2019 · 40 citations · 5 references
BusinessDecision SciencesIndustrial EngineeringInventory ControlInventory ManagementMarkov Decision ProcessesInventory TheoryReinforcement LearningStochastic ControlStochastic Inventory ModelsStochastic OptimizationStochastic ProgrammingBandit AlgorithmsCensored DistributionsConvexityConvexity AnalysisMarkov Decision ModelsStochastic BanditsStochastic Convex Optimization
We consider a stochastic inventory control problem under censored demands, lost sales, and positive lead times. This is a fundamental problem in inventory management, with significant literature establishing near-optimality of a simple class of policies called "base-stock policies" for the underlying Markov Decision Process (MDP), as well as convexity of long run average-cost under those policies. We consider the relatively less studied problem of designing a learning algorithm for this problem when the underlying demand distribution is unknown. The goal is to bound regret of the algorithm when compared to the best base-stock policy. We utilize the convexity properties and a newly derived bound on bias of base-stock policies to establish a connection to stochastic convex bandit optimization.
5
Stochastic Convex Optimization with Bandit Feedback
Alekh Agarwal, Dean P. Foster, Daniel Hsu et al. · SIAM Journal on Optimization · 2013 · 50 citations · Full text