Inverse Reinforcement Learning of Nonlinear Systems with Input Constraints

This paper proposes a model-based inverse reinforcement learning for nonlinear systems with input constraints. A saturation function is introduced to transform the original saturation optimal control problem into a new unconstrained optimal control problem. The recursive weight update law is established by using the approximate inverse Bellman error and the optimal controller error. Then, the effectiveness of the proposed method is verified through a simulation example.