Learning Simulation-Based Games from Data
Learning Simulation-Based Games from Data
复制标题
DOI：
--
复制
发表时间：
2019-05
期刊：
影响因子：
--
通讯作者：
Enrique Areyan Viqueira;A. Greenwald;Cyrus Cousins;E. Upfal
中科院分区：
文献类型：
--
作者：
Enrique Areyan Viqueira;A. Greenwald;Cyrus Cousins;E. Upfal
我们解决了经验博弈论分析（EGTA）中的一个基本问题，即基于模拟的游戏的学习均衡。这样的游戏不能用分析的形式来描述;相反，可以查询黑盒模拟器以获得实用程序的噪声样本。我们对EGTA的态度是本着可能近似正确的学习精神。我们设计了学习经验游戏的算法，这些算法统一地近似于来自大量样本的基于模拟的游戏的效用。我们的方法学所有的均衡基于模拟的游戏，而不是一个单一的。
We tackle a fundamental problem in empirical game-theoretic analysis (EGTA), that of learning equilibria of simulation-based games. Such games cannot be described in analytical form; instead, a black-box simulator can be queried to obtain noisy samples of utilities. Our approach to EGTA is in the spirit of probably approximately correct learning. We design algorithms that learn empirical games, which uniformly approximate the utilities of simulation-based games from finitely many samples. Our methodology learns all the equilibria of simulation-based games, as opposed to a single one.