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 1203.3480cs.GTcs.AI
收藏

使用合理性约束从数据中学习博弈表示

Learning Game Representations from Data Using Rationality Constraints

School of Engineering and Applied Sciences(工程与应用科学学院);Charles River Analytics Inc.(查尔斯河分析公司);Harvard University(哈佛大学)

Xi Alice Gao, Avi Pfeffer

摘要:

虽然博弈论被广泛用于模拟战略互动,但一个自然的问题是,博弈表示来自哪里?一个答案是从数据中学习表示。如果一个人想同时学习收益和参与人的策略,一个简单的方法是直接从数据中学习。这种方法忽略了一个事实,即参与者可能会采取相当好的策略,因此策略和数据之间存在联系。本文的主要贡献是在学习的同时建立这种联系。我们制定的学习问题作为一个加权约束满足的问题,包括约束都适合的回报和战略的数据和适合的策略的回报。我们使用量子反应平衡作为我们的合理性的概念,量化后者适合。我们的研究结果表明,结合合理性约束可以提高学习时的数据量是有限的。

英文摘要:

While game theory is widely used to model strategic interactions, a natural question is where do the game representations come from? One answer is to learn the representations from data. If one wants to learn both the payoffs and the players' strategies, a naive approach is to learn them both directly from the data. This approach ignores the fact the players might be playing reasonably good strategies, so there is a connection between the strategies and the data. The main contribution of this paper is to make this connection while learning. We formulate the learning problem as a weighted constraint satisfaction problem, including constraints both for the fit of the payoffs and strategies to the data and the fit of the strategies to the payoffs. We use quantal response equilibrium as our notion of rationality for quantifying the latter fit. Our results show that incorporating rationality constraints can improve learning when the amount of data is limited.

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。

↑