
+            "min": 0.0009709681500000008,
+            "max": 0.07465606929,
+            "count": 50
+        },
+        "Pyramids.Losses.RNDLoss.mean": {
+            "value": 0.006949213799089193,
+            "min": 0.006566396448761225,
+            "max": 0.38224899768829346,
+            "count": 50
+        },
+        "Pyramids.Losses.RNDLoss.sum": {
+            "value": 0.06254292279481888,
+            "min": 0.060324959456920624,
+            "max": 1.5289959907531738,
+            "count": 50
+        },
+        "Pyramids.Environment.EpisodeLength.mean": {
+            "value": 374.8474576271187,
+            "min": 348.4807692307692,
+            "max": 999.0,
+            "count": 50
+        },
+        "Pyramids.Environment.EpisodeLength.sum": {
+            "value": 22116.0,
+            "min": 15323.0,
+            "max": 31968.0,
+            "count": 50
+        },
+        "Pyramids.Environment.CumulativeReward.mean": {
+            "value": 1.6222586012605964,
+            "min": -1.0000000521540642,
+            "max": 1.6222586012605964,
+            "count": 50
+        },
+        "Pyramids.Environment.CumulativeReward.sum": {
+            "value": 94.09099887311459,
+            "min": -32.000001668930054,
+            "max": 94.09099887311459,
+            "count": 50
+        },
+        "Pyramids.Policy.ExtrinsicReward.mean": {
+            "value": 1.6222586012605964,
+            "min": -1.0000000521540642,
+            "max": 1.6222586012605964,
+            "count": 50
+        },
+        "Pyramids.Policy.ExtrinsicReward.sum": {
+            "value": 94.09099887311459,
+            "min": -32.000001668930054,
+            "max": 94.09099887311459,
+            "count": 50
+        },
+        "Pyramids.Policy.RndReward.mean": {
+            "value": 0.026957215070006927,
+            "min": 0.026129583753052948,
+            "max": 5.808251433540136,
+            "count": 50
+        },
+        "Pyramids.Policy.RndReward.sum": {
+            "value": 1.5635184740604018,
+            "min": 1.307538619497791,
+            "max": 92.93202293664217,
+            "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": "1787394184",
+        "python_version": "3.10.12 (main, Jul 26 2023, 13:20:36) [Clang 16.0.3 ]",
+        "command_line_arguments": ".venv-mlagents/bin/mlagents-learn config/ppo/PyramidsRND.yaml --env=training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids1 --no-graphics --force",
+        "mlagents_version": "1.2.0.dev0",
+        "mlagents_envs_version": "1.2.0.dev0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "2.8.0+cu128",
+        "numpy_version": "1.23.5",
+        "end_time_seconds": "1787395087"
+    },
+    "total": 903.479309686,
+    "count": 1,
+    "self": 0.5869812669999419,
+    "children": {
+        "run_training.setup": {
+            "total": 0.0565203360000055,
+            "count": 1,
+            "self": 0.0565203360000055
+        },
+        "TrainerController.start_learning": {
+            "total": 902.8358080830001,
+            "count": 1,
+            "self": 0.7708607759798269,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 12.615482134000047,
+                    "count": 1,
+                    "self": 12.615482134000047
+                },
+                "TrainerController.advance": {
+                    "total": 889.3699326650202,
+                    "count": 63652,
+                    "self": 0.7434145150274389,
+                    "children": {
+                        "env_step": {
+                            "total": 536.1517973169932,
+                            "count": 63652,
+                            "self": 449.9551739180137,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 85.70504401097747,
+                                    "count": 63652,
+                                    "self": 2.25659100996387,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 83.4484530010136,
+                                            "count": 62559,
+                                            "self": 83.4484530010136
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 0.4915793880020374,
+                                    "count": 63652,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 901.7233150899893,
+                                            "count": 63652,
+                                            "is_parallel": true,
+                                            "self": 502.4046308449831,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.012606593999976212,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.0021886170000016136,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.010417976999974599,
+                                                                    "count": 8,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.010417976999974599
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.031868248999955995,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.00022133699997084477,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.00022066799999720388,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00022066799999720388
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.03067702699996744,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.03067702699996744
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.0007492170000205078,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0001665239999510959,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.0005826930000694119,
+                                                                            "count": 8,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.0005826930000694119
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 399.31868424500624,
+                                                    "count": 63651,
+                                                    "is_parallel": true,
+                                                    "self": 11.94500670706384,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 9.272525469963682,
+                                                            "count": 63651,
+                                                            "is_parallel": true,
+                                                            "self": 9.272525469963682
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 343.31836329697194,
+                                                            "count": 63651,
+                                                            "is_parallel": true,
+                                                            "self": 343.31836329697194
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 34.78278877100678,
+                                                            "count": 63651,
+                                                            "is_parallel": true,
+                                                            "self": 8.213779039975861,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 26.569009731030917,
+                                                                    "count": 509208,
+                                                                    "is_parallel": true,
+                                                                    "self": 26.569009731030917
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 352.47472083299954,
+                            "count": 63652,
+                            "self": 1.356177588014532,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 64.77816243298406,
+                                    "count": 63652,
+                                    "self": 62.96707069398411,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 1.8110917389999486,
+                                            "count": 10,
+                                            "self": 1.8110917389999486
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 286.34038081200094,
+                                    "count": 447,
+                                    "self": 153.11913995300836,
+                                    "children": {
+                                        "TorchPPOOptimizer.update": {
+                                            "total": 133.2212408589926,
+                                            "count": 22818,
+                                            "self": 133.2212408589926
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 7.010000899754232e-07,
+                    "count": 1,
+                    "self": 7.010000899754232e-07
+                },
+                "TrainerController._save_models": {
+                    "total": 0.07953180699996665,
+                    "count": 1,
+                    "self": 0.0005698600000414444,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.0789619469999252,
+                            "count": 1,
+                            "self": 0.0789619469999252
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,110 @@
+{
+    "Pyramids": {
+        "checkpoints": [
+            {
+                "steps": 199893,
+                "file_path": "results/Pyramids1/Pyramids/Pyramids-199893.onnx",
+                "reward": -0.9996000528335571,
+                "creation_time": 1787394372.4959798,
+                "auxillary_file_paths": [
+                    "results/Pyramids1/Pyramids/Pyramids-199893.pt"
+                ]
+            },
+            {
+                "steps": 299951,
+                "file_path": "results/Pyramids1/Pyramids/Pyramids-299951.onnx",
+                "reward": 0.10639996826648712,
+                "creation_time": 1787394459.1874733,
+                "auxillary_file_paths": [
+                    "results/Pyramids1/Pyramids/Pyramids-299951.pt"
+                ]
+            },
+            {
+                "steps": 399927,
+                "file_path": "results/Pyramids1/Pyramids/Pyramids-399927.onnx",
+                "reward": null,
+                "creation_time": 1787394545.4466596,
+                "auxillary_file_paths": [
+                    "results/Pyramids1/Pyramids/Pyramids-399927.pt"
+                ]
+            },
+            {
+                "steps": 499945,
+                "file_path": "results/Pyramids1/Pyramids/Pyramids-499945.onnx",
+                "reward": null,
+                "creation_time": 1787394633.103358,
+                "auxillary_file_paths": [
+                    "results/Pyramids1/Pyramids/Pyramids-499945.pt"
+                ]
+            },
+            {
+                "steps": 599997,
+                "file_path": "results/Pyramids1/Pyramids/Pyramids-599997.onnx",
+                "reward": null,
+                "creation_time": 1787394723.0869727,
+                "auxillary_file_paths": [
+                    "results/Pyramids1/Pyramids/Pyramids-599997.pt"
+                ]
+            },
+            {
+                "steps": 699963,
+                "file_path": "results/Pyramids1/Pyramids/Pyramids-699963.onnx",
+                "reward": 1.0569999068975449,
+                "creation_time": 1787394814.8991609,
+                "auxillary_file_paths": [
+                    "results/Pyramids1/Pyramids/Pyramids-699963.pt"
+                ]
+            },
+            {
+                "steps": 799893,
+                "file_path": "results/Pyramids1/Pyramids/Pyramids-799893.onnx",
+                "reward": 1.841999962925911,
+                "creation_time": 1787394904.7333565,
+                "auxillary_file_paths": [
+                    "results/Pyramids1/Pyramids/Pyramids-799893.pt"
+                ]
+            },
+            {
+                "steps": 899921,
+                "file_path": "results/Pyramids1/Pyramids/Pyramids-899921.onnx",
+                "reward": 0.7231332709391912,
+                "creation_time": 1787394994.0133567,
+                "auxillary_file_paths": [
+                    "results/Pyramids1/Pyramids/Pyramids-899921.pt"
+                ]
+            },
+            {
+                "steps": 999996,
+                "file_path": "results/Pyramids1/Pyramids/Pyramids-999996.onnx",
+                "reward": 1.8219999969005585,
+                "creation_time": 1787395087.0048172,
+                "auxillary_file_paths": [
+                    "results/Pyramids1/Pyramids/Pyramids-999996.pt"
+                ]
+            },
+            {
+                "steps": 1000076,
+                "file_path": "results/Pyramids1/Pyramids/Pyramids-1000076.onnx",
+                "reward": 1.8147500269114971,
+                "creation_time": 1787395087.0883884,
+                "auxillary_file_paths": [
+                    "results/Pyramids1/Pyramids/Pyramids-1000076.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 1000076,
+            "file_path": "results/Pyramids1/Pyramids.onnx",
+            "reward": 1.8147500269114971,
+            "creation_time": 1787395087.0883884,
+            "auxillary_file_paths": [
+                "results/Pyramids1/Pyramids/Pyramids-1000076.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "1.2.0.dev0",
+        "torch_version": "2.8.0+cu128"
+    }
+}