Inverse Optimal Control in Conjunction With Inverse Reinforcement Learning for Distributed Parameter Systems

초록

This article focuses on the design of inverse optimal control (IOC) based on inverse reinforcement learning (IRL) for distributed parameter systems (DPSs) with unknown dynamic parameters. First, considering that the optimal policies may not display the expected performance when they are migrated to real-world DPSs due to model bias, the human-behavior learning (HBL) strategy is utilized to transfer the optimal strategy of the reference systems to the real-world DPSs. Furthermore, to avoid performance degradation caused by predefined reward-weight matrices during the optimal control process of the reference systems, the IRL policy iteration algorithm is employed to realize the IOC of the reference systems, and the equivalent reward-weight matrices and optimal control gains of the reference systems are solved. Finally, the effectiveness and superiority of the algorithms are verified in simulation.

키워드