Reinforcement Learning: Behaviors and Applications

Reinforcement learning addresses the design of agents that improve decisions while operating within complex and uncertain environments. This course covers principled and scalable approaches to realizing a range of intelligent learning behaviors. Topics include environment models, planning, abstraction, prediction, credit assignment, exploration, and generalization. Motivating examples will be drawn from web services, control, finance, and communications. Prerequisites: programming (e.g., CS106B), probability (e.g., MS&E 121, EE 178 or CS 109), machine learning (e.g., EE 104/CME 107, MS&E 226 or CS 229).