arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1602.04282stat.MLcs.LG
收藏

保守的强盗

Conservative Bandits

University of Alberta(阿尔伯塔大学)

Yifan Wu, Roshan Shariff, Tor Lattimore, Csaba Szepesvári

摘要:

我们研究了一种新的多臂强盗问题,该问题模拟了一家希望探索新策略以最大化收入的公司所面临的挑战,同时将其收入保持在固定基线以上,并随着时间的推移保持一致。虽然以前的工作解决了这个问题下的较弱的要求,保持收入约束,只有在一个给定的固定时间在未来,以前提出的算法是不合适的,由于他们的设计下更严格的约束。我们考虑了随机和对抗性设置,在那里我们提出了自然但新颖的策略,并分析了维持约束的价格。除其他事项外,我们证明了高概率和期望界的遗憾,同时我们也考虑了保持高概率或期望的约束的问题。对于对抗设置,维持约束的代价似乎更高,至少对于所考虑的算法来说是这样。给出了一个下界,表明该算法的随机设置几乎是最优的。在合成环境中获得的实证结果补充了我们的理论研究结果。

英文摘要:

We study a novel multi-armed bandit problem that models the challenge faced by a company wishing to explore new strategies to maximize revenue whilst simultaneously maintaining their revenue above a fixed baseline, uniformly over time. While previous work addressed the problem under the weaker requirement of maintaining the revenue constraint only at a given fixed time in the future, the algorithms previously proposed are unsuitable due to their design under the more stringent constraints. We consider both the stochastic and the adversarial settings, where we propose, natural, yet novel strategies and analyze the price for maintaining the constraints. Amongst other things, we prove both high probability and expectation bounds on the regret, while we also consider both the problem of maintaining the constraints with high probability or expectation. For the adversarial setting the price of maintaining the constraint appears to be higher, at least for the algorithm considered. A lower bound is given showing that the algorithm for the stochastic setting is almost optimal. Empirical results obtained in synthetic environments complement our theoretical findings.

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。

↑