arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2111.12151cs.LGstat.ML
收藏

具有安全约束的最佳手臂识别

Best Arm Identification with Safety Constraints

National University of Singapore(新加坡国立大学);University of Washington(华盛顿大学)

Zhenlin Wang, Andrew Wagenmaker, Kevin Jamieson

摘要:

多臂强盗环境中的最佳臂识别问题是许多现实世界决策问题的一个很好的模型,但它未能捕捉到这样一个事实,即在现实世界中,学习时通常必须满足安全约束。在这项工作中,我们研究的最佳武器识别的安全关键设置,代理的目标是找到最好的安全选项了许多,同时探索的方式,保证某些,最初未知的安全约束得到满足的问题。我们首先分析这个问题的设置中的奖励和安全约束采取线性结构,并显示几乎匹配的上限和下限。然后,我们分析了一个更一般的版本的问题,我们只假设奖励和安全约束可以由单调函数建模,并提出了一个算法,在这种设置,这是保证学习安全。最后,我们的实验结果证明了我们的方法在某些情况下的有效性,例如安全地从众多药物中选出最好的药物来治疗疾病。

英文摘要:

The best arm identification problem in the multi-armed bandit setting is an excellent model of many real-world decision-making problems, yet it fails to capture the fact that in the real-world, safety constraints often must be met while learning. In this work we study the question of best-arm identification in safety-critical settings, where the goal of the agent is to find the best safe option out of many, while exploring in a way that guarantees certain, initially unknown safety constraints are met. We first analyze this problem in the setting where the reward and safety constraint takes a linear structure, and show nearly matching upper and lower bounds. We then analyze a much more general version of the problem where we only assume the reward and safety constraint can be modeled by monotonic functions, and propose an algorithm in this setting which is guaranteed to learn safely. We conclude with experimental results demonstrating the effectiveness of our approaches in scenarios such as safely identifying the best drug out of many in order to treat an illness.

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。

↑