Learning and Sequential Decision Making

Catalog description

The course explores automated decision making from a computer-science perspective. It examines efficient algorithms, where they exist, for single agent and multiagent planning as well as approaches to learning near-optimal decisions from experience. Topics will include Markov decision processes, stochastic and repeated games, partially observable Markov decision processes, and reinforcement learning. Of particular interest will be issues of generalization, exploration, and representation. Participants should have taken a graduate-level computer science course and should have some exposure to machine learning from a previous computer-science class or seminar; check with instructor if not sure. Recommended Prerequisites: CSCI 1950F or CSCI 1420