ppo agent for Pyramids

Pyramids.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0815a7fad8019b885e33c3ecfa941f442811b579ca7ec29b10b8ac770976d20
+size 1420238

Pyramids/Pyramids-100093.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0815a7fad8019b885e33c3ecfa941f442811b579ca7ec29b10b8ac770976d20
+size 1420238

Pyramids/Pyramids-100093.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ca9f5065cf6504582a0f4b2d9f9ddd542fca3ecbdd566fc8bb073b32679b443
+size 8655149

Pyramids/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:828ea607e50270751b73990a820868806ec6345d1da22b600e1aa72798d21c26
+size 8654754

README.md

@@ -0,0 +1,35 @@
+---
+library_name: ml-agents
+tags:
+- Pyramids
+- deep-reinforcement-learning
+- reinforcement-learning
+- ML-Agents-Pyramids
+- ml-agents
+model-index:
+- name: ppo
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: ML-Agents-Pyramids
+      type: ML-Agents-Pyramids
+    metrics:
+    - type: mean_reward
+      value: -1.00 +/- 0.00
+      name: mean_reward
+      verified: false
+---
+# **ppo** Agent playing **Pyramids**
+
+This is a trained model of a **ppo** agent playing **Pyramids**, trained with Unity ML-Agents as part of the Hugging Face Deep Reinforcement Learning Course.
+
+## Evaluation
+
+Real inference run with the exported ONNX policy in the Unity environment.
+
+- episodes: 60
+- mean_reward: -1.000
+- std_reward: 0.000
+- score (mean - std): -1.000

configuration.yaml

@@ -0,0 +1,94 @@
+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: 100000
+    time_horizon: 128
+    summary_freq: 2000
+    threaded: false
+    self_play: null
+    behavioral_cloning: null
+env_settings:
+  env_path: ./envs/Startup/Startup.app
+  env_args:
+  - --mlagents-scene-name
+  - Assets/ML-Agents/Examples/Pyramids/Scenes/Pyramids.unity
+  base_port: 6080
+  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: Pyramids2
+  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 +1,311 @@
+Mono path[0] = '/Volumes/MINGLE_PROJECTS/项目库/06_知行研习/AI学习考试/deep-rl-course/mlagents/envs/Startup/Startup.app/Contents/Resources/Data/Managed'
+Mono config path = '/Volumes/MINGLE_PROJECTS/项目库/06_知行研习/AI学习考试/deep-rl-course/mlagents/envs/Startup/Startup.app/Contents/MonoBleedingEdge/etc'
+New input system (experimental) initialized
+Initialize engine version: 2022.3.4f1 (35713cd46cd7)
+[Subsystems] Discovering subsystems at path /Volumes/MINGLE_PROJECTS/项目库/06_知行研习/AI学习考试/deep-rl-course/mlagents/envs/Startup/Startup.app/Contents/Resources/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
+- Loaded All Assemblies, in  0.441 seconds
+- Finished resetting the current domain, in  0.027 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)
+UnloadTime: 3.020875 ms
+Command line arguments passed: /Volumes/MINGLE_PROJECTS/项目库/06_知行研习/AI学习考试/deep-rl-course/mlagents/./envs/Startup/Startup.app/Contents/MacOS/UnityEnvironment -nographics -batchmode --mlagents-port 6080 -logFile /Volumes/MINGLE_PROJECTS/项目库/06_知行研习/AI学习考试/deep-rl-course/mlagents/results/Pyramids2/run_logs/Player-0.log --mlagents-scene-name Assets/ML-Agents/Examples/Pyramids/Scenes/Pyramids.unity
+ERROR: Shader Legacy Shaders/VertexLit 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?
+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?
+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: '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?
+Unloading 6 Unused Serialized files (Serialized files now loaded: 0)
+UnloadTime: 0.213667 ms
+Registered Communicator in Agent.
+Unloading 8 unused Assets to reduce memory usage. Loaded Objects now: 4492.
+Total: 11.875708 ms (FindLiveObjects: 0.202041 ms CreateObjectMapping: 0.034167 ms MarkObjects: 11.579542 ms  DeleteObjects: 0.059583 ms)
+
+ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+Setting up 5 worker threads for Enlighten.
+Memory Statistics:
+[ALLOC_TEMP_TLS] TLS Allocator
+  StackAllocators : 
+    [ALLOC_TEMP_MAIN]
+      Peak usage frame count: [8.0 KB-16.0 KB]: 128 frames, [16.0 KB-32.0 KB]: 1205 frames, [32.0 KB-64.0 KB]: 508 frames, [64.0 KB-128.0 KB]: 58 frames, [2.0 MB-4.0 MB]: 1 frames
+      Initial Block Size 4.0 MB
+      Current Block Size 4.0 MB
+      Peak Allocated Bytes 2.1 MB
+      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_Loading.PreloadManager]
+      Initial Block Size 256.0 KB
+      Current Block Size 284.0 KB
+      Peak Allocated Bytes 213.8 KB
+      Overflow Count 9
+    [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_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 7]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.worker 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 12]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.worker 2]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.worker 9]
+      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 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 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 8]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.worker 10]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.worker 1]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_EnlightenWorker] x 5
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 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 8.3 KB
+      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 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_AssetGarbageCollectorHelper] x 9
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.worker 15]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 0 B
+      Overflow Count 0
+    [ALLOC_TEMP_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_OSX HID Input]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 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_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_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 8]
+      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 14]
+      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 170 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_DEFAULT] Dual Thread Allocator
+  Peak main deferred allocation count 10431
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 2.7 MB
+    [ALLOC_DEFAULT_MAIN]
+      Peak usage frame count: [32.0 MB-64.0 MB]: 1900 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 3
+      Peak Allocated memory 57.0 MB
+      Peak Large allocation bytes 16.0 MB
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [1.0 MB-2.0 MB]: 1 frames, [4.0 MB-8.0 MB]: 1899 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 6.5 MB
+      Peak Large allocation bytes 0 B
+[ALLOC_TEMP_JOB_1_FRAME]
+  Initial Block Size 2.0 MB
+  Used Block Count 0
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_TEMP_JOB_2_FRAMES]
+  Initial Block Size 2.0 MB
+  Used Block Count 0
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_TEMP_JOB_4_FRAMES (JobTemp)]
+  Initial Block Size 2.0 MB
+  Used Block Count 1
+  Overflow Count (too large) 0
+  Overflow Count (full) 0
+[ALLOC_TEMP_JOB_ASYNC (Background)]
+  Initial Block Size 1.0 MB
+  Used Block Count 1
+  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 2.7 MB
+    [ALLOC_GFX_MAIN]
+      Peak usage frame count: [32.0 KB-64.0 KB]: 1899 frames, [64.0 KB-128.0 KB]: 1 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 65.8 KB
+      Peak Large allocation bytes 0 B
+    [ALLOC_GFX_THREAD]
+      Peak usage frame count: [64.0 KB-128.0 KB]: 1900 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 66.8 KB
+      Peak Large allocation bytes 0 B
+[ALLOC_CACHEOBJECTS] Dual Thread Allocator
+  Peak main deferred allocation count 31
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 2.7 MB
+    [ALLOC_CACHEOBJECTS_MAIN]
+      Peak usage frame count: [0.5 MB-1.0 MB]: 299 frames, [1.0 MB-2.0 MB]: 1601 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: [0.5 MB-1.0 MB]: 1899 frames, [4.0 MB-8.0 MB]: 1 frames
+      Requested Block Size 4.0 MB
+      Peak Block count 2
+      Peak Allocated memory 4.1 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 2.7 MB
+    [ALLOC_TYPETREE_MAIN]
+      Peak usage frame count: [0-1.0 KB]: 1900 frames
+      Requested Block Size 2.0 MB
+      Peak Block count 1
+      Peak Allocated memory 112 B
+      Peak Large allocation bytes 0 B
+    [ALLOC_TYPETREE_THREAD]
+      Peak usage frame count: [1.0 KB-2.0 KB]: 1900 frames
+      Requested Block Size 2.0 MB
+      Peak Block count 1
+      Peak Allocated memory 1.9 KB
+      Peak Large allocation bytes 0 B

run_logs/timers.json

@@ -0,0 +1,349 @@
+{
+    "name": "root",
+    "gauges": {
+        "Pyramids.Policy.Entropy.mean": {
+            "value": 0.9082182049751282,
+            "min": 0.87479168176651,
+            "max": 1.6093244552612305,
+            "count": 50
+        },
+        "Pyramids.Policy.Entropy.sum": {
+            "value": 1860.0308837890625,
+            "min": 797.4410400390625,
+            "max": 3295.896484375,
+            "count": 50
+        },
+        "Pyramids.Step.mean": {
+            "value": 99965.0,
+            "min": 1920.0,
+            "max": 99965.0,
+            "count": 50
+        },
+        "Pyramids.Step.sum": {
+            "value": 99965.0,
+            "min": 1920.0,
+            "max": 99965.0,
+            "count": 50
+        },
+        "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
+            "value": -0.07558449357748032,
+            "min": -0.10592581331729889,
+            "max": 0.12113308906555176,
+            "count": 50
+        },
+        "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
+            "value": -1.209351897239685,
+            "min": -1.680419683456421,
+            "max": 1.9381294250488281,
+            "count": 50
+        },
+        "Pyramids.Policy.RndValueEstimate.mean": {
+            "value": 0.09358764439821243,
+            "min": -0.14957760274410248,
+            "max": 0.2111683189868927,
+            "count": 50
+        },
+        "Pyramids.Policy.RndValueEstimate.sum": {
+            "value": 1.497402310371399,
+            "min": -2.3932416439056396,
+            "max": 3.378693103790283,
+            "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
+        },
+        "Pyramids.Losses.PolicyLoss.mean": {
+            "value": 0.06861115565767423,
+            "min": 0.05883824355343635,
+            "max": 0.08491418677537392,
+            "count": 31
+        },
+        "Pyramids.Losses.PolicyLoss.sum": {
+            "value": 0.06861115565767423,
+            "min": 0.05883824355343635,
+            "max": 0.08491418677537392,
+            "count": 31
+        },
+        "Pyramids.Losses.ValueLoss.mean": {
+            "value": 0.00031524660586174357,
+            "min": 0.0002118563619054233,
+            "max": 0.025657440661840763,
+            "count": 31
+        },
+        "Pyramids.Losses.ValueLoss.sum": {
+            "value": 0.00031524660586174357,
+            "min": 0.0002118563619054233,
+            "max": 0.025657440661840763,
+            "count": 31
+        },
+        "Pyramids.Policy.LearningRate.mean": {
+            "value": 4.89099837000006e-07,
+            "min": 4.89099837000006e-07,
+            "max": 0.00028771200409599993,
+            "count": 31
+        },
+        "Pyramids.Policy.LearningRate.sum": {
+            "value": 4.89099837000006e-07,
+            "min": 4.89099837000006e-07,
+            "max": 0.00028771200409599993,
+            "count": 31
+        },
+        "Pyramids.Policy.Epsilon.mean": {
+            "value": 0.10016300000000002,
+            "min": 0.10016300000000002,
+            "max": 0.19590400000000005,
+            "count": 31
+        },
+        "Pyramids.Policy.Epsilon.sum": {
+            "value": 0.10016300000000002,
+            "min": 0.10016300000000002,
+            "max": 0.19590400000000005,
+            "count": 31
+        },
+        "Pyramids.Policy.Beta.mean": {
+            "value": 2.6283700000000194e-05,
+            "min": 2.6283700000000194e-05,
+            "max": 0.0095908096,
+            "count": 31
+        },
+        "Pyramids.Policy.Beta.sum": {
+            "value": 2.6283700000000194e-05,
+            "min": 2.6283700000000194e-05,
+            "max": 0.0095908096,
+            "count": 31
+        },
+        "Pyramids.Losses.RNDLoss.mean": {
+            "value": 0.06737803667783737,
+            "min": 0.06737803667783737,
+            "max": 0.7952181696891785,
+            "count": 31
+        },
+        "Pyramids.Losses.RNDLoss.sum": {
+            "value": 0.06737803667783737,
+            "min": 0.06737803667783737,
+            "max": 0.7952181696891785,
+            "count": 31
+        },
+        "Pyramids.Environment.EpisodeLength.mean": {
+            "value": 996.7142857142857,
+            "min": 744.0,
+            "max": 999.0,
+            "count": 12
+        },
+        "Pyramids.Environment.EpisodeLength.sum": {
+            "value": 13954.0,
+            "min": 744.0,
+            "max": 15984.0,
+            "count": 12
+        },
+        "Pyramids.Environment.CumulativeReward.mean": {
+            "value": -0.8547286210315568,
+            "min": -1.0000000521540642,
+            "max": 1.2559999972581863,
+            "count": 15
+        },
+        "Pyramids.Environment.CumulativeReward.sum": {
+            "value": -11.966200694441795,
+            "min": -15.000000782310963,
+            "max": 1.2559999972581863,
+            "count": 15
+        },
+        "Pyramids.Policy.ExtrinsicReward.mean": {
+            "value": -0.8547286210315568,
+            "min": -1.0000000521540642,
+            "max": 1.2559999972581863,
+            "count": 15
+        },
+        "Pyramids.Policy.ExtrinsicReward.sum": {
+            "value": -11.966200694441795,
+            "min": -15.000000782310963,
+            "max": 1.2559999972581863,
+            "count": 15
+        },
+        "Pyramids.Policy.RndReward.mean": {
+            "value": 0.775420717895031,
+            "min": 0.7220818847417831,
+            "max": 6.420726441343626,
+            "count": 15
+        },
+        "Pyramids.Policy.RndReward.sum": {
+            "value": 10.855890050530434,
+            "min": 0.7220818847417831,
+            "max": 96.31089662015438,
+            "count": 15
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1790098312",
+        "python_version": "3.10.12 (main, Jul 26 2023, 19:37:41) [Clang 16.0.3 ]",
+        "command_line_arguments": "./.venv-mla/bin/mlagents-learn ./config/Pyramids_run.yaml --env=./envs/Startup/Startup.app --run-id=Pyramids2 --results-dir=./results --no-graphics --base-port=6080 --force --env-args --mlagents-scene-name Assets/ML-Agents/Examples/Pyramids/Scenes/Pyramids.unity",
+        "mlagents_version": "1.1.0",
+        "mlagents_envs_version": "1.1.0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "2.4.1",
+        "numpy_version": "1.23.5",
+        "end_time_seconds": "1790100893"
+    },
+    "total": 2580.962755958026,
+    "count": 1,
+    "self": 0.9887815830297768,
+    "children": {
+        "run_training.setup": {
+            "total": 0.14984104200266302,
+            "count": 1,
+            "self": 0.14984104200266302
+        },
+        "TrainerController.start_learning": {
+            "total": 2579.8241333329934,
+            "count": 1,
+            "self": 0.25993692729389295,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 7.088897333014756,
+                    "count": 1,
+                    "self": 7.088897333014756
+                },
+                "TrainerController.advance": {
+                    "total": 2572.3850559476414,
+                    "count": 6337,
+                    "self": 0.28941082960227504,
+                    "children": {
+                        "env_step": {
+                            "total": 2046.8436690266826,
+                            "count": 6337,
+                            "self": 1975.1657304082182,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 71.30303015460959,
+                                    "count": 6337,
+                                    "self": 2.3501474938821048,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 68.95288266072748,
+                                            "count": 6331,
+                                            "self": 68.95288266072748
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 0.37490846385480836,
+                                    "count": 6337,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 2573.1003180179396,
+                                            "count": 6337,
+                                            "is_parallel": true,
+                                            "self": 626.1661453726701,
+                                            "children": {
+                                                "steps_from_proto": {
+                                                    "total": 0.0007749159703962505,
+                                                    "count": 1,
+                                                    "is_parallel": true,
+                                                    "self": 0.00017699989257380366,
+                                                    "children": {
+                                                        "_process_rank_one_or_two_observation": {
+                                                            "total": 0.0005979160778224468,
+                                                            "count": 8,
+                                                            "is_parallel": true,
+                                                            "self": 0.0005979160778224468
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 1946.933397729299,
+                                                    "count": 6337,
+                                                    "is_parallel": true,
+                                                    "self": 1.5140102336881682,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 4.4776417510584,
+                                                            "count": 6337,
+                                                            "is_parallel": true,
+                                                            "self": 4.4776417510584
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 1932.070827980293,
+                                                            "count": 6337,
+                                                            "is_parallel": true,
+                                                            "self": 1932.070827980293
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 8.870917764259502,
+                                                            "count": 6337,
+                                                            "is_parallel": true,
+                                                            "self": 1.8004718804731965,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 7.070445883786306,
+                                                                    "count": 50696,
+                                                                    "is_parallel": true,
+                                                                    "self": 7.070445883786306
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 525.2519760913565,
+                            "count": 6337,
+                            "self": 0.3286859543877654,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 39.73427055275533,
+                                    "count": 6337,
+                                    "self": 39.73427055275533
+                                },
+                                "_update_policy": {
+                                    "total": 485.1890195842134,
+                                    "count": 31,
+                                    "self": 47.87891324906377,
+                                    "children": {
+                                        "TorchPPOOptimizer.update": {
+                                            "total": 437.3101063351496,
+                                            "count": 2325,
+                                            "self": 437.3101063351496
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 1.2500095181167126e-06,
+                    "count": 1,
+                    "self": 1.2500095181167126e-06
+                },
+                "TrainerController._save_models": {
+                    "total": 0.09024187503382564,
+                    "count": 1,
+                    "self": 0.0024025000166147947,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.08783937501721084,
+                            "count": 1,
+                            "self": 0.08783937501721084
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,29 @@
+{
+    "Pyramids": {
+        "checkpoints": [
+            {
+                "steps": 100093,
+                "file_path": "./results/Pyramids2/Pyramids/Pyramids-100093.onnx",
+                "reward": null,
+                "creation_time": 1790100892.4495502,
+                "auxillary_file_paths": [
+                    "./results/Pyramids2/Pyramids/Pyramids-100093.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 100093,
+            "file_path": "./results/Pyramids2/Pyramids.onnx",
+            "reward": null,
+            "creation_time": 1790100892.4495502,
+            "auxillary_file_paths": [
+                "./results/Pyramids2/Pyramids/Pyramids-100093.pt"
+            ]
+        }
+    },
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "1.1.0",
+        "torch_version": "2.4.1"
+    }
+}