arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2102.06129cs.LGstat.ML
收藏

Meta-Thompson抽样

Meta-Thompson Sampling

Google Research(谷歌研究院);University of Alberta(阿尔伯塔大学);DeepMind(深度思维)

Branislav Kveton, Mikhail Konobeev, Manzil Zaheer, Chih-wei Hsu, Martin Mladenov, Craig Boutilier, Csaba Szepesvari

摘要:

如何有效地进行网络学习是在线学习的一个基本问题。我们提出了一个变体的汤普森采样,学习更好地探索,因为它与来自未知的先验的强盗实例相互作用。该算法元学习先验知识,因此我们称之为MetaTS。我们提出了几种有效的实现MetaTS和分析它在高斯强盗。我们的分析显示了元学习的好处,是一个更广泛的兴趣,因为我们得到了一个新的先验依赖贝叶斯后悔界汤普森采样。我们的理论得到了实证评估的补充,这表明MetaTS能够快速适应未知的先验。

英文摘要:

Efficient exploration in bandits is a fundamental online learning problem. We propose a variant of Thompson sampling that learns to explore better as it interacts with bandit instances drawn from an unknown prior. The algorithm meta-learns the prior and thus we call it MetaTS. We propose several efficient implementations of MetaTS and analyze it in Gaussian bandits. Our analysis shows the benefit of meta-learning and is of a broader interest, because we derive a novel prior-dependent Bayes regret bound for Thompson sampling. Our theory is complemented by empirical evaluation, which shows that MetaTS quickly adapts to the unknown prior.

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。

↑