[20191206 : Colloquium]

1. 일시 : 2019126() 오후 430~ 530

2. 장소 : 아산이학관 526

3. 연사 : 양인순(서울대학교 전기정보공학부, 교수)

4. 제목 : Wasserstein Distributionally Robust Stochastic Control: A Data-Driven Approach

5. 초록 : Standard stochastic control methods assume that the probability distribution of uncertain variables is available. Unfortunately, in practice, obtaining accurate distribution information is a challenging task. To resolve this issue, we investigate the problem of designing a control policy that is robust against errors in the empirical distribution obtained from data. This problem can be formulated as a two-player zero-sum dynamic game problem, where the action space of the adversarial player is a Wasserstein ball centered at the empirical distribution. We propose computationally tractable value and policy iteration algorithms with explicit estimates of the number of iterations required for constructing an ϵ-optimal policy. We show that the contraction property of associated Bellman operators extends a single-stage out-of-sample performance guarantee, obtained using a measure concentration inequality, to the corresponding multi-stage guarantee without any degradation in the confidence level. In addition, we characterize an explicit form of the optimal distributionally robust control policy and the worst-case distribution policy for linear-quadratic problems with Wasserstein penalty. Our study indicates that dynamic programming and Kantorovich duality play a critical role in solving and analyzing the Wasserstein distributionally robust stochastic control problems.


*연사소개: Insoon Yang is an Assistant Professor of Electrical and Computer Engineering at Seoul National University. He received B.S. degrees in Mathematics and in Mechanical Engineering (summa cum laude) from Seoul National University in 2009; and an M.S. in EECS, an M.A. in Mathematics and a Ph.D. in EECS from UC Berkeley in 2012, 2013 and 2015, respectively. He was an Assistant Professor of Electrical and Computer Engineering at University of Southern California from 2016 to 2018, and a Postdoctoral Associate at the Laboratory for Information and Decision Systems in Massachusetts Institute of Technology from 2015 to 2016. His research interests are in stochastic control and optimization, and reinforcement learning, with application to cyber-physical systems and safe autonomy. He is a recipient of the 2015 Eli Jury Award and a finalist for the Best Student Paper Award at the 55th IEEE Conference on Decision and Control 2016. He is an associate editor of the IEEE CSS Conference Editorial Board and a vice-chair of the IFAC Stochastic Systems Technical Committee.