A General Framework for Safe Decision Making: A Convex Duality Approach
Abstract
We study the problem of online interaction in general decision making problems, where the objective is not only to find optimal strategies, but also to satisfy some safety guarantees, expressed in terms of costs accrued. We propose a theoretical framework to address such problems and present BAN-SOLO, a UCB-like algorithm that, in an online interaction with an unknown environment, attains sublinear regret of order O(T^1/2) and plays safely with high probability at each iteration. At its core, BAN-SOLO relies on tools from convex duality to manage environment exploration while satisfying the safety constraints imposed by the problem.
Cite
Text
Bernasconi et al. "A General Framework for Safe Decision Making: A Convex Duality Approach." NeurIPS 2022 Workshops: MLSW, 2022.Markdown
[Bernasconi et al. "A General Framework for Safe Decision Making: A Convex Duality Approach." NeurIPS 2022 Workshops: MLSW, 2022.](https://mlanthology.org/neuripsw/2022/bernasconi2022neuripsw-general/)BibTeX
@inproceedings{bernasconi2022neuripsw-general,
title = {{A General Framework for Safe Decision Making: A Convex Duality Approach}},
author = {Bernasconi, Martino and Cacciamani, Federico and Gatti, Nicola and Trovò, Francesco},
booktitle = {NeurIPS 2022 Workshops: MLSW},
year = {2022},
url = {https://mlanthology.org/neuripsw/2022/bernasconi2022neuripsw-general/}
}