Are you an EPFL student looking for a semester project?
Work with us on data science and visualisation projects, and deploy your project as an app on top of Graph Search.
The concept of priority indices defined to discuss the Restless Bandit Problem (RBP) furnish a relevant approximative framework to approach the optimal scheduling of a multi-products make-to-stock production when no setup cost and/or time are incurred. The resulting policy involves switching curves and hedging stocks. At each time, the index policy selects the item to be produced for any global state of the net inventories. Moreover, the optimal hedging level is also reproduced for a single item problem.
Paolo Tombesi, Milinda Pathiraja
Corentin Jean Dominique Fivet, Gennaro Senatore, Jan Friedrich Georg Brütting