GradientDICE Rethinking Generalized Offline Estimation of Stationary Values

GradientDICE:RethinkingGeneralizedOfflineEstimationofStationaryValuesShangtongZhang1BoLiu2ShimonWhiteson1Abstractevaluationismoreflexible.Wecanevaluateanewpolicywithexistingdatainareplaybuffer(Lin,...