Foundations of Reinforcement Learning

3 credits · Undergraduate

Reinforcement learning represents a class of problems in which a learning agent is required to develop a policy for maximizing reward over some temporal horizon. Two basic themes will be developed: 1) Markov decision processes, dynamic programming and Monte Carlo Tree search. 2) Episodic policy search through Evolutionary Computation. Case studies will consider results from a broad range of applications. PREREQUISITES: CSCI 2150.03 and (STAT 2060.03 or CSCI 2360.03), each with a grade of C or better. EXCLUSIONS: CSCI 4156.03