Counterfactual Credit Assignment in Model-Free Reinforcement Learning.
Thomas MesnardTheophane WeberFabio ViolaShantanu ThakoorAlaa SaadeAnna HarutyunyanWill DabneyThomas S. StepletonNicolas HeessArthur GuezEric MoulinesMarcus HutterLars BuesingRémi MunosPublished in: ICML (2021)