@article{constraintgenerationpolicyoptimization, title = {Constraint-Generation Policy Optimization (CGPO): Nonlinear Programming for Policy Optimization in Mixed Discrete-Continuous MDPs}, author = {Michael Gimelfarb and Ayal Taitler and Scott Sanner}, year = {2024}, eprint = {2401.12243}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2401.12243v2}, }