@inproceedings{tang2020taylor,
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 (e.g., TRPO) 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.},
author = {Tang, Yunghao and Valko, Michal and Munos, R{\'{e}}mi},
booktitle = {International Conference on Machine Learning},
title = {{Taylor expansion policy optimization}},
year = {2020}
}