AI RESEARCH
Cost-Ordered Feasibility for Multi-Armed Bandits with Cost Subsidy
arXiv CS.LG
•
ArXi:2605.07171v1 Announce Type: new The classic multi-armed bandit (MAB) problem tackles the challenge of accruing maximum reward while making decisions under uncertainty. However, in applications, often the goal is to minimize cost subject to a constraint on the minimum permissible reward, an objective captured by multi-armed bandits with cost-subsidy (MAB-CS). Of interest to this paper is the setting where the quality (reward) constraint is specified relative to the unknown best reward and the cost of each arm is known.