MaximumEntropy-RegularizedMulti-GoalReinforcementLearningRuiZhao12XudongSun1VolkerTresp12AbstractOneofthebiggestchallengesinRListomaketheagentlearnefficientlyinapplicationswithsparserewards.ToInMul...
CURIOUS:IntrinsicallyMotivatedModularMulti-GoalReinforcementLearningCe´dricColas1PierreFournier2OlivierSigaud2MohamedChetouani2Pierre-YvesOudeyer1AbstractFigure1.TheModularGoalFetchArmenvironment....