danesabo/Obsidian
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
Obsidian/SoK_High_Assurance_Reinforcement_Learning_for_Control.md
Dane Sabo ae0ab17291 Auto sync: 2025-08-18 16:54:48 (667 files changed) 
R  "Zettelkasten/Hub Notes/NNFM Ontology.canvas" -> "NNFM Ontology.canvas"

R  "Zettelkasten/Hub Notes/Permanent Notes/Programming/Assembly/Assembly Canvas.canvas" -> "Programming/Assembly/Assembly Canvas.canvas"

R  "Zettelkasten/Hub Notes/Permanent Notes/Programming/Assembly/Untitled.md" -> Programming/Assembly/Untitled.md

R  "Zettelkasten/Hub Notes/Permanent Notes/Programming/Formal Methods/LEAN/Learning Plan.md" -> "Programming/Formal Methods/LEAN/Learning Plan.md"

R  "Zettelkasten/Hub Notes/Permanent Notes/Programming/Formal Methods/LEAN/Tutorial World.md" -> "Programming/Formal Methods/LEAN/Tutorial World.md"

R  "Zettelkasten/Hub Notes/Permanent Notes/Programming/Formal Methods/TLA/TLA Canvas.canvas" -> "Programming/Formal Methods/TLA/TLA Canvas.canvas"

R  "Zettelkasten/Hub Notes/Permanent Notes/Programming/Formal Methods/TLA/TLA+ Learning Plan.md" -> "Programming/Formal Methods/TLA/TLA+ Learning Plan.md"

R  "Zettelkasten/Hub Notes/Permanent Notes/Programming/Formal Methods/TLA/What is TLA?.md" -> "Programming/Formal Methods/TLA/What is TLA?.md"
2025-08-18 16:54:48 -04:00

1.2 KiB
Raw Blame History

First Thoughts

  • Discuss the layout of the paper
  • Create a timeline of tasks to be done
  • Really pin down why this paper should exist - outline existing reviews

Previous Literature Reviews

Example Title

Who wrote this paper: When was it written:

What's good about it, what's bad about it?

What does this review cover? What does it miss?

Zettelkasten/Literature Notes/A Review of Formal Methods applied to Machine Learning

Written by Caterina Urban and Antoine Mine at Universite PSL. Written April 22, 2021

Paper Outline

  1. Motivation
  2. What will be covered
  3. Reinforcement learning methods for control systems
  4. Where reinforcement learning is used in control and why
  5. Current approaches to high assurance reinforcement learning
  6. The slippery nature of high assurance reinforcement learning
  7. Future thrusts

Paper Timeline and Goals

A successful paper will:

  • cover at least 60 citations (75 stretch goal!)
  • provide at least 10 sources from 2024+ (stretch goal 15)

MILESTONES: Paper reviews complete - August 15th Draft Complete - August 22th

To be successful, each week I must accomplish at least:

  • 8 papers read
  • 500 words?

Weekly Updates

Jun 23