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 |
卷 | 30 |
期 | 6 |
DOI | |
出版状态 | 已出版 - 6月 2019 |