Stable and Efficient Policy Evaluation

Daoming Lyu, Bo Liu, Matthieu Geist, Wen Dong, Saad Biaz, Qi Wang

科研成果: 期刊稿件文章同行评审

8 引用 (Scopus)

摘要

Policy evaluation algorithms are essential to reinforcement learning due to their ability to predict the performance of a policy. However, there are two long-standing issues lying in this prediction problem that need to be tackled: off-policy stability and on-policy efficiency. The conventional temporal difference (TD) algorithm is known to perform very well in the on-policy setting, yet is not off-policy stable. On the other hand, the gradient TD and emphatic TD algorithms are off-policy stable, but are not on-policy efficient. This paper introduces novel algorithms that are both off-policy stable and on-policy efficient by using the oblique projection method. The empirical experimental results on various domains validate the effectiveness of the proposed approach.

源语言英语
文章编号8515047
页(从-至)1831-1840
页数10
期刊IEEE Transactions on Neural Networks and Learning Systems
30
6
DOI
出版状态已出版 - 6月 2019

指纹

探究 'Stable and Efficient Policy Evaluation' 的科研主题。它们共同构成独一无二的指纹。

引用此