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 1809.03066cs.GTcs.LGmath.OC
收藏

时变博弈中的多智能体在线学习

Multi-agent online learning in time-varying games

Maastricht University(马斯特里赫特大学);Univ. Grenoble Alpes(格勒诺布尔阿尔卑斯大学);CNRS(法国国家科学研究中心);Inria(法国国家信息与自动化研究所);Criteo AI Lab(科韬人工智能实验室)

Benoit Duvocelle, Panayotis Mertikopoulos, Mathias Staudigl, Dries Vermeulen

摘要:

我们研究了多智能体在线学习在游戏中随时间演变的长期行为。具体来说,我们专注于广泛的一类政策的基础上镜像下降,我们表明,诱导序列的发挥(a)收敛到纳什均衡在随时间变化的游戏,从长远来看,稳定在一个严格的单调限制;和(b)它保持渐近接近的阶段游戏序列(假设它们是强单调的)的演变均衡。我们的结果适用于基于梯度和基于回报的反馈-即,“强盗反馈”的情况下,玩家只能观察他们选择的行动的收益。

英文摘要:

We examine the long-run behavior of multi-agent online learning in games that evolve over time. Specifically, we focus on a wide class of policies based on mirror descent, and we show that the induced sequence of play (a) converges to Nash equilibrium in time-varying games that stabilize in the long run to a strictly monotone limit; and (b) it stays asymptotically close to the evolving equilibrium of the sequence of stage games (assuming they are strongly monotone). Our results apply to both gradient-based and payoff-based feedback - i.e., the "bandit feedback" case where players only get to observe the payoffs of their chosen actions.

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。

↑