@article{mindthegapofflinepolicyoptimizationfor, title = {Mind the Gap: Offline Policy Optimization for Imperfect Rewards}, author = {Jianxiong Li and Xiao Hu and Haoran Xu and Jingjing Liu and Xianyuan Zhan and Qing-Shan Jia and Ya-Qin Zhang}, year = {2023}, eprint = {2302.01667}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2302.01667v1}, }