Mix-zero-sum differential games for linear systems with unknown dynamics based on off-policy IRL

Abstract

This paper discusses a multi-player mixed-zero-sum (MZS) differential games with completely unknown dynamics. Based on off-policy integral reinforcement learning (IRL), a novel algorithm is proposed to obtain the optimal control. First, a policy iteration algorithm is put forward to obtain the optimal solution for deterministic system. Next, the case that the system dynamics is completely unknown is considered. And an IRL-based off-policy algorithm is presented. Meanwhile, the convergence of the presented algorithms is proved in this paper. At the end, the effectiveness of the proposed algorithm is shown by a simulation.