Neural network-based event-triggered integral reinforcement learning for constrained H1 tracking control with experience replay

Authors：Xue, Shan; Luo, Biao; Liu, Derong^*; Gao, Ying

Source：NEUROCOMPUTING, 2022, 513: 25-35.

DOI：10.1016/j.neucom.2022.09.119

• Adaptive dynamic programming
• Neural networks
• Integral reinforcement learning
• H 1 tracking control
• Event -triggered mechanism

Since input constraints and external disturbances are unavoidable in tracking control problems, how to obtain a controller in this case to save communication and data resources at the same time is very chal-lenging. Aiming at these challenges, this paper develops a novel neural network (NN)-based event -triggered integral reinforcement learning (IRL) algorithm for constrained H1 tracking control problems. First, the constrained H1 tracking control problem is transformed into a regulation problem. Second, an event-triggered optimal controller is designed to reduce network transmission burden and improve resource utilization, where a novel threshold is proposed and its non-negativity can be guaranteed. Third, for implementation purpose, a novel NN-based event-triggered IRL algorithm is developed. In order to improve data utilization, the experience replay technique with an easy-to-verify condition is employed in the learning process. Theoretical analysis proves that the tracking error and weight estima-tion error are uniformly ultimately bounded. Finally, simulation verification shows the effectiveness of the present method.