default-ish parameters

Pyramids.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c885997a05d7d1d5db46c516ca869740a9ef45a10aa432b6b027a1a8d4d064f
+size 1420238

Pyramids/Pyramids-2499898.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8448ab0643f50b4050f3f821b16c585ecb49d128958e0896adc354283990bc52
+size 1420238

Pyramids/Pyramids-2499898.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31ec61ecbdd9db92a246d4a2aa1967a1c196bf0be74feb2e81b5e74218762ba2
+size 8655228

Pyramids/Pyramids-2499947.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a333f3fc509df4abb011379ca4971b290e7722f1c136581c969986f5f8f86157
+size 1420238

Pyramids/Pyramids-2499947.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fedfb35df530fe2580442ef5673abda031ce967665abc2867388777bb409dedd
+size 8656252

Pyramids/Pyramids-2999909.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:639c7219a73f162cf64897ca2cbf964df100a6682af3282a07900d5725c92970
+size 1420238

Pyramids/Pyramids-2999909.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:634c9c8a10c14020533b408cb3d4f12170903f006fb5c2fdb55bc0eb4a59aa6e
+size 8655228

Pyramids/Pyramids-2999964.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fcf6c90982a45cb47c3b3a026edfd3cfe419b6b870a2d1fa08bb9d2447b49fd
+size 1420238

Pyramids/Pyramids-2999964.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91ac423ce3e5e8c1d6ca7a0e63296dcef9747bf209f6b04ce1039f09b9ec7cd8
+size 8656252

Pyramids/Pyramids-3499872.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a88ebfa12d7077c9bf72c345e1850828a1a57facf9deace0e9dc397c92f82cb6
+size 1420238

Pyramids/Pyramids-3499872.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:867c73e83f85a2129215a40546a4e735e07a8003c043928069956dd4d9208882
+size 8655228

Pyramids/Pyramids-3499941.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:619419729346bb95693799b1f3fe7607b0385f9ea8b5222e187c89733218df1e
+size 1420238

Pyramids/Pyramids-3499941.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8940ec6f9640a328c784c0e6d56837f93a72795a039de0ee626fb35db6cce334
+size 8656252

Pyramids/Pyramids-3999926.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7095aee6d8cdb1786606956eea616db882841c28a1b2abb900af98796c086e5b
+size 1420238

Pyramids/Pyramids-3999926.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9356420d2b917f4b3bbd363949aa453767c50061d09b32bd89b92096c02a206b
+size 8656252

Pyramids/Pyramids-3999942.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a1e65e04f3c7a14fb09f59a36bf8304db179b76d9f86b4cc45f73bc83b81bc6
+size 1420238

Pyramids/Pyramids-3999942.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c884c2ba22ecb3218ae2a0805bb3fd705b7932a33d39c6bbf500850629ae8a52
+size 8655228

Pyramids/Pyramids-4194305.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51abe9c36f56bc6276b45f98d4f9984b931dc72503ed016066de12675252ed25
+size 1420238

Pyramids/Pyramids-4194305.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9185f123ea9b3b82a4a0576098b8fba663f48c227882ddfd09d69e9af93cd4d
+size 8655228

Pyramids/Pyramids-4194384.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c885997a05d7d1d5db46c516ca869740a9ef45a10aa432b6b027a1a8d4d064f
+size 1420238

Pyramids/Pyramids-4194384.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:100c53392be7666e97c08eb6b7a5a0f62fb45f2ced80c5a392814b963860bfdb
+size 8656252

Pyramids/Pyramids-44520.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e498f0b5babf8e5e570399b487cbcac29c8fcf44820295d7165c5213233f9cb
+size 1420238

Pyramids/Pyramids-44520.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d9ebe1e5423dc16ba7513a65c3243050f42f3b648d749ddff33ac51048c418e
+size 8656094

Pyramids/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b76f957799f8fe4b301ee39f9675afa274f7a2e431bde385f5251d2e89cd49fc
+size 8655778

Pyramids/events.out.tfevents.1738594274.hrichter-5950x.11130.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:edb73a91eba1a8235c6cf8f65d369d63d46cd0ddee411f5185ee23f66757a851
+size 1132782

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: knoffel/ppo-Pyramids-RND
+  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": 4194304, "time_horizon": 128, "summary_freq": 30000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/linux/Pyramids/Pyramids", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "timeout_wait": 60, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true, "no_graphics_monitor": false}, "environment_parameters": null, "checkpoint_settings": {"run_id": "Pyramids Training RND", "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: 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: 4194304
+    time_horizon: 128
+    summary_freq: 30000
+    threaded: false
+    self_play: null
+    behavioral_cloning: null
+env_settings:
+  env_path: ./training-envs-executables/linux/Pyramids/Pyramids
+  env_args: null
+  base_port: 5005
+  num_envs: 1
+  num_areas: 1
+  timeout_wait: 60
+  seed: -1
+  max_lifetime_restarts: 10
+  restarts_rate_limit_n: 1
+  restarts_rate_limit_period_s: 60
+engine_settings:
+  width: 84
+  height: 84
+  quality_level: 5
+  time_scale: 20
+  target_frame_rate: -1
+  capture_frame_rate: 60
+  no_graphics: true
+  no_graphics_monitor: false
+environment_parameters: null
+checkpoint_settings:
+  run_id: Pyramids Training RND
+  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 +1,444 @@
+Mono path[0] = '/home/hrichter/projects/hf_rl_course/training-envs-executables/linux/Pyramids/Pyramids_Data/Managed'
+Mono config path = '/home/hrichter/projects/hf_rl_course/training-envs-executables/linux/Pyramids/Pyramids_Data/MonoBleedingEdge/etc'
+Found 3 interfaces on host : 0) 192.168.101.72 1) 10.113.249.15 2) 172.17.0.1
+Multi-casting "[IP] 192.168.101.72 [Port] 55264 [Flags] 2 [Guid] 1317124028 [EditorId] 764847374 [Version] 1048832 [Id] LinuxPlayer(13,192.168.101.72) [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/hrichter/projects/hf_rl_course/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  0.056 seconds
+ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+ERROR: Shader Legacy Shaders/VertexLit shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+WARNING: Shader Unsupported: 'Autodesk Interactive' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
+ERROR: Shader Autodesk Interactive shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+WARNING: Shader Unsupported: 'Autodesk Interactive' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
+WARNING: Shader Unsupported: 'Legacy Shaders/Diffuse' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
+ERROR: Shader Legacy Shaders/Diffuse shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+WARNING: Shader Unsupported: 'Legacy Shaders/Diffuse' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
+WARNING: Shader Unsupported: 'ML-Agents/GridPattern' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
+ERROR: Shader ML-Agents/GridPattern shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+WARNING: Shader Unsupported: 'ML-Agents/GridPattern' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
+WARNING: Shader Unsupported: 'Standard' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
+ERROR: Shader Standard shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+WARNING: Shader Unsupported: 'Standard' - All subshaders removed
+WARNING: Shader Did you use #pragma only_renderers and omit this platform?
+WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
+UnloadTime: 0.529120 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 16 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]: 8007 frames, [32.0 KB-64.0 KB]: 46134 frames, [64.0 KB-128.0 KB]: 24525 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_Job.Worker 18]
+      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 8]
+      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_Job.Worker 27]
+      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 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_Job.Worker 21]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 25]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 13]
+      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 2]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 22]
+      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_Job.Worker 15]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 12]
+      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 251.6 KB
+      Overflow Count 4
+    [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_Job.Worker 17]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 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_Profiler.Dispatcher]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 3.8 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 14]
+      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 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_Job.Worker 11]
+      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_Job.Worker 0]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_EnlightenWorker] x 16
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 9]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 9]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Loading.AsyncRead]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 128 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 16]
+      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_Job.Worker 20]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 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_Job.Worker 30]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 26]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 29]
+      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 15]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.Worker 7]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_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 23]
+      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 24]
+      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 31
+      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 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_Background Job.Worker 14]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 28]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 7]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Job.Worker 19]
+      Initial Block Size 256.0 KB
+      Current Block Size 256.0 KB
+      Peak Allocated Bytes 0.8 KB
+      Overflow Count 0
+[ALLOC_MEMORYPROFILER]
+  Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 78368 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 12115
+    [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]: 78666 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 3
+      Peak Allocated memory 30.9 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [16.0 MB-32.0 MB]: 78667 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 30.9 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]: 78666 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]: 78667 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]: 78368 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]: 78666 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]: 78667 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]: 78667 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]: 78667 frames
+  Requested Block Size 16.0 MB
+  Peak Block count 1
+  Peak Allocated memory 54.4 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":1738598179813,"processId":11220,"allocatedMemory":2006255,"memoryLabels":[{"Default":9033},{"Permanent":1264},{"NewDelete":12801},{"Thread":35300},{"Manager":33551},{"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":3541},{"DynamicArray":30868},{"HashMap":7680},{"Utility":13600},{"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": 0.12661775946617126,
+            "min": 0.12661775946617126,
+            "max": 1.3403754234313965,
+            "count": 139
+        },
+        "Pyramids.Policy.Entropy.sum": {
+            "value": 3745.85986328125,
+            "min": 3745.85986328125,
+            "max": 40661.62890625,
+            "count": 139
+        },
+        "Pyramids.Step.mean": {
+            "value": 4169953.0,
+            "min": 29952.0,
+            "max": 4169953.0,
+            "count": 139
+        },
+        "Pyramids.Step.sum": {
+            "value": 4169953.0,
+            "min": 29952.0,
+            "max": 4169953.0,
+            "count": 139
+        },
+        "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 0.8268681764602661,
+            "min": -0.11072057485580444,
+            "max": 0.9321785569190979,
+            "count": 139
+        },
+        "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 247.23358154296875,
+            "min": -26.683658599853516,
+            "max": 293.18743896484375,
+            "count": 139
+        },
+        "Pyramids.Policy.RndValueEstimate.mean": {
+            "value": 0.009303764440119267,
+            "min": -0.042200781404972076,
+            "max": 0.6160295009613037,
+            "count": 139
+        },
+        "Pyramids.Policy.RndValueEstimate.sum": {
+            "value": 2.781825542449951,
+            "min": -11.09880542755127,
+            "max": 145.99899291992188,
+            "count": 139
+        },
+        "Pyramids.Losses.PolicyLoss.mean": {
+            "value": 0.06799422354476216,
+            "min": 0.06394597697840225,
+            "max": 0.07374791761004909,
+            "count": 139
+        },
+        "Pyramids.Losses.PolicyLoss.sum": {
+            "value": 1.0199133531714324,
+            "min": 0.5003612831822194,
+            "max": 1.0699331861687824,
+            "count": 139
+        },
+        "Pyramids.Losses.ValueLoss.mean": {
+            "value": 0.014920670442127934,
+            "min": 0.0001861820094411787,
+            "max": 0.016767832649567136,
+            "count": 139
+        },
+        "Pyramids.Losses.ValueLoss.sum": {
+            "value": 0.223810056631919,
+            "min": 0.002420366122735323,
+            "max": 0.2347496570939399,
+            "count": 139
+        },
+        "Pyramids.Policy.LearningRate.mean": {
+            "value": 2.8299225506830216e-06,
+            "min": 2.8299225506830216e-06,
+            "max": 0.00029884382013985764,
+            "count": 139
+        },
+        "Pyramids.Policy.LearningRate.sum": {
+            "value": 4.2448838260245327e-05,
+            "min": 4.2448838260245327e-05,
+            "max": 0.004001000713742209,
+            "count": 139
+        },
+        "Pyramids.Policy.Epsilon.mean": {
+            "value": 0.10094327449798585,
+            "min": 0.10094327449798585,
+            "max": 0.1996146065848214,
+            "count": 139
+        },
+        "Pyramids.Policy.Epsilon.sum": {
+            "value": 1.5141491174697876,
+            "min": 1.3973022460937499,
+            "max": 2.8336668491363524,
+            "count": 139
+        },
+        "Pyramids.Policy.Beta.mean": {
+            "value": 0.00010423312234878539,
+            "min": 0.00010423312234878539,
+            "max": 0.00996149919782366,
+            "count": 139
+        },
+        "Pyramids.Policy.Beta.sum": {
+            "value": 0.0015634968352317808,
+            "min": 0.0015634968352317808,
+            "max": 0.13338331822872163,
+            "count": 139
+        },
+        "Pyramids.Losses.RNDLoss.mean": {
+            "value": 0.005316837690770626,
+            "min": 0.00511825829744339,
+            "max": 0.5967947840690613,
+            "count": 139
+        },
+        "Pyramids.Losses.RNDLoss.sum": {
+            "value": 0.07975256443023682,
+            "min": 0.07195756584405899,
+            "max": 4.177563667297363,
+            "count": 139
+        },
+        "Pyramids.Environment.EpisodeLength.mean": {
+            "value": 230.81203007518798,
+            "min": 189.74074074074073,
+            "max": 999.0,
+            "count": 139
+        },
+        "Pyramids.Environment.EpisodeLength.sum": {
+            "value": 30698.0,
+            "min": 15984.0,
+            "max": 33497.0,
+            "count": 139
+        },
+        "Pyramids.Environment.CumulativeReward.mean": {
+            "value": 1.7090150287052743,
+            "min": -1.0000000521540642,
+            "max": 1.8060340087632745,
+            "count": 139
+        },
+        "Pyramids.Environment.CumulativeReward.sum": {
+            "value": 227.29899881780148,
+            "min": -30.17300172895193,
+            "max": 293.1627984791994,
+            "count": 139
+        },
+        "Pyramids.Policy.ExtrinsicReward.mean": {
+            "value": 1.7090150287052743,
+            "min": -1.0000000521540642,
+            "max": 1.8060340087632745,
+            "count": 139
+        },
+        "Pyramids.Policy.ExtrinsicReward.sum": {
+            "value": 227.29899881780148,
+            "min": -30.17300172895193,
+            "max": 293.1627984791994,
+            "count": 139
+        },
+        "Pyramids.Policy.RndReward.mean": {
+            "value": 0.012755914703565142,
+            "min": 0.01059819941069328,
+            "max": 12.678219143301249,
+            "count": 139
+        },
+        "Pyramids.Policy.RndReward.sum": {
+            "value": 1.6965366555741639,
+            "min": 1.5618635597929824,
+            "max": 202.85150629281998,
+            "count": 139
+        },
+        "Pyramids.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 139
+        },
+        "Pyramids.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 139
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1738594273",
+        "python_version": "3.10.16 (main, Dec  4 2024, 08:53:38) [GCC 13.2.0]",
+        "command_line_arguments": "/home/hrichter/projects/hf_rl_course/.venv/bin/mlagents-learn ml-agents/config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training RND --no-graphics --force",
+        "mlagents_version": "1.2.0.dev0",
+        "mlagents_envs_version": "1.2.0.dev0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "2.5.1+cu124",
+        "numpy_version": "1.23.5",
+        "end_time_seconds": "1738598179"
+    },
+    "total": 3905.9609358640005,
+    "count": 1,
+    "self": 0.2180168859999867,
+    "children": {
+        "run_training.setup": {
+            "total": 0.015057243000001108,
+            "count": 1,
+            "self": 0.015057243000001108
+        },
+        "TrainerController.start_learning": {
+            "total": 3905.7278617350003,
+            "count": 1,
+            "self": 2.4446929558953343,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 1.4401749290000225,
+                    "count": 1,
+                    "self": 1.4401749290000225
+                },
+                "TrainerController.advance": {
+                    "total": 3901.7912311101054,
+                    "count": 273835,
+                    "self": 2.5200714938191595,
+                    "children": {
+                        "env_step": {
+                            "total": 2490.929578938104,
+                            "count": 273835,
+                            "self": 2185.725352476874,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 303.5715818341579,
+                                    "count": 273835,
+                                    "self": 8.230848409151918,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 295.34073342500596,
+                                            "count": 262221,
+                                            "self": 295.34073342500596
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 1.6326446270722954,
+                                    "count": 273835,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 3901.762734884753,
+                                            "count": 273835,
+                                            "is_parallel": true,
+                                            "self": 1897.81562272177,
+                                            "children": {
+                                                "run_training.setup": {
+                                                    "total": 0.0,
+                                                    "count": 0,
+                                                    "is_parallel": true,
+                                                    "self": 0.0,
+                                                    "children": {
+                                                        "steps_from_proto": {
+                                                            "total": 0.0009466559999964375,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.00022919100001672632,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 0.0007174649999797111,
+                                                                    "count": 8,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.0007174649999797111
+                                                                }
+                                                            }
+                                                        },
+                                                        "UnityEnvironment.step": {
+                                                            "total": 0.02041816700000254,
+                                                            "count": 1,
+                                                            "is_parallel": true,
+                                                            "self": 0.00020874099993761774,
+                                                            "children": {
+                                                                "UnityEnvironment._generate_step_input": {
+                                                                    "total": 0.00019684100004724314,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00019684100004724314
+                                                                },
+                                                                "communicator.exchange": {
+                                                                    "total": 0.01937417099998129,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.01937417099998129
+                                                                },
+                                                                "steps_from_proto": {
+                                                                    "total": 0.0006384140000363914,
+                                                                    "count": 1,
+                                                                    "is_parallel": true,
+                                                                    "self": 0.00014979100001255574,
+                                                                    "children": {
+                                                                        "_process_rank_one_or_two_observation": {
+                                                                            "total": 0.0004886230000238356,
+                                                                            "count": 8,
+                                                                            "is_parallel": true,
+                                                                            "self": 0.0004886230000238356
+                                                                        }
+                                                                    }
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 2003.947112162983,
+                                                    "count": 273834,
+                                                    "is_parallel": true,
+                                                    "self": 47.876944490791175,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 33.30915514407741,
+                                                            "count": 273834,
+                                                            "is_parallel": true,
+                                                            "self": 33.30915514407741
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 1783.656841315873,
+                                                            "count": 273834,
+                                                            "is_parallel": true,
+                                                            "self": 1783.656841315873
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 139.10417121224145,
+                                                            "count": 273834,
+                                                            "is_parallel": true,
+                                                            "self": 30.037486382786255,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 109.0666848294552,
+                                                                    "count": 2190672,
+                                                                    "is_parallel": true,
+                                                                    "self": 109.0666848294552
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 1408.3415806781823,
+                            "count": 273835,
+                            "self": 5.083995277255326,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 274.06235688592847,
+                                    "count": 273835,
+                                    "self": 273.650273610928,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 0.41208327500044106,
+                                            "count": 8,
+                                            "self": 0.41208327500044106
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 1129.1952285149985,
+                                    "count": 1962,
+                                    "self": 609.6197948401142,
+                                    "children": {
+                                        "TorchPPOOptimizer.update": {
+                                            "total": 519.5754336748843,
+                                            "count": 95631,
+                                            "self": 519.5754336748843
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 5.699994289898314e-07,
+                    "count": 1,
+                    "self": 5.699994289898314e-07
+                },
+                "TrainerController._save_models": {
+                    "total": 0.05176217000007455,
+                    "count": 1,
+                    "self": 0.0017888270003822981,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.04997334299969225,
+                            "count": 1,
+                            "self": 0.04997334299969225
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,65 @@
+{
+    "Pyramids": {
+        "checkpoints": [
+            {
+                "steps": 2499947,
+                "file_path": "results/Pyramids Training RND/Pyramids/Pyramids-2499947.onnx",
+                "reward": 1.7487142639500755,
+                "creation_time": 1738596559.9280655,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training RND/Pyramids/Pyramids-2499947.pt"
+                ]
+            },
+            {
+                "steps": 2999964,
+                "file_path": "results/Pyramids Training RND/Pyramids/Pyramids-2999964.onnx",
+                "reward": 1.8416666512688,
+                "creation_time": 1738597042.4574587,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training RND/Pyramids/Pyramids-2999964.pt"
+                ]
+            },
+            {
+                "steps": 3499941,
+                "file_path": "results/Pyramids Training RND/Pyramids/Pyramids-3499941.onnx",
+                "reward": 1.7917142744575227,
+                "creation_time": 1738597523.1721656,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training RND/Pyramids/Pyramids-3499941.pt"
+                ]
+            },
+            {
+                "steps": 3999926,
+                "file_path": "results/Pyramids Training RND/Pyramids/Pyramids-3999926.onnx",
+                "reward": 1.7471999824047089,
+                "creation_time": 1738597995.6053648,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training RND/Pyramids/Pyramids-3999926.pt"
+                ]
+            },
+            {
+                "steps": 4194384,
+                "file_path": "results/Pyramids Training RND/Pyramids/Pyramids-4194384.onnx",
+                "reward": 1.7725454555316404,
+                "creation_time": 1738598179.6111715,
+                "auxillary_file_paths": [
+                    "results/Pyramids Training RND/Pyramids/Pyramids-4194384.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 4194384,
+            "file_path": "results/Pyramids Training RND/Pyramids.onnx",
+            "reward": 1.7725454555316404,
+            "creation_time": 1738598179.6111715,
+            "auxillary_file_paths": [
+                "results/Pyramids Training RND/Pyramids/Pyramids-4194384.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "1.2.0.dev0",
+        "torch_version": "2.5.1+cu124"
+    }
+}