一般和重复矩阵对策中的近优在线平均学习
Near-Optimal Online Egalitarian learning in General Sum Repeated Matrix Games
摘要:
我们研究两个玩家一般和重复有限游戏,每个玩家的奖励是从一个未知的分布。我们的目标是找到平等主义的谈判解决方案(EBS)的重复游戏,这可以导致更高的回报比最大化的价值,双方球员。我们最重要的贡献是推导出一个算法,同时实现,为双方球员,一个高概率的遗憾界的顺序$\mathcal{O}(\sqrt[3]{\ln T}\cdot T^{2/3})$后,任何$T$轮的比赛。我们证明了我们的上限是近最优的证明下限的$Ω(T^{2/3})$的任何算法。
英文摘要:
We study two-player general sum repeated finite games where the rewards of each player are generated from an unknown distribution. Our aim is to find the egalitarian bargaining solution (EBS) for the repeated game, which can lead to much higher rewards than the maximin value of both players. Our most important contribution is the derivation of an algorithm that achieves simultaneously, for both players, a high-probability regret bound of order $\mathcal{O}(\sqrt[3]{\ln T}\cdot T^{2/3})$ after any $T$ rounds of play. We demonstrate that our upper bound is nearly optimal by proving a lower bound of $Ω(T^{2/3})$ for any algorithm.
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。