MURAL Meta-Learning Uncertainty-Aware Rewards for Outcome-Driven Reinforcement Learning

MURAL:Meta-LearningUncertainty-AwareRewardsforOutcome-DrivenReinforcementLearningKevinLi1AbhishekGupta1VitchyrPong1AshwinReddy1AurickZhou1JustinYu1SergeyLevine1AbstractFigure1.MURAL:Ourmethodtrains...