Courses Detail Information
ECE7606J – Stochastic Control and Reinforcement Learning
Credits: 3 credits
Control and optimization of discrete-time and continuous-time Markov processes. Probability model, convergence of random variables. Countable-state Markov chains, continuous-state Markov chains, Foster-Lyapunov stability theory, Markov decision processes, dynamic programming, Monte-Carlo method, temporal-difference method, approximate dynamic programming. Continuous-time Markov processes, Poisson processes, queuing theory, infinitesimal generator, piecewise-deterministic Markov processes. Applications include connected and autonomous vehicles, intelligent transportation systems, computer and communication systems, social networks, epidemics, and finance.