First Push

Pyramids.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e237ba2b4e9a2c9ea582109997767b4fb89e1c6cfdfb8aac7f5693fd35899a0e
+size 1420237

Pyramids/Pyramids-1000100.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e237ba2b4e9a2c9ea582109997767b4fb89e1c6cfdfb8aac7f5693fd35899a0e
+size 1420237

Pyramids/Pyramids-1000100.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d74fa31e33e4e67ea79c637a9001050d2eab9db5160b7a9fb90a19f4e7ede6ae
+size 8655801

Pyramids/Pyramids-499920.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a40c4f67a68451c462de51943f158ff36689574d54e999fa7fef5c564a13272
+size 1420237

Pyramids/Pyramids-499920.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:839eabed8388404b70c10bece0eef2e296ebf02f476fddda8ce3eb66b6d6063a
+size 8655724

Pyramids/Pyramids-999972.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e237ba2b4e9a2c9ea582109997767b4fb89e1c6cfdfb8aac7f5693fd35899a0e
+size 1420237

Pyramids/Pyramids-999972.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a96fd572034915c4c5f94e898cf64f6a5ddcef76e63f0a3fe0e140b0ad491a5
+size 8655724

Pyramids/checkpoint.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fe44986050b8fb7816e154db406f191608492d366ff95ff2b2813fb5c858d72
+size 8655339

Pyramids/events.out.tfevents.1694539621.vmgaming.11316.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e02f26637566be6eb157d91257497ef392c6a7c83912c57bd61b8a92270e624
+size 147605

Pyramids/events.out.tfevents.1694541436.vmgaming.19840.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db98459ea851432ed7ed728901a10defc927f5ceedf73b5a80d561e9b4e0ddad
+size 167926

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: Lethargus/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": 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": 1000000, "time_horizon": 128, "summary_freq": 30000, "threaded": false, "self_play": null, "behavioral_cloning": null}}, "env_settings": {"env_path": "../Pyramids/UnityEnvironment.exe", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true}, "environment_parameters": null, "checkpoint_settings": {"run_id": "Pyramids Training", "initialize_from": null, "load_model": false, "resume": true, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -0,0 +1,90 @@
+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: 1000000
+    time_horizon: 128
+    summary_freq: 30000
+    threaded: false
+    self_play: null
+    behavioral_cloning: null
+env_settings:
+  env_path: ../Pyramids/UnityEnvironment.exe
+  env_args: null
+  base_port: 5005
+  num_envs: 1
+  num_areas: 1
+  seed: -1
+  max_lifetime_restarts: 10
+  restarts_rate_limit_n: 1
+  restarts_rate_limit_period_s: 60
+engine_settings:
+  width: 84
+  height: 84
+  quality_level: 5
+  time_scale: 20
+  target_frame_rate: -1
+  capture_frame_rate: 60
+  no_graphics: true
+environment_parameters: null
+checkpoint_settings:
+  run_id: Pyramids Training
+  initialize_from: null
+  load_model: false
+  resume: true
+  force: false
+  train_model: false
+  inference: false
+  results_dir: results
+torch_settings:
+  device: null
+debug: false

run_logs/Player-0.log

@@ -0,0 +1,282 @@
+Mono path[0] = 'C:/Users/bdonn/Documents/DRL-Explore/Pyramids/UnityEnvironment_Data/Managed'
+Mono config path = 'C:/Users/bdonn/Documents/DRL-Explore/Pyramids/MonoBleedingEdge/etc'
+[Physics::Module] Initialized MultithreadedJobDispatcher with 3 workers.
+Initialize engine version: 2023.1.12f1 (38370f5b2257)
+[Subsystems] Discovering subsystems at path C:/Users/bdonn/Documents/DRL-Explore/Pyramids/UnityEnvironment_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
+C:\build\output\Unity-Technologies\mono\mono\metadata\icall.c:1842:
+C:\build\output\Unity-Technologies\mono\mono\metadata\icall.c:1842:
+C:\build\output\Unity-Technologies\mono\mono\metadata\icall.c:1842:
+C:\build\output\Unity-Technologies\mono\mono\metadata\icall.c:1842:
+C:\build\output\Unity-Technologies\mono\mono\metadata\icall.c:1842:
+C:\build\output\Unity-Technologies\mono\mono\metadata\icall.c:1842:
+C:\build\output\Unity-Technologies\mono\mono\metadata\icall.c:1842:
+C:\build\output\Unity-Technologies\mono\mono\metadata\icall.c:1842:
+C:\build\output\Unity-Technologies\mono\mono\metadata\icall.c:1842:
+- Loaded All Assemblies, in  0.136 seconds
+C:\build\output\Unity-Technologies\mono\mono\metadata\icall.c:1842:
+C:\build\output\Unity-Technologies\mono\mono\metadata\icall.c:1842:
+- Finished resetting the current domain, in  0.002 seconds
+ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+Microsoft Media Foundation video decoding to texture disabled: graphics device is Null, only Direct3D 11 and Direct3D 12 (only on desktop) are supported for hardware-accelerated video decoding.
+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: 0.677900 ms
+Registered Communicator in Agent.
+ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
+Setting up 2 worker threads for Enlighten.
+Memory Statistics:
+[ALLOC_TEMP_TLS] TLS Allocator
+  StackAllocators : 
+    [ALLOC_TEMP_MAIN]
+      Peak usage frame count: [1.0 KB-2.0 KB]: 7845 frames, [64.0 KB-128.0 KB]: 1548 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 4]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 66 B
+      Overflow Count 0
+    [ALLOC_TEMP_Loading.PreloadManager]
+      Initial Block Size 256.0 KB
+      Current Block Size 312.0 KB
+      Peak Allocated Bytes 244.3 KB
+      Overflow Count 5
+    [ALLOC_TEMP_Background Job.worker 3]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 66 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 66 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 66 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 66 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 66 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 66 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 66 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_Background Job.worker 10]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 66 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 66 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 66 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 66 B
+      Overflow Count 0
+    [ALLOC_TEMP_EnlightenWorker] x 2
+      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 0.8 KB
+      Overflow Count 0
+    [ALLOC_TEMP_Background Job.worker 13]
+      Initial Block Size 32.0 KB
+      Current Block Size 32.0 KB
+      Peak Allocated Bytes 66 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 66 B
+      Overflow Count 0
+    [ALLOC_TEMP_AssetGarbageCollectorHelper] x 3
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 66 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 66 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 66 B
+      Overflow Count 0
+    [ALLOC_TEMP_Loading.AsyncRead]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 297 B
+      Overflow Count 0
+    [ALLOC_TEMP_BatchDeleteObjects]
+      Initial Block Size 64.0 KB
+      Current Block Size 64.0 KB
+      Peak Allocated Bytes 66 B
+      Overflow Count 0
+[ALLOC_DEFAULT] Dual Thread Allocator
+  Peak main deferred allocation count 4767
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 2.3 MB
+    [ALLOC_DEFAULT_MAIN]
+      Peak usage frame count: [32.0 MB-64.0 MB]: 9394 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 3
+      Peak Allocated memory 45.4 MB
+      Peak Large allocation bytes 16.0 MB
+    [ALLOC_DEFAULT_THREAD]
+      Peak usage frame count: [4.0 MB-8.0 MB]: 1 frames, [8.0 MB-16.0 MB]: 9393 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 14.4 MB
+      Peak Large allocation bytes 0 B
+[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 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 2.3 MB
+    [ALLOC_GFX_MAIN]
+      Peak usage frame count: [32.0 KB-64.0 KB]: 9393 frames, [64.0 KB-128.0 KB]: 1 frames
+      Requested Block Size 16.0 MB
+      Peak Block count 1
+      Peak Allocated memory 66.3 KB
+      Peak Large allocation bytes 0 B
+    [ALLOC_GFX_THREAD]
+      Peak usage frame count: [64.0 KB-128.0 KB]: 9394 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 3
+    [ALLOC_BUCKET]
+      Large Block size 4.0 MB
+      Used Block count 1
+      Peak Allocated bytes 2.3 MB
+    [ALLOC_CACHEOBJECTS_MAIN]
+      Peak usage frame count: [0.5 MB-1.0 MB]: 46 frames, [1.0 MB-2.0 MB]: 9348 frames
+      Requested Block Size 4.0 MB
+      Peak Block count 1
+      Peak Allocated memory 1.5 MB
+      Peak Large allocation bytes 0 B
+    [ALLOC_CACHEOBJECTS_THREAD]
+      Peak usage frame count: [1.0 MB-2.0 MB]: 9393 frames, [2.0 MB-4.0 MB]: 1 frames
+      Requested Block Size 4.0 MB
+      Peak Block count 1
+      Peak Allocated memory 3.8 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 2.3 MB
+    [ALLOC_TYPETREE_MAIN]
+      Peak usage frame count: [4.0 KB-8.0 KB]: 9394 frames
+      Requested Block Size 2.0 MB
+      Peak Block count 1
+      Peak Allocated memory 4.1 KB
+      Peak Large allocation bytes 0 B
+    [ALLOC_TYPETREE_THREAD]
+      Peak usage frame count: [1.0 KB-2.0 KB]: 9394 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 +1,356 @@
+{
+    "name": "root",
+    "gauges": {
+        "Pyramids.Policy.Entropy.mean": {
+            "value": 0.4531543254852295,
+            "min": 0.4531543254852295,
+            "max": 1.0132265090942383,
+            "count": 17
+        },
+        "Pyramids.Policy.Entropy.sum": {
+            "value": 13427.869140625,
+            "min": 10796.94140625,
+            "max": 30436.46875,
+            "count": 17
+        },
+        "Pyramids.Step.mean": {
+            "value": 989961.0,
+            "min": 509993.0,
+            "max": 989961.0,
+            "count": 17
+        },
+        "Pyramids.Step.sum": {
+            "value": 989961.0,
+            "min": 509993.0,
+            "max": 989961.0,
+            "count": 17
+        },
+        "Pyramids.Policy.ExtrinsicValueEstimate.mean": {
+            "value": 0.314156711101532,
+            "min": -0.020626777783036232,
+            "max": 0.3798234164714813,
+            "count": 17
+        },
+        "Pyramids.Policy.ExtrinsicValueEstimate.sum": {
+            "value": 82.3090591430664,
+            "min": -1.6707689762115479,
+            "max": 98.75408935546875,
+            "count": 17
+        },
+        "Pyramids.Policy.RndValueEstimate.mean": {
+            "value": -0.033712223172187805,
+            "min": -0.033712223172187805,
+            "max": 0.04274001717567444,
+            "count": 17
+        },
+        "Pyramids.Policy.RndValueEstimate.sum": {
+            "value": -8.832602500915527,
+            "min": -8.832602500915527,
+            "max": 11.069664001464844,
+            "count": 17
+        },
+        "Pyramids.Environment.EpisodeLength.mean": {
+            "value": 486.42622950819674,
+            "min": 309.25,
+            "max": 834.025641025641,
+            "count": 17
+        },
+        "Pyramids.Environment.EpisodeLength.sum": {
+            "value": 29672.0,
+            "min": 1237.0,
+            "max": 32696.0,
+            "count": 17
+        },
+        "Pyramids.Environment.CumulativeReward.mean": {
+            "value": 1.1856098056572382,
+            "min": -0.11661030103762944,
+            "max": 1.690750002861023,
+            "count": 17
+        },
+        "Pyramids.Environment.CumulativeReward.sum": {
+            "value": 72.32219814509153,
+            "min": -4.547801740467548,
+            "max": 83.06279814988375,
+            "count": 17
+        },
+        "Pyramids.Policy.ExtrinsicReward.mean": {
+            "value": 1.1856098056572382,
+            "min": -0.11661030103762944,
+            "max": 1.690750002861023,
+            "count": 17
+        },
+        "Pyramids.Policy.ExtrinsicReward.sum": {
+            "value": 72.32219814509153,
+            "min": -4.547801740467548,
+            "max": 83.06279814988375,
+            "count": 17
+        },
+        "Pyramids.Policy.RndReward.mean": {
+            "value": 0.06454847306852825,
+            "min": 0.051007845118874684,
+            "max": 0.12605790901579894,
+            "count": 17
+        },
+        "Pyramids.Policy.RndReward.sum": {
+            "value": 3.937456857180223,
+            "min": 0.20403138047549874,
+            "max": 5.042316360631958,
+            "count": 17
+        },
+        "Pyramids.Losses.PolicyLoss.mean": {
+            "value": 0.06812104680284393,
+            "min": 0.06629444303351203,
+            "max": 0.07307606635534865,
+            "count": 17
+        },
+        "Pyramids.Losses.PolicyLoss.sum": {
+            "value": 0.953694655239815,
+            "min": 0.2923042654213946,
+            "max": 1.0957097937838018,
+            "count": 17
+        },
+        "Pyramids.Losses.ValueLoss.mean": {
+            "value": 0.013116745470878889,
+            "min": 0.0026308059390371535,
+            "max": 0.014184579108890222,
+            "count": 17
+        },
+        "Pyramids.Losses.ValueLoss.sum": {
+            "value": 0.18363443659230444,
+            "min": 0.010523223756148614,
+            "max": 0.19858410752446312,
+            "count": 17
+        },
+        "Pyramids.Policy.LearningRate.mean": {
+            "value": 7.550047483350001e-06,
+            "min": 7.550047483350001e-06,
+            "max": 0.00014832387555872498,
+            "count": 17
+        },
+        "Pyramids.Policy.LearningRate.sum": {
+            "value": 0.00010570066476690001,
+            "min": 0.00010570066476690001,
+            "max": 0.0018691090769639,
+            "count": 17
+        },
+        "Pyramids.Policy.Epsilon.mean": {
+            "value": 0.10251664999999999,
+            "min": 0.10251664999999999,
+            "max": 0.14944127500000004,
+            "count": 17
+        },
+        "Pyramids.Policy.Epsilon.sum": {
+            "value": 1.4352330999999998,
+            "min": 0.5977651000000002,
+            "max": 2.0230361000000006,
+            "count": 17
+        },
+        "Pyramids.Policy.Beta.mean": {
+            "value": 0.00026141333500000007,
+            "min": 0.00026141333500000007,
+            "max": 0.0049491833725,
+            "count": 17
+        },
+        "Pyramids.Policy.Beta.sum": {
+            "value": 0.003659786690000001,
+            "min": 0.003659786690000001,
+            "max": 0.06238130639,
+            "count": 17
+        },
+        "Pyramids.Losses.RNDLoss.mean": {
+            "value": 0.012849760241806507,
+            "min": 0.011811994947493076,
+            "max": 0.015293809585273266,
+            "count": 17
+        },
+        "Pyramids.Losses.RNDLoss.sum": {
+            "value": 0.17989663779735565,
+            "min": 0.05437934026122093,
+            "max": 0.21411333978176117,
+            "count": 17
+        },
+        "Pyramids.IsTraining.mean": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 17
+        },
+        "Pyramids.IsTraining.sum": {
+            "value": 1.0,
+            "min": 1.0,
+            "max": 1.0,
+            "count": 17
+        }
+    },
+    "metadata": {
+        "timer_format_version": "0.1.0",
+        "start_time_seconds": "1694541431",
+        "python_version": "3.10.12 | packaged by Anaconda, Inc. | (main, Jul  5 2023, 19:01:18) [MSC v.1916 64 bit (AMD64)]",
+        "command_line_arguments": "\\\\?\\C:\\Users\\bdonn\\miniconda3\\envs\\DRL\\Scripts\\mlagents-learn ./config/ppo/PyramidsRND.yaml --env=../Pyramids/UnityEnvironment.exe --run-id=Pyramids Training --no-graphics --resume",
+        "mlagents_version": "0.31.0.dev0",
+        "mlagents_envs_version": "0.31.0.dev0",
+        "communication_protocol_version": "1.5.0",
+        "pytorch_version": "2.0.1",
+        "numpy_version": "1.25.2",
+        "end_time_seconds": "1694542605"
+    },
+    "total": 1173.3677240000106,
+    "count": 1,
+    "self": 0.3613532001618296,
+    "children": {
+        "run_training.setup": {
+            "total": 0.17205539997667074,
+            "count": 1,
+            "self": 0.17205539997667074
+        },
+        "TrainerController.start_learning": {
+            "total": 1172.8343153998721,
+            "count": 1,
+            "self": 1.0854164024349302,
+            "children": {
+                "TrainerController._reset_env": {
+                    "total": 6.197830699849874,
+                    "count": 1,
+                    "self": 6.197830699849874
+                },
+                "TrainerController.advance": {
+                    "total": 1165.4142691974994,
+                    "count": 31986,
+                    "self": 0.9317487992811948,
+                    "children": {
+                        "env_step": {
+                            "total": 654.2052320900839,
+                            "count": 31986,
+                            "self": 524.4149543903768,
+                            "children": {
+                                "SubprocessEnvManager._take_step": {
+                                    "total": 129.08072021254338,
+                                    "count": 31986,
+                                    "self": 2.8359906140249223,
+                                    "children": {
+                                        "TorchPolicy.evaluate": {
+                                            "total": 126.24472959851846,
+                                            "count": 31312,
+                                            "self": 126.24472959851846
+                                        }
+                                    }
+                                },
+                                "workers": {
+                                    "total": 0.7095574871636927,
+                                    "count": 31986,
+                                    "self": 0.0,
+                                    "children": {
+                                        "worker_root": {
+                                            "total": 1166.8321079106536,
+                                            "count": 31986,
+                                            "is_parallel": true,
+                                            "self": 713.9999165155459,
+                                            "children": {
+                                                "steps_from_proto": {
+                                                    "total": 0.0012974001001566648,
+                                                    "count": 1,
+                                                    "is_parallel": true,
+                                                    "self": 0.0003544003702700138,
+                                                    "children": {
+                                                        "_process_rank_one_or_two_observation": {
+                                                            "total": 0.000942999729886651,
+                                                            "count": 8,
+                                                            "is_parallel": true,
+                                                            "self": 0.000942999729886651
+                                                        }
+                                                    }
+                                                },
+                                                "UnityEnvironment.step": {
+                                                    "total": 452.8308939950075,
+                                                    "count": 31986,
+                                                    "is_parallel": true,
+                                                    "self": 11.983218401670456,
+                                                    "children": {
+                                                        "UnityEnvironment._generate_step_input": {
+                                                            "total": 9.725233814446256,
+                                                            "count": 31986,
+                                                            "is_parallel": true,
+                                                            "self": 9.725233814446256
+                                                        },
+                                                        "communicator.exchange": {
+                                                            "total": 396.8172612024937,
+                                                            "count": 31986,
+                                                            "is_parallel": true,
+                                                            "self": 396.8172612024937
+                                                        },
+                                                        "steps_from_proto": {
+                                                            "total": 34.305180576397106,
+                                                            "count": 31986,
+                                                            "is_parallel": true,
+                                                            "self": 7.4639062327332795,
+                                                            "children": {
+                                                                "_process_rank_one_or_two_observation": {
+                                                                    "total": 26.841274343663827,
+                                                                    "count": 255888,
+                                                                    "is_parallel": true,
+                                                                    "self": 26.841274343663827
+                                                                }
+                                                            }
+                                                        }
+                                                    }
+                                                }
+                                            }
+                                        }
+                                    }
+                                }
+                            }
+                        },
+                        "trainer_advance": {
+                            "total": 510.2772883081343,
+                            "count": 31986,
+                            "self": 2.3398887978401035,
+                            "children": {
+                                "process_trajectory": {
+                                    "total": 98.11965311155654,
+                                    "count": 31986,
+                                    "self": 97.80131631135009,
+                                    "children": {
+                                        "RLTrainer._checkpoint": {
+                                            "total": 0.3183368002064526,
+                                            "count": 2,
+                                            "self": 0.3183368002064526
+                                        }
+                                    }
+                                },
+                                "_update_policy": {
+                                    "total": 409.81774639873765,
+                                    "count": 234,
+                                    "self": 222.75601530075073,
+                                    "children": {
+                                        "TorchPPOOptimizer.update": {
+                                            "total": 187.06173109798692,
+                                            "count": 11346,
+                                            "self": 187.06173109798692
+                                        }
+                                    }
+                                }
+                            }
+                        }
+                    }
+                },
+                "trainer_threads": {
+                    "total": 1.00000761449337e-06,
+                    "count": 1,
+                    "self": 1.00000761449337e-06
+                },
+                "TrainerController._save_models": {
+                    "total": 0.1367981000803411,
+                    "count": 1,
+                    "self": 0.016386400209739804,
+                    "children": {
+                        "RLTrainer._checkpoint": {
+                            "total": 0.1204116998706013,
+                            "count": 1,
+                            "self": 0.1204116998706013
+                        }
+                    }
+                }
+            }
+        }
+    }
+}

run_logs/training_status.json

@@ -0,0 +1,47 @@
+{
+    "metadata": {
+        "stats_format_version": "0.3.0",
+        "mlagents_version": "0.31.0.dev0",
+        "torch_version": "2.0.1"
+    },
+    "Pyramids": {
+        "checkpoints": [
+            {
+                "steps": 499920,
+                "file_path": "results\\Pyramids Training\\Pyramids\\Pyramids-499920.onnx",
+                "reward": null,
+                "creation_time": 1694541442.2888396,
+                "auxillary_file_paths": [
+                    "results\\Pyramids Training\\Pyramids\\Pyramids-499920.pt"
+                ]
+            },
+            {
+                "steps": 999972,
+                "file_path": "results\\Pyramids Training\\Pyramids\\Pyramids-999972.onnx",
+                "reward": -0.9994000494480133,
+                "creation_time": 1694542604.789448,
+                "auxillary_file_paths": [
+                    "results\\Pyramids Training\\Pyramids\\Pyramids-999972.pt"
+                ]
+            },
+            {
+                "steps": 1000100,
+                "file_path": "results\\Pyramids Training\\Pyramids\\Pyramids-1000100.onnx",
+                "reward": -0.9994000494480133,
+                "creation_time": 1694542604.9472592,
+                "auxillary_file_paths": [
+                    "results\\Pyramids Training\\Pyramids\\Pyramids-1000100.pt"
+                ]
+            }
+        ],
+        "final_checkpoint": {
+            "steps": 1000100,
+            "file_path": "results\\Pyramids Training\\Pyramids.onnx",
+            "reward": -0.9994000494480133,
+            "creation_time": 1694542604.9472592,
+            "auxillary_file_paths": [
+                "results\\Pyramids Training\\Pyramids\\Pyramids-1000100.pt"
+            ]
+        }
+    }
+}