关键词: 关键词：多议题协商, 协商僵局, 学习机制, 议题权值, 优化策略

Abstract: To solve the problem of deadlock in multi-issue negotiation, an optimization strategy was presented. This paper adopted a learning method to estimate opponents' preferences of their negotiation issue, and gave full consideration to the issue dependencies. Considering the weight value of the opponent, the reserved value of some issues were adjusted accordingly to solve the deadlock problem quickly and efficiently, and at the same time the negotiation participants could get a reasonable solution. The results prove that the efficiency of the whole negotiation process improves greatly.

Key words: Key words: multi-issue negotiation, deadlock, learning method, weighted value, optimization strategy