Synchronous optimal control method for nonlinear systems with saturating actuators and unknown dynamics using off-policy integral reinforcement learning

摘要

The present study establishes an approximate optimal critic learning algorithm, based on the single-network integral reinforcement learning (IRL) algorithm and intends to solve the optimal control problem for an unknown nonlinear system with saturating actuators. The value function is formulated through building generalized nonquadratic functions. In order to solve the Hamilton-Jacobi-Bellman (HJB) equation, a novel optimal scheme for the control approximation, based on the off-policy iteration is presented. Moreover, the single-neural network implementation procedure is introduced to complete the iteration algorithm. The synchronous IRL policy iteration is proposed to update the weight of the critic neural network. Finally, reasonable simulation results are provided for confirming the effectiveness of the proposed optimal approximation control technique in solving equations for a linear and oscillating systems. (C) 2019 Elsevier B.V. All rights reserved.