TiltingthePlayingfield:DynamicallossfunctionsformachinelearningMiguelRuiz-Garcia12GeZhang1SamuelS.Schoenholz3AndreaJ.Liu1Abstracttionscale(Glorot&Bengio,2010;Xiaoetal.,2018)orlearningrateschedule(H...
LearningWhilePlayinginMean-FieldGames:ConvergenceandOptimalityQiaominXie1ZhuoranYang2ZhaoranWang3AndreeaMinca1Abstractfromthescalabilityissue.Specifically,inamulti-agentsystem,eachagentinteractswit...
LearningbyPlaying–SolvingSparseRewardTasksfromScratchMartinRiedmiller1RolandHafner1ThomasLampe1MichaelNeunert1JonasDegrave1TomVandeWiele1VolodymyrMnih1NicolasHeess1TobiasSpringenberg1Abstractsimul...
InvestigatingHumanPriorsforPlayingVideoGamesRachitDubey1PulkitAgrawal1DeepakPathak1ThomasL.Griffiths1AlexeiA.Efros1AbstractFigure1.Motivatingexample.(a)Asimpleplatformergame.(b)Thesamegamemodifiedb...