MyopicPosteriorSamplingforAdaptiveGoalOrientedDesignofExperimentsKirthevasanKandasamy1WillieNeiswanger1ReedZhang1AkshayKrishnamurthy2JeffSchneider1Barnaba´sPo´czos1Abstractity.Onadifferentday,she...
AutomaticGoalGenerationforReinforcementLearningAgentsCarlosFlorensa1DavidHeld2XinyangGeng1PieterAbbeel13AbstracttodefeatachampionGoplayer(Silveretal.,2016),tooutperformhumansin49Atarigames(Guoetal....