After the cooperation proposal B_i^t is generated, the vehicle vi will receive different rewards according to the deviation between its own cooperation proposal and the cooperation proposal of other vehicles. The basic principle is that the smaller the deviation of the cooperation proposal with other vehicles, the more rewards the vehicle vi will receive, and vice versa. In order to maximize the reward, each vehicle needs to continuously interact and share their cooperation proposals in the virtual logic loop, and dynamically adjust according to the magnitude of the deviation until agreement is reached.
正在翻译中..