A General Framework for Safe Decision Making: A Convex Duality ApproachDownload PDF

Published: 05 Dec 2022, Last Modified: 05 May 2023MLSW2022Readers: Everyone
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.
1 Reply