Hao, Meiling, Su, Pingfan, Hu, Liyuan, Szabo, Zoltan ORCID: 0000-0001-6183-7603, Zhao, Qianyu and Shi, Chengchun ORCID: 0000-0001-7773-2099 (2024) Forward and backward state abstractions for off-policy evaluation. . arXiv. (Submitted)