Date	Speaker	Title
2020-08-17	Ian Hogeboom-Burr	Regularity Properties of Value Functions in Information Structures for Stochastic Team and Zero-Sum Game Problems
2020-08-24	Sina Sanjari	Independently randomized symmetric policies are optimal for exchangeable stochastic teams with infinitely many decision makers
2020-09-14	Ali D. Kara	Performance bounds for Finite Memory Feedback Policies in Partially Observed Markov Decision Processes - Part I
2020-09-21	Ali D. Kara	Performance bounds for Finite Memory Feedback Policies in Partially Observed Markov Decision Processes - Part II
2020-09-28	Meysam Ghomi	Structure and approximations of optimal zero-delay coders for linear $R^d$-valued Markov sources
2020-10-05	Nicolas Garcia	A conditional entropy inequality using stochastic realization theory (and a refined data-rate theorem in nonlinear networked control)
2020-10-19	Naci Saldi	Regularized Stochastic Team Problems
2020-10-26	Serdar Yuksel	Optimality of Stationary and Deterministic Policies in Average Cost Stochastic Control: Convex Analytic Method Revisited
2020-11-02	Ertan Kazikli	Signaling Games
2020-11-09	Sina Sanjari	Policy-dependent and Policy-Independent Static Reductions of Dynamic Teams and Games
2020-11-16/23	Naci Saldi	Stochastic Control Theoretic Approach to Large Deviations Theory
2020-11-30	Serdar Yuksel	Another look at optimal control under partial information: Optimal solutions without belief-MDP reduction

Time : 10:30am-11:50am Mondays through Zoom.