Interactive Learning from Policy-Dependent Human Feedback

InteractiveLearningfromPolicy-DependentHumanFeedbackJamesMacGlashan1MarkKHo2RobertLoftin3BeiPeng4GuanWang2DavidL.Roberts3MatthewE.Taylor4MichaelL.Littman2Abstractbehaviorusingthesesimplesignals.Ind...