UAI 2024poster0 citations
Offline Reward Perturbation Boosts Distributional Shift in Online RL
Zishun Yu, Siteng Kang, Xinhua Zhang
Abstract
Offline-to-online reinforcement learning has recently been shown effective in reducing the online sample complexity by first training from offline collected data. However, this additional data source may also invite new poisoning attacks that target offline training. In this work, we reveal such vulnerabilities in
BibTeX
@InProceedings{pmlr-v244-yu24a,
title = {Offline Reward Perturbation Boosts Distributional Shift in Online RL},
author = {Yu, Zishun and Kang, Siteng and Zhang, Xinhua},
booktitle = {Proceedings of the Fortieth Conference on Uncertainty in Artificial Intelligence},
pages = {4041--4055},
year = {2024},
editor = {Kiyavash, Negar and Mooij, Joris M.},
volume = {244},
series = {Proceedings of Machine Learning Research},
month = {15--19 Jul},
publisher = {PMLR},
pdf = {https://raw.githubusercontent.com/mlresearch/v244/main/assets/yu24a/yu24a.pdf},
url = {https://proceedings.mlr.press/v244/yu24a.html},
abstract = {Offline-to-online reinforcement learning has recently been shown effective in reducing the online sample complexity by first training from offline collected data. However, this additional data source may also invite new poisoning attacks that target offline training. In this work, we reveal such vulnerabilities in