TargetedDataAcquisitionforEvolvingNegotiationAgentsMinaeKwon1SiddharthKaramcheti1Mariano-FlorentinoCue´llar2DorsaSadigh1Abstract(Baarslagetal.,2016;Leetal.,2018).Considerastandardnon-cooperativene...
Megaverse:SimulatingEmbodiedAgentsatOneMillionExperiencesperSecondAlekseiPetrenko12ErikWijmans13BrennanShacklett4VladlenKoltun1Figure1.Megaverseisanewresearchplatformthatsupportssimulatingembodieda...
CausalCuriosity:RLAgentsDiscoveringSelf-supervisedExperimentsforCausalRepresentationLearningSumedhASontakke1ArashMehrjou2LaurentItti1BernhardSchölkopf2Abstractform.Thus,therehasbeenrecentinteresti...
ProbingEmergentSemanticsinPredictiveAgentsviaQuestionAnsweringAbhishekDas1FedericoCarnevale2HamzaMerzic2LauraRimell2RosaliaSchneider2JoshAbramson2AldenHung2ArunAhuja2StephenClark2GregoryWayne2Felix...
CausalStrategicLinearRegressionYonadavShavit1BenjaminL.Edelman1BrianAxelrod2Abstractthen,aresomemodelskepthiddenfromtheviewofthosesubjecttotheirdecisions?Inmanypredictivedecision-makingscenarios,su...
BreakingtheCurseofManyAgents:ProvableMeanEmbeddingQ-IterationforMean-FieldReinforcementLearningLingxiaoWang1ZhuoranYang2ZhaoranWang1Abstract1998;Dzˇeroskietal.,2001;Guestrinetal.,2002;Karetal.,201...
StructuredAgentsforphysicalconstructionVictorBapst1AlvaroSanchez-Gonzalez1CarlDoersch1KimberlyL.Stachenfeld1PushmeetKohli1PeterW.Battaglia1JessicaB.Hamrick1AbstractPhysicalconstructioninvolvescompo...
AutomaticGoalGenerationforReinforcementLearningAgentsCarlosFlorensa1DavidHeld2XinyangGeng1PieterAbbeel13AbstracttodefeatachampionGoplayer(Silveretal.,2016),tooutperformhumansin49Atarigames(Guoetal....
Strongly-TypedAgentsareGuaranteedtoInteractSafelyDavidBalduzzi1Abstractbeadaptedtoanotherwithoutadverseeffects?Theprob-lemsfallundermechanismdesign,abranchofgametheoryAsartificialAgentsproliferate,...