EECE 5614 — Reinforcement Learning and Decision Making Under Uncertainty
4 semester hoursGraduateLectureusually offered: springtypical days: T/FBostonTraditional
Covers fundamentals of reinforcement learning. Begins with multiarmed bandit problems and basics of exploration and exploitation. Relates the key concepts of decision theory to dynamic programming and reinforcement learning. Discusses well-known off-policy and on-policy temporal difference learning methods. Connects reinforcement learning to key concepts in reasoning under uncertainty. Covers large-scale learning methods, including deep-value-based and policy-based methods. Explores reinforcement learning applications in robot navigation in uncertain and complex environments. Describes the applications of reinforcement learning in genomics and systems biology, including the derivation of intervention strategies for treating chronic diseases such as cancer.
Prerequisites
- one of:
Offering history
| Term | Sections | Enrolled | Capacity | Full | Open seats/section |
|---|---|---|---|---|---|
| Spring 2025 | 1 | 37 | 55 | 67% | 18.0 |
| Spring 2026 | 1 | 35 | 39 | 90% | 4.0 |
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 0% · T 100% · W 0% · Th 0% · F 100%
Common patterns: TF (100% of sections) — in patterns, R means Thursday
Professors
Spring
- Mahdi Imani (100% of students) · reviews
Percentages are each professor's average share of the season's enrolled students in recent terms.
Links
Official catalog (EECE course descriptions) · Student reviews on RateMyHusky · All EECE courses · Plan it at numap.app