arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1111.2888cs.GT
收藏

有界记忆博弈中的自适应后悔最小化

Adaptive Regret Minimization in Bounded-Memory Games

Jeremiah Blocki, Nicolas Christin, Anupam Datta, Arunesh Sinha

摘要:

最小化后悔的在线学习算法在涉及在不确定环境中重复做出决策的情况下提供了强有力的保证,例如,驾驶员每天决定开车上班的路线。虽然后悔最小化已被广泛研究重复游戏,我们研究后悔最小化的更丰富的一类游戏称为有界记忆游戏。在两人有限记忆-m博弈的每一轮中,两个玩家同时进行一个动作,观察一个结果并获得奖励。奖励可以取决于最后m个结果以及玩家在当前回合中的动作。对于重复游戏,标准的后悔概念不再适用,因为行为和奖励可能取决于游戏的历史。为了解释这种普遍性,我们引入了k-自适应后悔的概念,它比较了通过对一个假设的k-自适应对手的算法规定的行动所获得的奖励,以及事后对同一对手的最佳专家所获得的奖励。粗略地说,一个假设的k-适应对手调整她的策略,以防御者的行动完全一样,真正的对手会在每个窗口的k轮。我们的定义是由一组专家参数化,其中可以包括固定和自适应防御策略。我们研究了完美和不完美信息的有界记忆博弈中自适应遗憾最小化的内在复杂性,并设计了相应的算法。我们证明了一个硬度的结果表明,与不完美的信息,任何k-自适应后悔最小化算法(与固定的战略专家)必须是低效的,除非NP=RP,即使对一个不经意的对手。相比之下,对于完美和不完美信息的有界记忆博弈,我们提出了近似0-自适应遗憾最小化算法,以对抗时间为n^{O(1)}的遗忘对手。

英文摘要:

Online learning algorithms that minimize regret provide strong guarantees in situations that involve repeatedly making decisions in an uncertain environment, e.g. a driver deciding what route to drive to work every day. While regret minimization has been extensively studied in repeated games, we study regret minimization for a richer class of games called bounded memory games. In each round of a two-player bounded memory-m game, both players simultaneously play an action, observe an outcome and receive a reward. The reward may depend on the last m outcomes as well as the actions of the players in the current round. The standard notion of regret for repeated games is no longer suitable because actions and rewards can depend on the history of play. To account for this generality, we introduce the notion of k-adaptive regret, which compares the reward obtained by playing actions prescribed by the algorithm against a hypothetical k-adaptive adversary with the reward obtained by the best expert in hindsight against the same adversary. Roughly, a hypothetical k-adaptive adversary adapts her strategy to the defender's actions exactly as the real adversary would within each window of k rounds. Our definition is parametrized by a set of experts, which can include both fixed and adaptive defender strategies. We investigate the inherent complexity of and design algorithms for adaptive regret minimization in bounded memory games of perfect and imperfect information. We prove a hardness result showing that, with imperfect information, any k-adaptive regret minimizing algorithm (with fixed strategies as experts) must be inefficient unless NP=RP even when playing against an oblivious adversary. In contrast, for bounded memory games of perfect and imperfect information we present approximate 0-adaptive regret minimization algorithms against an oblivious adversary running in time n^{O(1)}.

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。

↑