TY - Front. Comput. Sci. A1 - Lihong LI T1 - A perspective on off-policy evaluation in reinforcement learning Y1 - 2019-10-15 JF - Frontiers of Computer Science JO - Front. Comput. Sci. SP - 911 EP - 912 VL - 13 IS - 5 UR - https://journal.hep.com.cn/fcs N1 - 10.1007/s11704-019-9901-7 ER -