UBC SCAIM Seminar: Lexing Ying

  • Date: 01/24/2023
  • Time: 12:30
Lexing Ying, Stanford University Mathematics and ICME

University of British Columbia


On Optimization Formulations and Algorithms of Markov Decision Problems


Markov decision problems and reinforcement learning have been active research areas in the past decade. Compared with the rapid algorithmic developments, the linear/convex programming formulations of the Markov decision problem are less well-known. In the first part of talk, we will discuss the convex optimization formulations of Markov decision problems in the primal, dual, and primal-dual forms. In the second part of the talk, we will present two new algorithms that are inspired by these optimization formulations and exhibit exponential or even super-exponential convergence.

Other Information: 

Location: ESB 4133


Time: 12.30pm Pacific


N.B: Pizza lunch will be provided.