arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 0903.2282cs.MAcs.GTcs.LG
收藏

大型匿名博弈中的多智能体学习

Multiagent Learning in Large Anonymous Games

Cornell University(康奈尔大学)

Ian A. Kash, Eric J. Friedman, Joseph Y. Halpern

摘要:

在大型系统中,智能体学习有效地行动是很重要的,但是复杂的多智能体学习算法通常不能扩展。另一种方法是找到限制类的游戏,简单,有效的算法收敛。结果表明,阶段学习有效地收敛到纳什均衡在大型匿名游戏,如果最佳回复动态收敛。确定了两个功能,提高收敛。首先,更多的代理人在许多情况下实际上是有益的,而不是使学习更加困难。其次,为代理提供有关其他人行为的统计信息可以显着减少所需的观察次数。

英文摘要:

In large systems, it is important for agents to learn to act effectively, but sophisticated multi-agent learning algorithms generally do not scale. An alternative approach is to find restricted classes of games where simple, efficient algorithms converge. It is shown that stage learning efficiently converges to Nash equilibria in large anonymous games if best-reply dynamics converge. Two features are identified that improve convergence. First, rather than making learning more difficult, more agents are actually beneficial in many settings. Second, providing agents with statistical information about the behavior of others can significantly reduce the number of observations needed.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑