Taylor Expansion Policy Optimization
Abstract
In this work, we investigate the application of Taylor expansions in reinforcement learning. In particular, we propose Taylor Expansion Policy Optimization, a policy optimization formalism that generalizes prior work as a first-order special case. We also show that Taylor expansions intimately relate to off-policy evaluation. Finally, we show that this new formulation entails modifications which improve the performance of several state-of-the-art distributed algorithms.
Cite
Text
Tang et al. "Taylor Expansion Policy Optimization." International Conference on Machine Learning, 2020.Markdown
[Tang et al. "Taylor Expansion Policy Optimization." International Conference on Machine Learning, 2020.](https://mlanthology.org/icml/2020/tang2020icml-taylor/)BibTeX
@inproceedings{tang2020icml-taylor,
title = {{Taylor Expansion Policy Optimization}},
author = {Tang, Yunhao and Valko, Michal and Munos, Remi},
booktitle = {International Conference on Machine Learning},
year = {2020},
pages = {9397-9406},
volume = {119},
url = {https://mlanthology.org/icml/2020/tang2020icml-taylor/}
}