The Mirage of Action-Dependent Baselines in Reinforcement Learning

TheMirageofAction-DependentBaselinesinReinforcementLearningGeorgeTucker1SuryaBhupatiraju12ShixiangGu134RichardE.Turner3ZoubinGhahramani35SergeyLevine16Abstractetal.,2015a;2017)areaclassofmodel-free...