MET CS 766
Deep Reinforcement Learning
ML TheoryRoboticsAI Safety
Offered 2025–26Covers MDPs, bandits, Monte Carlo and temporal-difference methods, DQN variants, policy gradients, actor-critic methods, and AI safety.
- Level
- grad
- Department
- MET
- Credits
- 4
- Prerequisites
- MET CS 767 or consent
- BU Bulletin
- View in the BU Bulletin
Instructors
Last verified: July 20, 2026
Suggest a correction