Beyond Worst-Case: Instance-Dependent Optimality in Reinforcement Learning

Beyond Worst-Case: Instance-Dependent Optimality in Reinforcement Learning

Simons Institute via YouTube Direct link

Introduction

1 of 12

1 of 12

Introduction

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

Beyond Worst-Case: Instance-Dependent Optimality in Reinforcement Learning

Automatically move to the next video in the Classroom when playback concludes

  1. 1 Introduction
  2. 2 Problem Statement
  3. 3 Global Minimax
  4. 4 Policy Evaluation
  5. 5 Is TD Learning Optimal
  6. 6 How to Get an InstanceOptimal Algorithm
  7. 7 Useful Bounds
  8. 8 Summary
  9. 9 Questions
  10. 10 Decoupling
  11. 11 Optimal Site
  12. 12 QA

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Someone learning on their laptop while sitting on the floor.