Undergraduate Prerequisites: (ENGEK500) ENGEK381 and ENG EC402 or ENG EC501. - This course covers the fundamentals of sequential decision making in both known and unknown environments through dynamic programming and reinforcement learning. The first part of the course delves into selecting optimal permissible actions upon observing a system state with established system evolution rules. This section examines finite and infinite horizon stochastic dynamic systems, introducing methods like value iteration, policy iteration, and linear programming solution approaches. Subsequently the course shifts to strategies for optimal action selection under uncertain stochastic system dynamics, covering techniques such as temporal differences, Q-learning, policy gradient, actor-critic, neural network/deep-learning-based reinforcement learning, and federated learning. This course is cross-listed as ENG ME 710 and ENG SE 710. Note: Credit is granted for only one of these courses.

Note that this information may change at any time. Please visit the MyBU Student Portal for the most up-to-date course information.