arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2003.05878cs.LGcs.AImath.SP
收藏

基于流形分析的无报酬期权发现

Option Discovery in the Absence of Rewards with Manifold Analysis

Technion, Israel Institute of Technology(以色列理工学院)

Amitay Bar, Ronen Talmon, Ron Meir

摘要:

选项已被证明是强化学习的有效工具,有助于改善探索和学习。在本文中,我们提出了一种基于谱图理论的方法,并推导出一种算法,系统地发现选项,而无需访问特定的奖励或任务分配。与以往的方法不同,我们的算法充分利用了图的Laplacian谱。与更高的图形频率相关联的扩展模式解开域的微妙之处,这被证明是有用的选项发现。使用几何和流形为基础的分析,我们提出了一个理论上的理由的算法。此外,我们还展示了它在几个领域的性能,与竞争方法相比有明显的改进。

英文摘要:

Options have been shown to be an effective tool in reinforcement learning, facilitating improved exploration and learning. In this paper, we present an approach based on spectral graph theory and derive an algorithm that systematically discovers options without access to a specific reward or task assignment. As opposed to the common practice used in previous methods, our algorithm makes full use of the spectrum of the graph Laplacian. Incorporating modes associated with higher graph frequencies unravels domain subtleties, which are shown to be useful for option discovery. Using geometric and manifold-based analysis, we present a theoretical justification for the algorithm. In addition, we showcase its performance in several domains, demonstrating clear improvements compared to competing methods.

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。

↑