Robust Q-Learning for finite ambiguity sets

📅 2024-07-05
🏛️ arXiv.org
📈 Citations: 0
Influential: 0
📄 PDF
🤖 AI Summary
This paper studies distributionally robust Markov decision processes (DR-MDPs), addressing the limitation of existing approaches that rely exclusively on Wasserstein- or KL-divergence-based ambiguity sets. We propose the first online Q-learning algorithm applicable to *arbitrary* finite-support probability measure ambiguity sets. Methodologically, we integrate robust optimization with Q-learning to construct an iterative update framework grounded in distributionally robust dynamic programming, and establish its convergence under standard assumptions. Our contributions are threefold: (1) the first Q-learning framework supporting arbitrarily structured finite-support ambiguity sets—eliminating dependence on specific distance metrics; (2) an online learning mechanism with theoretical convergence guarantees; and (3) flexible user-specified ambiguity sets better aligned with real-world uncertainty structures. Numerical experiments demonstrate the algorithm’s computational efficiency, scalability, and significantly enhanced policy robustness under model misspecification.

Technology Category

Application Category

📝 Abstract
In this paper we propose a novel $Q$-learning algorithm allowing to solve distributionally robust Markov decision problems for which the ambiguity set of probability measures can be chosen arbitrarily as long as it comprises only a finite amount of measures. Therefore, our approach goes beyond the well-studied cases involving ambiguity sets of balls around some reference measure with the distance to reference measure being measured with respect to the Wasserstein distance or the Kullback--Leibler divergence. Hence, our approach allows the applicant to create ambiguity sets better tailored to her needs and to solve the associated robust Markov decision problem via a $Q$-learning algorithm whose convergence is guaranteed by our main result. Moreover, we showcase in several numerical experiments the tractability of our approach.
Problem

Research questions and friction points this paper is trying to address.

Develops robust Q-Learning for finite ambiguity sets
Solves distributionally robust Markov decision problems
Ensures algorithm convergence with tailored ambiguity sets
Innovation

Methods, ideas, or system contributions that make the work stand out.

Robust Q-learning algorithm
Finite ambiguity sets
Customizable probability measures
🔎 Similar Papers
No similar papers found.
C
C'ecile Decker
National University of Singapore, Department of Mathematics, 21 Lower Kent Ridge Road, 119077
J
Julian Sester
National University of Singapore, Department of Mathematics, 21 Lower Kent Ridge Road, 119077