paper-with-me

홈 › Papers

Best Arm Identification with Safety Constraints

2021-11-23 · Zhenlin Wang, Andrew Wagenmaker, Kevin Jamieson

The best arm identification problem in the multi-armed bandit setting is an excellent model of many real-world decision-making problems, yet it fails to capture the fact that in the real-world, safety constraints often must be met while learning. In this work we study the question of best-arm identification in safety-critical settings, where the goal of the agent is to find the best safe option out of many, while exploring in a way that guarantees certain, initially unknown safety constraints are met. We first analyze this problem in the setting where the reward and safety constraint takes a linear structure, and show nearly matching upper and lower bounds. We then analyze a much more general version of the problem where we only assume the reward and safety constraint can be modeled by monotonic functions, and propose an algorithm in this setting which is guaranteed to learn safely. We conclude with experimental results demonstrating the effectiveness of our approaches in scenarios such as safely identifying the best drug out of many in order to treat an illness.

📄 PDF Abstract BibTeX arXiv:2111.12151

Code (1)

Criss-Wang/BAI-with-Safety-Constraint

Tasks

Decision Making

Similar Papers 제목 키워드 기반

Active Learning with Safety Constraints

2022-06-22 · Romain Camilleri, Andrew Wagenmaker, Jamie Morgenstern, Lalit Jain 외

Active learning methods have shown great promise in reducing the number of samples necessary for learning. As automated learning systems are adopted into real-time, real-world decision-making pipelines, it is increasingl…

Active LearningDecision MakingExperimental Design

Safe Q-learning for continuous-time linear systems

2023-04-26 · Soutrik Bandyopadhyay, Shubhendu Bhasin

Q-learning is a promising method for solving optimal control problems for uncertain systems without the explicit need for system identification. However, approaches for continuous-time Q-learning have limited provable sa…

Q-Learning

Price of Safety in Linear Best Arm Identification

2023-09-15 · Xuedong Shang, Igor Colin, Merwan Barlier, Hamza Cherkaoui

We introduce the safe best-arm identification framework with linear feedback, where the agent is subject to some stage-wise safety constraint that linearly depends on an unknown parameter vector. The agent must take acti…

Constrained Best Arm Identification with Tests for Feasibility

2025-11-12 · Ting Cai, Kirthevasan Kandasamy arxiv

Best arm identification (BAI) aims to identify the highest-performance arm among a set of $K$ arms by collecting stochastic samples from each arm. In real-world problems, the best arm needs to satisfy additional feasibil…

Drug Discovery

Reinforcement Learning for Optimal Experiment Design in Parameter Identification of Mechatronic Systems

2026-05-19 · Julian Langschwert, Georg Schaefer, Jakob Rehrl, Stefan Huber 외 arxiv

Informative excitation signals are critical for accurate system identification of mechatronic systems, yet classical system identification (SI) approaches require expert knowledge and hand-crafted signal design to respec…

Reinforcement Learning