CSCI 8351 Reinforcement Learning
In this course, we will learn and implement basic theory and practical algorithms of reinforcement learning (RL) to be capable of understanding research papers on RL and able to develop a new RL algorithm for a given problem. The course will focus on state-of-the-art techniques including Deep Q-Learning, Policy Gradient, and Actor Critic. After studying basic algorithms, current scientific topics selected from recent Deep Reinforcement Learning research papers will be discussed.
Prerequisite
Consent of Instructor.
Offered
As Scheduled