Skip to main content
Browse by:

Effective March 10, 2020, all Duke-sponsored events over 50 people have been cancelled, rescheduled, postponed or virtualized.
Please check with the event contact regarding event status. For more information, please see

Introduction to Reinforcement Learning

Event Image
Icon calendar
Thursday, February 21, 2019
Icon time
4:00 pm - 6:00 pm
Icon speaker
Lawrence Carin

Reinforcement learning is a branch of machine learning, in which in algorithm learns a good policy for acting in an environment of interest, based on experience. When interacting with the environment, an agent (algorithm) experiences rewards or costs, based upon actions taken in particular situations. The algorithm learns a policy by "reinforcing" (learning to favor) actions that yield high rewards. In this introduction to reinforcement learning, basic concepts like Q-learning will be developed. In addition, we will discuss how deep learning (neural networks) have impacted reinforcement learning, including a discussion of how the Alpha-Go system developed by Google Deep Mind was able to defeat the best human players in the game Go.