Reinforcement Learning#

This jupyter-book contains my notes for the CSE 546 Reinforcement Learning course during the Spring-2023 semester taught by Professor Alina Vereshchaka.

Course description: This course is intended for students interested in artificial intelligence. Reinforcement learning is an area of machine learning in which an agent learns how to behave in an environment by performing actions and assessing the results. Reinforcement learning is the method by which Google DeepMind created the AlphaGo system that beat a high-ranking Go player and how AlphaStar became the first artificially intelligent system to defeat a top professional player in StarCraft II.

How to navigate through these notes: The sections on the left hand side of this book indicate the chapters and the navigation on the right hand side in individual page is a sub-section in a chapter. Search functionality works throughout the book.

Acknowledgments: The work is gathered from the lecture slides and lecture videos of CSE-546 Reinforcement Learning course at UB. All the work is owned by the course instructors.

Reference books:

  • Richard S. Sutton and Andrew G. Barto, “Reinforcement learning: An introduction”, Second Edition, MIT Press, 2019.

  • Wiering, Marco, and Martijn Van Otterlo. “Reinforcement learning.” Adaptation, learning, and optimization 12 (2012): 3.

  • Russell, Stuart J., and Peter Norvig. “Artificial intelligence: a modern approach.”Pearson Education Limited, 2016.

  • Goodfellow, Ian, Yoshua Bengio, and Aaron Courville “Deep learning.” MIT press, 2016.