Seminar on Reinforcement Learning

Abstract

Our seminar mainly focuses on the book “Reinforcement Learning :An Introduction”. We the basic parts of Reinforcement Learning, including Multi Armed Bandit, Thompson Sampling, Markov Decision Process, Monte Carlo Methods, Temporal-Difference Learning, On-policy Approximations and Policy Gradient Methods. We not only present the Theory of the methods in our seminar, but also use some experiment to illustrate our method.

Time

9:30am-11:30am, Tuesday, 2022 Spring

Materials

Materials are continuously updated on our Github repository.