arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1507.01569cs.LGcs.AI
收藏

强调时间差异学习

Emphatic Temporal-Difference Learning

University of Alberta(阿尔伯塔大学)

A. Rupam Mahmood, Huizhen Yu, Martha White, Richard S. Sutton

摘要:

强调算法是时间差学习算法,其通过选择性地强调和不强调其在不同时间步长上的更新来改变其有效状态分布。Sutton,Mahmood and White(2015)和Yu(2015)最近的研究表明,通过以特定的方式改变重点,这些算法在使用线性函数近似的非策略训练下变得稳定和收敛。本文作为一个统一的总结,从两个工程的可用结果。此外,我们证明了经验的好处,从灵活性的算法,包括状态相关的折扣,状态相关的自举,和用户指定的函数近似资源的分配。

英文摘要:

Emphatic algorithms are temporal-difference learning algorithms that change their effective state distribution by selectively emphasizing and de-emphasizing their updates on different time steps. Recent works by Sutton, Mahmood and White (2015), and Yu (2015) show that by varying the emphasis in a particular way, these algorithms become stable and convergent under off-policy training with linear function approximation. This paper serves as a unified summary of the available results from both works. In addition, we demonstrate the empirical benefits from the flexibility of emphatic algorithms, including state-dependent discounting, state-dependent bootstrapping, and the user-specified allocation of function approximation resources.

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。

↑