arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2107.01595cs.GTcs.LGmath.OC
收藏

非原子博弈中的学习,第一部分:有限作用空间和种群博弈

Learning in nonatomic games, Part I: Finite action spaces and population games

Tweag I/O(Tweag I/O公司);CNRS(法国国家科学研究中心);University of Dauphine-PSL(巴黎多芬大学-巴黎文理研究大学);University of Liverpool(利物浦大学);Univ. Grenoble Alpes(格勒诺布尔阿尔卑斯大学);Inria(法国国家信息与自动化研究所);Grenoble INP(格勒诺布尔国立理工学院);Sorbonne Université(索邦大学);UPMC(巴黎第六大学)

Saeed Hadikhanloo, Rida Laraki, Panayotis Mertikopoulos, Sylvain Sorin

摘要:

我们研究了在非原子游戏中学习的各种动态的长期行为,在离散和连续的时间。我们考虑的动力学类型包括虚拟游戏及其正则化变体、最佳回复动力学(同样,可能是正则化的),以及双重平均/“跟随正则化领导者”的动力学(它们本身包括作为特例的复制者动力学和弗里德曼的投影动力学)。我们的分析关注的实际轨迹的发挥和它的时间平均,我们涵盖潜在的和单调的游戏,以及游戏的进化稳态(全球或其他)。我们专注于有限行动空间的游戏,连续行动空间的非原子游戏在本文的第二部分中详细讨论。

英文摘要:

We examine the long-run behavior of a wide range of dynamics for learning in nonatomic games, in both discrete and continuous time. The class of dynamics under consideration includes fictitious play and its regularized variants, the best-reply dynamics (again, possibly regularized), as well as the dynamics of dual averaging / "follow the regularized leader" (which themselves include as special cases the replicator dynamics and Friedman's projection dynamics). Our analysis concerns both the actual trajectory of play and its time-average, and we cover potential and monotone games, as well as games with an evolutionarily stable state (global or otherwise). We focus exclusively on games with finite action spaces; nonatomic games with continuous action spaces are treated in detail in Part II of this paper.

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。

↑