information and develop online learning algorithms whose average profit approaches that of the optimal (s,S,p) with a tight O ̃ …(√T) regret rate. A number of salient features differentiate our work from the existing online learning researches in the OM … involving unknown quantities, which is different from the majority of learning problems in operations management that only …

absolute difference between the expected profit of the data-driven policy and the expected optimal profit. A simulation study …