Offline Meta-Reinforcement Learning with Advantage Weighting

OfflineMeta-ReinforcementLearningwithAdvantageWeightingEricMitchell1RafaelRafailov1XueBinPeng2SergeyLevine2ChelseaFinn1Abstractofreinforcementlearningalgorithms,whenthegoalistoultimatelylearnmanyta...