arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2006.02119stat.MLcs.LG
收藏

具有中间观测值的非平稳时滞Bandits

Non-Stationary Delayed Bandits with Intermediate Observations

DeepMind

Claire Vernade, Andras Gyorgy, Timothy Mann

摘要:

在线推荐系统在接收反馈时通常会面临长时间的延迟,特别是在优化一些长期指标时。虽然在静态环境中减轻学习延迟的影响是众所周知的,但当环境发生变化时,这个问题变得更具挑战性。事实上,如果变化的时间尺度与延迟相当,就不可能了解环境,因为现有的观测已经过时。然而,如果中间信号没有延迟地可用,则可以解决所出现的问题,使得给定这些信号,系统的长期行为是稳定的。为了模拟这种情况,我们引入了随机的,非平稳的,延迟土匪与中间观测的问题。我们开发了一个计算效率高的算法UCRL的基础上,并证明次线性后悔保证其性能。实验结果表明,我们的方法是能够学习在非平稳的延迟环境中,现有的方法失败。

英文摘要:

Online recommender systems often face long delays in receiving feedback, especially when optimizing for some long-term metrics. While mitigating the effects of delays in learning is well-understood in stationary environments, the problem becomes much more challenging when the environment changes. In fact, if the timescale of the change is comparable to the delay, it is impossible to learn about the environment, since the available observations are already obsolete. However, the arising issues can be addressed if intermediate signals are available without delay, such that given those signals, the long-term behavior of the system is stationary. To model this situation, we introduce the problem of stochastic, non-stationary, delayed bandits with intermediate observations. We develop a computationally efficient algorithm based on UCRL, and prove sublinear regret guarantees for its performance. Experimental results demonstrate that our method is able to learn in non-stationary delayed environments where existing methods fail.

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。

↑