arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv cs/0507062cs.LG
收藏

自适应Bandits的FPL分析

FPL Analysis for Adaptive Bandits

Jan Poland

摘要:

在线决策问题的“跟随扰动领导者”策略的一个主要问题是遗憾界通常是针对遗忘对手证明的。在部分观测的情况下,它是不清楚如何获得对自适应对手的性能保证,而不恶化的界限。我们提出一个概念上简单的论点来解决这个问题。利用这一点,在对抗性多臂强盗问题中,FPL的遗憾界为O(t^(2/3))。该界限仅适用于仅使用指定探索回合的观察结果的常见FPL变体。使用所有的观测值可以得到更强的O(t^(1/2))的界,与迄今为止已知的最佳界(本质上是已知的下界)相匹配。令人惊讶的是,这种变体甚至不需要明确的探索,它是自我稳定的。然而,抽样概率必须由外部提供或近似到足够的精度,在每一步中使用O(t^2 log t)个样本。

英文摘要:

A main problem of "Follow the Perturbed Leader" strategies for online decision problems is that regret bounds are typically proven against oblivious adversary. In partial observation cases, it was not clear how to obtain performance guarantees against adaptive adversary, without worsening the bounds. We propose a conceptually simple argument to resolve this problem. Using this, a regret bound of O(t^(2/3)) for FPL in the adversarial multi-armed bandit problem is shown. This bound holds for the common FPL variant using only the observations from designated exploration rounds. Using all observations allows for the stronger bound of O(t^(1/2)), matching the best bound known so far (and essentially the known lower bound) for adversarial bandits. Surprisingly, this variant does not even need explicit exploration, it is self-stabilizing. However the sampling probabilities have to be either externally provided or approximated to sufficient accuracy, using O(t^2 log t) samples in each step.

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。

↑