Reinforcement Learning

This module explores reinforcement learning, a type of machine learning where agents learn to make decisions by interacting with an environment to maximize cumulative reward. It covers key concepts such as the Markov decision process, policy optimization, and value-based methods, along with applications in areas like gaming, robotics, and autonomous systems.

Portal > Artificial Intelligence > Reinforcement Learning

Curriculum Builder

View Curriculum

Sutton, Richard S, and Andrew G Barto. Reinforcement Learning : An Introduction. Second edition. Cambridge, Massachusetts ; The MIT Press, 2018.

Bertsekas, Dimitri, “Reinforcement Learning and Optimal Control”, Athena Scientific, 2019.

Agarwal, Alekh, Jiang, Nan, and S. Kakade. “Reinforcement Learning: Theory and Algorithms”, 2020.

Kochenderfer, Mykel J, Wheeler, Tim A, and Kyle H. Mray. “Algorithms for Decision Making,” MIT Press, 2022.