Robust Best-arm Identification in Linear Bandits
Not on the map. Why?
Abstract (arXiv)
We study the robust best-arm identification problem (RBAI) in the case of linear rewards. The primary objective is to identify a near-optimal robust arm, which involves selecting arms at every round and assessing their robustness by exploring potential adversarial actions. This approach is particularly relevant when utilizing a simulator and seeking to identify a robust solution for real-world transfer. To this end, we present an instance-dependent lower bound for the robust best-arm identification problem with linear rewards. Furthermore, we propose both static and adaptive bandit algorithms that achieve sample complexity that matches the lower bound. In synthetic experiments, our algorithms effectively identify the best robust arm and perform similarly to the oracle strategy. As an application, we examine diabetes care and the process of learning insulin dose recommendations that are robust with respect to inaccuracies in standard calculators. Our algorithms prove to be effective in identifying robust dosage values across various age ranges of patients.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 17 of its 37 references that are in the map. First posted on arXiv 8 Nov 2023.
Builds on
17 of 37 references.
References · 17
- 2014On the Complexity of Best Arm Identification in Multi-Armed Bandit Modelscited by 280
- 2020Ethical Machine Learning in Health Carecited by 112
- 2014Best-Arm Identification in Linear Banditscited by 98
- 2019Linear Stochastic Bandits Under Safety Constraintscited by 90
- 2019Sequential Experimental Design for Transductive Linear Banditscited by 88
- 2020Stochastic Bandits with Linear Constraintscited by 68
- 2020Stochastic Linear Bandits Robust to Adversarial Attackscited by 65
- 2018Adversarially Robust Optimization with Gaussian Processescited by 61
- 2020Gamification of Pure Exploration for Linear Banditscited by 61
- 2022Nearly Optimal Algorithms for Linear Contextual Bandits with Adversarial Corruptionscited by 51
- 2019Safe Linear Thompson Sampling with Side Informationcited by 37
- 2021Robust Stochastic Linear Contextual Bandits Under Adversarial Attackscited by 33
5 more
- 2019Safe Linear Stochastic Banditscited by 27
- 2020Deep Reinforcement Learning for Closed-Loop Blood Glucose Controlcited by 26
- 2021Best Arm Identification with Safety Constraintscited by 25
- 2022Interactively Learning Preference Constraints in Linear Banditscited by 11
- 2021Safe Linear Leveling Banditscited by 1
Built on by
Not cited yet.