A Family of Robust Stochastic Operators for Reinforcement Learning
Authors
Authors
- Yingdong Lu
- Mark Squillante
- Chai Wah Wu
We consider a new family of stochastic operators for reinforcement learning that seeks to alleviate negative effects and become more robust to approximation or estimation errors. Theoretical results are established, showing that our family of operators preserve optimality and increase the action gap in a stochastic sense. Empirical results illustrate the strong benefits of our robust stochastic operators, significantly outperforming the classical Bellman and recently proposed operators.
This work was published in NeurIPS 2019.
Please cite our work using the BibTeX below.
@inproceedings{NEURIPS2019_a44ba908,
author = {Lu, Yingdong and Squillante, Mark and Wu, Chai Wah},
booktitle = {Advances in Neural Information Processing Systems},
editor = {H. Wallach and H. Larochelle and A. Beygelzimer and F. d\textquotesingle Alch\'{e}-Buc and E. Fox and R. Garnett},
pages = {},
publisher = {Curran Associates, Inc.},
title = {A Family of Robust Stochastic Operators for Reinforcement Learning},
url = {https://proceedings.neurips.cc/paper/2019/file/a44ba9086b2b83ccf2baf7c678723449-Paper.pdf},
volume = {32},
year = {2019}
}