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 2001.08177cs.GTcs.AIcs.LGcs.MA
收藏

基于效用的多目标范式对策均衡分析

A utility-based analysis of equilibria in multi-objective normal form games

Vrije Universiteit Brussel(布鲁塞尔自由大学);National University of Ireland Galway(爱尔兰国立大学戈尔韦分校);Universiteit van Amsterdam(阿姆斯特丹大学);HU University of Applied Sciences Utrecht(HU乌得勒支应用科学大学)

Roxana Rădulescu, Patrick Mannion, Yijie Zhang, Diederik M. Roijers, Ann Nowé

摘要:

在多目标多智能体系统(MOMAS)中,智能体显式地考虑相互冲突的目标函数之间可能的权衡。我们认为,在MOMAS竞争目标之间的妥协应分析的基础上,这些妥协的效用,为用户的系统,代理的效用函数映射到标量效用值的回报向量。这种基于效用的方法自然会导致两个不同的优化标准的代理在MOMAS:预期标量化回报(ESR)和标量化预期回报(SER)。在这篇文章中,我们探讨这两个标准之间的差异,使用多目标范式游戏(MONFGs)的框架。我们表明,选择的优化标准(ESR或SER)可以从根本上改变一组MONFG的均衡时,使用非线性效用函数。

英文摘要:

In multi-objective multi-agent systems (MOMAS), agents explicitly consider the possible tradeoffs between conflicting objective functions. We argue that compromises between competing objectives in MOMAS should be analysed on the basis of the utility that these compromises have for the users of a system, where an agent's utility function maps their payoff vectors to scalar utility values. This utility-based approach naturally leads to two different optimisation criteria for agents in a MOMAS: expected scalarised returns (ESR) and scalarised expected returns (SER). In this article, we explore the differences between these two criteria using the framework of multi-objective normal form games (MONFGs). We demonstrate that the choice of optimisation criterion (ESR or SER) can radically alter the set of equilibria in a MONFG when non-linear utility functions are used.

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。

↑