arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2603.26982stat.MLcs.AIcs.LG
收藏

在线统计推断常样本均值Q学习

Online Statistical Inference of Constant Sample-averaged Q-Learning

University of Houston(休斯顿大学);Texas Tech University(德克萨斯理工大学)

Saunak Kumar Panda, Tong Li, Ruiqi Liu, Yisha Xiang

AI总结:

本文提出一种在线统计推断框架,用于改进样本均值Q学习算法,通过功能中心极限定理和随机缩放构建置信区间,实验验证了改进方法在网格世界和动态资源匹配问题中的性能。

摘要:

强化学习算法在各种领域中被广泛用于决策任务。然而,这些算法的性能可能受到高方差和不稳定性的影响,特别是在存在噪声或稀疏奖励的环境中。本文提出了一种框架,用于对样本均值Q学习方法进行统计在线推断。我们适应功能中心极限定理(FCLT)以适应修改后的算法,在某些一般条件下,并通过随机缩放构建Q值的置信区间。我们进行了实验,对修改后的算法及其传统对应物Q学习进行推断,使用随机缩放报告了它们在两个问题上的覆盖率和置信区间宽度:一个网格世界问题作为简单的玩具示例,以及一个动态资源匹配问题作为现实世界的比较示例。

英文摘要:

Reinforcement learning algorithms have been widely used for decision-making tasks in various domains. However, the performance of these algorithms can be impacted by high variance and instability, particularly in environments with noise or sparse rewards. In this paper, we propose a framework to perform statistical online inference for a sample-averaged Q-learning approach. We adapt the functional central limit theorem (FCLT) for the modified algorithm under some general conditions and then construct confidence intervals for the Q-values via random scaling. We conduct experiments to perform inference on both the modified approach and its traditional counterpart, Q-learning using random scaling and report their coverage rates and confidence interval widths on two problems: a grid world problem as a simple toy example and a dynamic resource-matching problem as a real-world example for comparison between the two solution approaches.

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。

↑