CMSC389F

Special Topics in Computer Science; Reinforcement Learning

Prerequisites: CMSC216 and CMSC250 with a grade of C- or better. Provides a theory-centric introduction to Reinforcement Learning. Students will learn the key concepts and algorithms driving Reinforcement Learning, including Markov Decision Processes, Monte Carlo Learning, and Policy Gradient methods.

Sister Courses: CMSC389A, CMSC389B, CMSC389C, CMSC389E, CMSC389G, CMSC389I, CMSC389J, CMSC389K, CMSC389L, CMSC389M, CMSC389N, CMSC389O, CMSC389P, CMSC389Q, CMSC389R, CMSC389T, CMSC389U, CMSC389V, CMSC389W, CMSC389Y, CMSC389Z

Past Semesters

11 reviews
Average rating: 4.09

17 reviews
Average rating: 3.71

* "W"s are considered to be 0.0 quality points. "Other" grades are not factored into GPA calculation. Grade data not guaranteed to be correct.