Off-policy RL algorithms can be sample-efficient for continuous control via sample multiple reuse
Jiafei Lyu, Le Wan, Xiu Li, Zongqing Lu
Topics & Concepts
HyperparameterComputer scienceReuseReinforcement learningSample (material)AlgorithmConvergence (economics)Control (management)Base (topology)Machine learningArtificial intelligenceMathematicsEconomicsMathematical analysisBiologyEconomic growthEcologyChromatographyChemistryReinforcement Learning in RoboticsEvolutionary Algorithms and ApplicationsAdaptive Dynamic Programming Control