@article{orsoacceleratingrewarddesignviaonline, title = {ORSO: Accelerating Reward Design via Online Reward Selection and Policy Optimization}, author = {Chen Bo Calvin Zhang and Zhang-Wei Hong and Aldo Pacchiano and Pulkit Agrawal}, year = {2024}, eprint = {2410.13837}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2410.13837v3}, }