基于DDQN的多智能体冲突消解方法

o solve the problem that agents cannot make effective decisions under local observation, a conflict resolutionmethod combined with deep reinforcement learning is proposed. Based on DDQN algorithm, this method uses the characteristicsof reinforcement learning mode to calculate the cumulative return of agent and determine the priority of agent throughthe return value, so as to achieve the purpose of conflict resolution. The method is evaluated by simulating the traffic jam inreal life, and the experimental results show that the method can effectively solve the agent conflict.