/reinforcement-learning-book

My solutions of some excercises of Reinforcement Learning: An Introduction (Sutton and Barto, 2018)

Primary LanguageJupyter Notebook

Solutions to some excercises from Reinforcement Learning: An Introduction

My solutions to some excercises and implementation of some algorithms from Reinforcement Learning: An Introduction (2018)

Implementations

All the code is implemented in Jupyter Notebooks

  • Bandits (Chapter 2) : The 10 armed Testbed
  • Dynamic Programming (Chapter 4): Gambler's Problem (Ex 4.9)
  • Monte Carlo Methods (Chapter 5): Racetrack (Ex 5.12)
  • TD Learning (Chapter 6): Windy Gridworld (Ex 6.5)
  • Planning and Learning with Tabular Methods (Chapter 8): Dyna-Q