Blind Network Revenue Management and Bandits with Knapsacks Under Limited Switches

• 成果类型: Article
• 署名作者: Simchi-Levi, David; Xu, Yunzong; Zhao, Jinglong
• 署名单位: Massachusetts Institute of Technology (MIT); Massachusetts Institute of Technology (MIT); University of Illinois System; University of Illinois Urbana-Champaign; Boston University
• 刊物名称: OPERATIONS RESEARCH
• ISSN/ISSBN: 0030-364X
• DOI: 10.1287/opre.2020.0753
• 发表日期: 2025
• 关键词: bid prices; demand; MODEL

摘要

This paper studies the impact of limited switches on resource-constrained dynamic pricing with demand learning. We focus on the classical price-based blind network revenue management problem and extend our results to the bandits with knapsacks problem. In both settings, a decision maker faces stochastic and distributionally unknown demand, and must allocate finite initial inventory across multiple resources over time. In addition to standard resource constraints, we impose a switching constraint that limits the number of allowable action changes over the time horizon. We establish matching upper and lower bounds on the optimal regret and develop computationally efficient limitedswitch algorithms that achieve it. We show that the optimal regret rate is fully characterized by a piecewise-constant function of the switching budget, which further depends on the number of resource constraints. Our results highlight the fundamental role of resource constraints in shaping the statistical complexity of online learning under limited switches. Extensive simulations demonstrate that our algorithms maintain strong cumulative reward performance while significantly reducing the number of switches.