arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.07067cs.GTcs.LG
收藏

学习严格凸随机合作博弈的期望核

Learning the Expected Core of Strictly Convex Stochastic Cooperative Games

University of Warwick(华威大学);CSIRO’s Data61(澳大利亚联邦科学与工业研究组织数据61部);King’s College London(伦敦国王学院)

Nam Phuong Tran, The Anh Ta, Shuqing Shi, Debmalya Mandal, Yali Du, Long Tran-Thanh

AI总结:

针对随机合作博弈中奖励分布未知、难以计算稳定分配核的问题,提出Common-Points-Picking算法,借助多项式采样以高概率求得严格凸博弈的期望核,并扩展了多凸集分离超平面定理用于算法分析。

摘要:

奖励分配也称为信用分配问题,一直是经济学、工程学和机器学习领域的重要课题。奖励分配中的一个核心概念是核(core),即稳定分配的集合,在这类分配中没有智能体有动机偏离大联盟。在以往的研究中,计算核要么需要确定性博弈中的奖励函数知识,要么需要随机博弈中的奖励分布知识。但这并不现实,因为奖励函数或分布通常仅部分可知,且可能存在不确定性。本文研究奖励分布未知的随机合作博弈中的核学习问题,目标是学习期望核——也就是在期望意义下稳定的分配集合,仅借助每轮可返回查询联盟随机奖励的预言机(oracle)。在严格凸博弈范畴内,我们提出了名为Common-Points-Picking的算法,该算法在多项式数量的采样下,能以高概率返回期望核中的一个点。为分析该算法,我们提出了适用于多凸集的分离超平面定理的新扩展形式。

英文摘要:

Reward allocation, also known as the credit assignment problem, has been an important topic in economics, engineering, and machine learning. An important concept in reward allocation is the core, which is the set of stable allocations where no agent has the motivation to deviate from the grand coalition. In previous works, computing the core requires either knowledge of the reward function in deterministic games or the reward distribution in stochastic games. However, this is unrealistic, as the reward function or distribution is often only partially known and may be subject to uncertainty. In this paper, we consider the core learning problem in stochastic cooperative games, where the reward distribution is unknown. Our goal is to learn the expected core, that is, the set of allocations that are stable in expectation, given an oracle that returns a stochastic reward for an enquired coalition each round. Within the class of strictly convex games, we present an algorithm named \texttt{Common-Points-Picking} that returns a point in the expected core given a polynomial number of samples, with high probability. To analyse the algorithm, we develop a new extension of the separation hyperplane theorem for multiple convex sets.

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。

↑