/reinforcement_learning_an_introduction

Notes and exercise solutions for second edition of Sutton & Barto's book

Primary LanguageTeXMIT LicenseMIT

Reinforcement Learning: An Introduction

Notes and exercise solutions to the second edition of Sutton & Barto's book.

Some of the solutions have mistakes, so be mindful! If you spot a mistake, please raise an issue and (at some point...) I'll fix it.


Notes:

  • The code has been refactored as I've gone along, so some of the earlier exercises might break/have code duplicated elsewhere
  • I used the online draft, so the numbering of sections, equations and exercises might not be consistent with the published version of the book. This is unfortunate, but I don't have time to correct it.
  • If there is a typo/mistake somewhere then let me know