arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2408.12581cs.LGcs.AI
收藏

在全局环境变化下识别最佳臂

Identifying the Best Arm in the Presence of Global Environment Shifts

University of Warwick(华威大学)

Phurinut Srisawad, Juergen Branke, Long Tran-Thanh

AI总结:

本文研究非平稳随机老虎机中存在全局环境变化时的最佳臂识别问题,提出了一种鲁棒的选择策略和利用全局变化信息的LinLUCB分配策略,显著提升了识别性能。

摘要:

本文在非平稳随机老虎机设定下提出了一个新的最佳臂识别问题,其中所有臂的均值由于环境的全局影响以相同方式发生偏移。目标是在给定固定总预算的情况下,识别出跨越环境变化的唯一最佳臂。尽管该设定可以被视为对抗性老虎机或腐败老虎机的特例,但我们证明了为这些设定量身定制的现有解决方案并未充分利用这种全局影响的本质,因此在实践中效果不佳(尽管它们具有理论保证)。为了克服这一问题,本文开发了一种在处理全局环境变化时具有一致性和鲁棒性的新型选择策略。随后,我们提出了一种分配策略 LinLUCB,它利用了每个环境中所有臂之间全局变化的信息。实证测试表明,我们的策略相较于其他现有方法有显著提升。

英文摘要:

This paper formulates a new Best-Arm Identification problem in the non-stationary stochastic bandits setting, where the means of all arms are shifted in the same way due to a global influence of the environment. The aim is to identify the unique best arm across environmental change given a fixed total budget. While this setting can be regarded as a special case of Adversarial Bandits or Corrupted Bandits, we demonstrate that existing solutions tailored to those settings do not fully utilise the nature of this global influence, and thus, do not work well in practice (despite their theoretical guarantees). To overcome this issue, in this paper we develop a novel selection policy that is consistent and robust in dealing with global environmental shifts. We then propose an allocation policy, LinLUCB, which exploits information about global shifts across all arms in each environment. Empirical tests depict a significant improvement in our policies against other existing methods.

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。

↑