arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1807.08545cs.MA
收藏

一种可编程的Agent博弈框架

Towards a Programmable Framework for Agent Game Playing

Francis Lawlor, Rem Collier, Vivek Nallur

摘要:

博弈论领域提供了一种有用的机制,用于对许多决策场景进行建模。在参与这些情景时,个人和团体采取特定的策略,通常取得不同程度的成功。然而,大多数结果都集中在以迭代方式玩同一游戏的玩家身上。本文描述了一个框架,它可以用来观察代理人时,他们不知道在事先的游戏,他们要玩。也就是说,同一组代理人可以先玩几轮迭代囚徒困境,然后玩几轮线性公共产品博弈,然后玩几轮少数者博弈,或者以严格交替的方式或随机实例化的博弈进行所有博弈。这个框架将允许在更复杂的环境中,当有关于未来的不确定性,和有限的资源来存储策略的代理人的调查。

英文摘要:

The field of Game Theory provides a useful mechanism for modeling many decision-making scenarios. In participating in these scenarios individuals and groups adopt particular strategies, which generally perform with varying levels of success. However, most results have focussed on players that play the same game in an iterated fashion. This paper describes a framework which can be used to observe agents when they do not know in advance which game they are going to play. That is, the same group of agents could first play a few rounds of the Iterated Prisoner's Dilemma, and then a few rounds of the Linear Public Goods Game, and then a few rounds of Minority Game, or perhaps all games in a strictly alternating fashion or a randomized instantiation of games. This framework will allow for investigation of agents in more complex settings, when there is uncertainty about the future, and limited resources to store strategies.

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。

↑