CS 5180 — Reinforcement Learning and Sequential Decision Making

4 semester hoursGraduateLectureusually offered: fall, springBostonPortland, MaineSeattle, WASilicon Valley, CALive CastTraditional

Introduces reinforcement learning and the underlying computational frameworks and the Markov decision process framework. Covers a variety of reinforcement learning algorithms, including model-based, model-free, value function, policy gradient, actor-critic, and Monte Carlo methods. Examines commonly used representations including deep learning representations and approaches to partially observable problems. Students are expected to have a working knowledge of probability and linear algebra, to complete programming assignments, and to complete a course project that applies some form of reinforcement learning to a problem of interest.

Offering history

TermSectionsEnrolledCapacityFullOpen seats/section
Fall 20231869096%4.0
Spring 20241647091%6.0
Fall 20241627089%8.0
Spring 20251889791%9.0
Fall 20251173253%15.0
Spring 2026418720691%4.8

Snapshots from scheduled scrapes — not live seat availability. "Full" can exceed 100% when sections over-enroll.

Meeting times

Share of recent sections by weekday: M 49% · T 48% · W 13% · Th 31% · F 35%

Common patterns: TF (35% of sections), MR (28% of sections), T (13% of sections), MW (13% of sections), M (9% of sections), R (3% of sections) — in patterns, R means Thursday

Professors

Fall

Spring

Percentages are each professor's average share of the season's enrolled students in recent terms.

Unlocks

CS 6180

Courses that list CS 5180 in their prerequisites.

Links

Official catalog (CS course descriptions) · Student reviews on RateMyHusky · All CS courses · Plan it at numap.app