Abstract: The coordination problem between Agents in traffic intersections is a gambling problem. On the basis of bounded rationality, this paper tentatively made use of game learning thought to build the multi-Agent coordinate game learning algorithm. This learning coordination algorithm analyzed travelers' unreasonable behavior and corrected it to realize the urban traffic intersections unimpeded, so as to achieve regional and global transportation optimization. At last, its feasibility is verified by means of an example and simulation.

Key words: bounded rationality , game learning , multi-agent , coordination algorithm

摘要： 交通路口中的各Agent之间的协调问题是一个博弈问题。在有限理性的基础上，利用博弈学习思想，构建多智能体（multi-Agent）博弈学习协调算法，利用此学习协调算法对出行者行为分析并修正，实现城市交通路口的畅通，进而达到区域、全局的交通优化。最后通过实例仿真验证其可行性。

关键词: 有限理性, 博弈学习, 多智能体, 协调算法