Entropy-Regularized Backward Stochastic Control System With Partial Information: Optimality and Algorithm Implementation

• 成果类型: Article
• 署名作者: Chen, Ziyue; Wang, Guangchen; Zhang, Qi
• 署名单位: Fudan University; Shandong University
• 刊物名称: IEEE TRANSACTIONS ON AUTOMATIC CONTROL
• ISSN/ISSBN: 0018-9286
• DOI: 10.1109/TAC.2026.3665129
• 发表日期: 2026
• 关键词: differential-equations; SUCCESSIVE-APPROXIMATIONS; numerical-methods

摘要

In this article, we study the optimal exploratory control for an entropy-regularized backward stochastic control system with partial information. The stochastic maximum principle are given for the concerned nonlinear system. Then, the existence and uniqueness of optimal control for the entropy-regularized linear quadratic control problem with partial information is proved. Based on theoretical results, we design an efficient iterative algorithm for optimal control of linear-convex stochastic systems with partial information in the case that the state variable and the control variable are separated in the cost functional, and moreover, we prove that the algorithm has an 1/n-order convergence rate. Finally, numerical examples are given to demonstrate the effectiveness of our proposed algorithm.