Speaker: Yuanhua Ni, professor and doctoral supervisor, College of Artificial Intelligence, Nankai University

Date: June 21, 2024

Time: 15:00-16:00

Location: B1238, Zhixin Building, Shandong University

Sponsor: School of Mathematics, Shandong University

Abstract:

This paper aims to extend the BML method proposed in [Probabilistic framework of Howard's policy iteration: BML evaluation and robust convergence analysis, IEEE TAC, 2023, DOI:10.1109/TAC.2023.3344870] to make it applicable to more general coupled nonlinear FBSDEs. We interpret BML from the fixed-point iteration perspective and show that optimizing BML+1) Q is equivalent to minimizing the distance between two consecutive trial solutions in a fixed-point iteration. Thus, this paper provides a theoretical foundation for an optimization-based approach to solving FBSDEs. We also empirically evaluate the method through four numerical experiments.

For more information, please visit:

https://view.sdu.edu.cn/info/1020/192707.htm