Notes on Sutton & Barto

Preface

Welcome to my study notes on “Reinforcement Learning: An Introduction” by Richard S. Sutton and Andrew G. Barto (Sutton and Barto 2018). These notes primarily focus on my solutions and insights while working through the exercises in the book.

I copy to the chapter and section structure of the book, presenting and solving the exercises within this framework. Additionally, sections with titles in lowercase are my own additions.

Sutton, Richard S., and Andrew G. Barto. 2018. Reinforcement Learning: An Introduction. Second edition. Adaptive Computation and Machine Learning Series. Cambridge, MA: MIT Press. https://mitpress.mit.edu/9780262039246/reinforcement-learning/.