Online Adaptive Dynamic Programming-Based Solution of Networked Multiple-Pursuer and Single-Evader Game

Abstract

This paper presents a new scheme for the online solution of a networked multi-agent pursuit–evasion game based on an online adaptive dynamic programming method. As a multi-agent in the game can form an Internet of Things (IoT) system, by incorporating the relative distance and the control energy as the performance index, the expression of the policies when the agents reach the Nash equilibrium is obtained and proved by the minmax principle. By constructing a Lyapunov function, the capture conditions of the game are obtained and discussed. In order to enable each agent to obtain the policy for reaching the Nash equilibrium in real time, the online adaptive dynamic programming method is used to solve the game problem. Furthermore, the parameters of the neural network are fitted by value function approximation, which avoids the difficulties of solving the Hamilton-Jacobi–Isaacs equation, and the numerical solution of the Nash equilibrium is obtained. Simulation results depict the feasibility of the proposed method for use on multi-agent pursuit–evasion games.

Research on Partner Selection of High-Speed Railway Dynamic Logistics Alliance Based on the Dynamic Programming Model

“…On the optimization of database use, Crispim et al [19] proposed using the TOPSIS method to sort and select candidate partners; Wang Daoqu [20] combined AHP and TOPSIS to achieve partner selection; Gong et al [21] used the adaptive dynamic programming method to research and solve the online solution of the network multiagent pursuit and evasion game so that each agent can obtain the strategy to achieve Nash equilibrium in real time; Liang and Xu [22] established a fnite-time domain Markov decision process model with the goal of maximizing the benefts of the hospital in terms of inspection equipment, and combined it with the dynamic programming theory to obtain the optimal reservation scheduling strategy of the system. In order to adapt the warehouse to the increasing variety and quantity of storage products, Djurdjević et al [23] used the dynamic programming method to obtain the optimal allocation of products in diferent order-picking areas.…”

Cooperative control for multi-player pursuit-evasion games embedded on communication technology with reinforcement learning

“…A multiagent pursuit-evasion game requires that a set of agents persuade a different set of agents (evaders) to cooperate in order to be apprehended [16,17]. The playing eld, the players' game information and the players' ability to manage their movements Other crucial factors to take into account include the exibility of the evaders' manoeuvrability and the concept of a capture [18,19]. Another type of chase-evasion game involves the pursuit and evasion of players in a de ned setting, such as a grid map.…”