Backward Stochastic Control System with Entropy Regularization

TL;DR

This paper develops a theoretical framework for entropy-regularized optimal control in backward stochastic systems, providing conditions for optimality and establishing existence and uniqueness results, with potential applications in finance and algorithms.

Contribution

It introduces a novel approach to backward stochastic control with entropy regularization, including a stochastic maximum principle and existence-uniqueness results.

Findings

Established stochastic maximum principle for the control system.

Proved sufficient conditions and implicit form of optimal control.

Demonstrated existence and uniqueness in linear-quadratic cases.

Abstract

The entropy regularization is inspired by information entropy from machine learning and the ideas of exploration and exploitation in reinforcement learning, which appears in the control problem to design an approximating algorithm for the optimal control. This paper is concerned with the optimal exploratory control for backward stochastic system, generated by the backward stochastic differential equation and with the entropy regularization in its cost functional. We give the theoretical depict of the optimal relaxed control so as to lay the foundation for the application of such a backward stochastic control system to mathematical finance and algorithm implementation. For this, we first establish the stochastic maximum principle by convex variation method. Then we prove sufficient condition for the optimal control and demonstrate the implicit form of optimal control. Finally, the existence and uniqueness of the optimal control for backward linear-quadratic control problem with entropy regularization is proved by decoupling techniques.