@article{instrumentalvariablevalueiterationfor, title = {Instrumental Variable Value Iteration for Causal Offline Reinforcement Learning}, author = {Luofeng Liao and Zuyue Fu and Zhuoran Yang and Yixin Wang and Mladen Kolar and Zhaoran Wang}, year = {2021}, eprint = {2102.09907}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2102.09907v3}, }