Counterfactual Credit Assignment in Model-Free Reinforcement Learning.
Thomas MesnardThéophane WeberFabio ViolaShantanu ThakoorAlaa SaadeAnna HarutyunyanWill DabneyTom StepletonNicolas HeessArthur GuezMarcus HutterLars BuesingRémi MunosPublished in: CoRR (2020)