Sample-efficient backtrack temporal difference deep reinforcement learning
Qi Liu, Pengbin Chen, Ke Lin, Kaidong Zhao, Jinliang Ding, Yanjie Li
Topics & Concepts
Reinforcement learningTemporal difference learningComputer scienceArtificial intelligenceControl (management)Sampling (signal processing)Machine learningBellman equationAction (physics)PrioritizationValue (mathematics)Representation (politics)Task analysisDeep learningLimit (mathematics)Mode (computer interface)Active learning (machine learning)Stability (learning theory)Performance improvementFace (sociological concept)Q-learningFunction (biology)Multi-task learningAlgorithmProbably approximately correct learningFunction approximationImportance samplingSemi-supervised learningScale (ratio)Reinforcement Learning in RoboticsSmart Grid Energy ManagementAdaptive Dynamic Programming Control