CS 4180 — Reinforcement Learning
4 semester hoursUndergraduateLectureusually offered: fall, springtypical days: M/ThBostonTraditional
Introduces reinforcement learning and the Markov decision process (MDP) framework. Covers methods for planning and learning in MDPs such as dynamic programming, model-based methods, and model-free methods. Examines commonly used representations including deep-learning representations. Students are expected to have a working knowledge of probability, to complete programming assignments, and to complete a course project that applies some form of reinforcement learning to a problem of interest.
Prerequisites
Offering history
| Term | Sections | Enrolled | Capacity | Full | Open seats/section |
|---|---|---|---|---|---|
| Fall 2023 | 1 | 5 | 5 | 100% | 0.0 |
| Spring 2024 | 1 | 9 | 15 | 60% | 6.0 |
| Fall 2024 | 1 | 13 | 15 | 87% | 2.0 |
| Spring 2025 | 1 | 15 | 16 | 94% | 1.0 |
| Spring 2026 | 1 | 16 | 15 | 107% | 0.0 |
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 66% · T 34% · W 16% · Th 50% · F 34%
Common patterns: MR (50% of sections), TF (34% of sections), MW (16% of sections) — in patterns, R means Thursday
Professors
Fall
- Christopher Amato (72% of students) · reviews
- Robert Platt (28% of students) · reviews
Spring
- Christopher Amato (40% of students) · reviews
- Benjamin Hescott (38% of students) · reviews
- Lok Sang Wong (23% of students) · reviews
Percentages are each professor's average share of the season's enrolled students in recent terms.
Links
Official catalog (CS course descriptions) · Student reviews on RateMyHusky · All CS courses · Plan it at numap.app