arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2202.00867stat.MLcs.LG
收藏

学习控制具有不可观测上下文的强盗的有效算法

Efficient Algorithms for Learning to Control Bandits with Unobserved Contexts

Hongju Park, Mohamad Kazem Shirani Faradonbeh

摘要:

上下文强盗被广泛用于研究有限动作空间的基于学习的控制策略。虽然这个问题是很好的研究强盗与完美的观察上下文向量,很少有人知道的情况下,不完美的观察上下文。在这种情况下,现有的办法不适用,需要新的概念和技术框架。我们提出了一个可实现的后验抽样算法的土匪与不完美的背景下的意见,并研究其性能的学习最优决策。所提供的数值结果与算法的性能有关的不同数量的利益,包括武器的数量,尺寸,观察矩阵,后重新缩放因子,和信噪比。在一般情况下,所提出的算法暴露效率从噪声不完美的观察和采取相应的行动。启发性的理解,分析提供以及有趣的未来方向,它指向,以及进行了讨论。

英文摘要:

Contextual bandits are widely-used in the study of learning-based control policies for finite action spaces. While the problem is well-studied for bandits with perfectly observed context vectors, little is known about the case of imperfectly observed contexts. For this setting, existing approaches are inapplicable and new conceptual and technical frameworks are required. We present an implementable posterior sampling algorithm for bandits with imperfect context observations and study its performance for learning optimal decisions. The provided numerical results relate the performance of the algorithm to different quantities of interest including the number of arms, dimensions, observation matrices, posterior rescaling factors, and signal-to-noise ratios. In general, the proposed algorithm exposes efficiency in learning from the noisy imperfect observations and taking actions accordingly. Enlightening understandings the analyses provide as well as interesting future directions it points to, are discussed as well.

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。

↑