Prerequisites: EE 215 or EE 244 or CS 224 or EE 228 or CS 228 or EE 251B or CS 252B; graduate standing; or consent of instructor
Description: This course introduces key ideas and algorithms of reinforcement learning (RL). Key topics covered include finite Markov Decision Process (MDP), dynamic programming, Monte Carlo methods, temporal-difference learning, policy gradient methods, safety-constrained RL, batch-constrained RL, multi-agent RL, multi-armed bandits, and imitation learning.
Cross-listing: Cross-listed with CS 258.
Credit: May be taken Satisfactory (S) or No Credit (NC) with consent of instructor and graduate advisor.