Abstract
We consider the problem of remanufacturing planning in the presence of statistical estimation errors. We model this problem as a robust Markov decision process, where the true system transition probability is assumed to be unknown but lie in an interval-based uncertainty set. We establish structural properties of optimal robust policies under this uncertainty set. A computational study on the NASA turbofan engine shows that our data-driven decision framework consistently yields better worst-case performances and higher reliability of the performance guarantee.