Theoretic Solution of Multi-Player Pursuit-Evasion Game Based on Adaptive Dynamic Programming

This paper mainly studies the problem of pursuit-evasion game with multiple pursuers and escapers. In order to improve the real-time performance of the algorithm, the synchronous optimal adaptive controllers are introduced, and the online tuning model is constructed to realize the convergence process of the neural network parameters. The adaptive dynamic programming method is applied to continuous system game problems, and the convergence of the method is proved by establishing a Lyapunov function. Simulation experiments verify the feasibility of the method.