Integrated learning self-triggered control for model-free continuous-time systems with convergence guarantees

This paper presents an integrated self-triggered control strategy with convergence guarantees for model-free continuous-time systems using reinforcement learning. To consider the control cost and triggering consumption in the self-triggered scheme simultaneously, an integrated cost function is proposed. With this integrated cost function, the trade-off between the triggering occupation and control performance could be adjusted according to different requirements. Then, the actor-critic framework of reinforcement learning is employed to learn the control inputs and triggering intervals by minimizing the corresponding integrated cost function. Considering the divergent characteristics between the control inputs and triggering intervals, two different actors are utilized to learn the triggering strategy and control policy, respectively. Also, the convergence of the developed model-free self-triggered control learning algorithm is proved to ensure the limited learning duration of both the control policy and triggering strategy. The proposed framework can be used to design self-triggered controllers for a wide range of engineering systems with unknow dynamics, including control of aircraft, robots, chemical processes, and other automated systems. Finally, the effectiveness and superiorities of the proposed method are verified by an illustrative example.