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 1602.04676math.STcs.GTstat.MLstat.TH
收藏

最大最小行为识别:一种新的博弈强盗框架

Maximin Action Identification: A New Bandit Framework for Games

Aurélien Garivier, Emilie Kaufmann, Wouter Koolen

摘要:

我们研究了一个原始的纯探索问题的战略土匪模型的动机是蒙特卡洛树搜索。它包括确定游戏中的最佳行动,当玩家可以从顺序选择的行动对中随机抽取结果时。我们提出了两种策略的固定的信心设置:最大值LUCB,基于上下限的信心界限;和最大值赛车,它通过连续消除次优的行动。我们讨论了这两种方法的样本复杂性,并比较它们的性能经验。我们勾勒出一个下界分析,并可能连接到一个最佳的算法。

英文摘要:

We study an original problem of pure exploration in a strategic bandit model motivated by Monte Carlo Tree Search. It consists in identifying the best action in a game, when the player may sample random outcomes of sequentially chosen pairs of actions. We propose two strategies for the fixed-confidence setting: Maximin-LUCB, based on lower-and upper-confidence bounds; and Maximin-Racing, which operates by successively eliminating the sub-optimal actions. We discuss the sample complexity of both methods and compare their performance empirically. We sketch a lower bound analysis, and possible connections to an optimal 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。

↑