Approximate Optimal Indirect Regulation of an Unknown Agent With a Lyapunov-Based Deep Neural Network

An approximate optimal policy is developed for a pursuing agent to indirectly regulate an evading agent coupled by an unknown interaction dynamic. Approximate dynamic programming is used to design a controller for the pursuing agent to optimally influence the evading agent to a goal location. Since the interaction dynamic between the agents is unknown, integral concurrent learning is used to update a Lyapunov-based deep neural network to facilitate sustained learning and system identification. A Lyapunov-based stability analysis is used to show uniformly ultimately bounded convergence. Simulation results demonstrate the performance of the developed method.