Topics# Problems of Decision and Control in Discrete-event Systems And Their Optimal Solution Using Dynamic Programming Methods. Basic Modal of Markov Decision Processes,common Solution Methods And Aplications to Computer Systems, Communication Networks, Path Planning and Robotics. Introduction and Overview of Advanced Topics of Reinforcement Learning (rl) and Online Planning (opl.)

Faculty: Electrical and Computer Engineering
|Undergraduate Studies |Graduate Studies

Pre-required courses

(44202 - Random Signals and 46195 - Machine Learning)


Course with no extra credit

46194 - Learning and Planing in Dynamic Prog.


Semestrial Information