Optimistic reinforcement learning by forward Kullback–Leibler divergence optimization
Taisuke Kobayashi
Topics & Concepts
Reinforcement learningDivergence (linguistics)Computer scienceKullback–Leibler divergenceMathematical optimizationHyperparameterOptimization problemArtificial intelligenceBellman equationMarkov decision processMachine learningMathematicsMarkov processStatisticsLinguisticsPhilosophyReinforcement Learning in RoboticsAdversarial Robustness in Machine LearningAdvanced Multi-Objective Optimization Algorithms