Mathematics 690STK - ReinfrcLearning&StochCntrlThry
Spring
2026
01
3.00
Thejani Gamage
M W F 1:25PM 2:15PM
UMass Amherst
85290
Lederle Grad Res Tower Rm 143
tgamage@umass.edu
This course is an introduction to stochastic control theory and reinforcement learning. The goal is to explore the theory of reinforcement learning through control theory and game theory, enabling the students to design novel algorithms in single agent and multi-agent settings, and evaluate the accuracy, efficiency and robustness of the designed algorithms theoretically as well as empirically. The course will cover topics in control theory, algorithm design in reinforcement learning, game theory, use of deep learning tools in reinforcement learning, recent advances, and applications of reinforcement learning.
MATH 545&605,STAT607&MATH532/4