Abstract:
In this article, the initial excitation-based optimal control methods are presented for continuous-time linear nonzero-sum games. The traditional reinforcement learning-b...Show MoreMetadata
Abstract:
In this article, the initial excitation-based optimal control methods are presented for continuous-time linear nonzero-sum games. The traditional reinforcement learning-based optimal control methods for continuous-time linear nonzero-sum games require the persistent excitation condition or data storage to guarantee the convergence of the algorithms. To relax the above conditions, the initial excitation-based policy iteration and value iteration algorithms are presented to obtain the Nash equilibrium solution under an online-verifiable initial excitation condition. The properties of the initial excitation-based policy iteration and value iteration algorithms are analyzed. Simulation examples are provided to show the efficiency of the presented methods.
Published in: IEEE Transactions on Systems, Man, and Cybernetics: Systems ( Volume: 54, Issue: 9, September 2024)