TY - RPRT TI - Batch reinforcement learning for network-safe demand response in unknown electric grids AU - Lesage-Landry, Antoine (ORCID:0000000196526557) AU - Callaway, Duncan S. PY - 2022 DO - 10.1016/j.epsr.2022.108375 UR - https://www.osti.gov/biblio/1877762 ID - 1877762 ER -