@article{mathprogrammingbasedreinforcementlearnin, title = {Deep Policy Iteration with Integer Programming for Inventory Management}, author = {Pavithra Harsha and Ashish Jagmohan and Jayant Kalagnanam and Brian Quanz and Divya Singhvi}, year = {2021}, eprint = {2112.02215}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2112.02215v3}, }