Contextual Bandits with Knapsacks for a Conversion Model Zhen Li BNP Paribas, 16 boulevard des Italiens, 75009 Paris, France HEC Paris, 1 rue de la Libération, 78350 Jouy-en-Josas, France

We consider contextual bandits with knapsacks, with an underlying structure between rewards generated and cost vectors suffered. We do so motivated by sales with commercial discounts. At each round, given the stochastic i.i.d.