Adaptive Dynamic Programming and Optimal Control of Unknown Multiplayer Systems Based on Game Theory

In this paper, we present a new adaptive dynamic programming (ADP) scheme to solve the optimal control problem of multi-player systems with unknown dynamics from perspective nonzero-sum (NZS) games. presented scheme, iterative equation is given. On basis given equation, policy and corresponding value function for each player can be learned by using state input data, which does not need identify system dynamics. To overcome difficulty dynamics, neural network (NN)-based approximation techniques are employed in implementation. Based on NN-based techniques, non-model-based ADP algorithm developed. The convergence developed rigorously analyzed proved. Finally, two numerical simulation examples provided demonstrate performance algorithm.