A Dual-Mode Framework for Mean-Field Systems: Model-Based $H_2/H_\infty$ Control with Jump Diffusions and Model-Free Reinforcement Learning

Abstract: The stochastic $H_2/H_\infty$ control problem for continuous-time mean-field stochastic differential equations with Poisson jumps over finite horizon is investigated in this paper. Continuous and jump diffusion terms in the system depend not only on the state but also on the control input, external disturbance, and mean-field components. By employing the quasi-linear technique and the method of completing the square, a mean-field stochastic jump bounded real lemma of the system is derived. This study demonstrates that the feasibility of the stochastic $H_2/H_\infty$ control problem is equivalent to the solvability of four sets of cross-coupled generalized differential Riccati equations, which generalizes the previous results to mean-field jump-diffusion systems. To validate the proposed methodology, a numerical simulation example is provided to illustrate the effectiveness of the control strategy. This paper also presents a data-driven, model-free, off-policy reinforcement learning approach, which can be utilized to solve the $H_\infty$ control problem for the mean-field systems discussed herein. The findings establish a systematic framework for designing robust controllers for interacting particle systems.