TY - RPRT TI - Safe Off-Policy Deep Reinforcement Learning Algorithm for Volt-VAR Control in Power Distribution Systems AU - Wang, Wei AU - Yu, Nanpeng (ORCID:0000000150865465) AU - Gao, Yuanqi (ORCID:0000000340786143) AU - Shi, Jie (ORCID:0000000217600462) PY - 2020 DO - 10.1109/tsg.2019.2962625 UR - https://www.osti.gov/biblio/1801325 ID - 1801325 ER -