Self-Paced Deep Reinforcement Learning
Pascal Klink1 , Carlo D’Eramo1 , Jan Peters1 , Joni Pajarinen1,2
1
Intelligent Autonomous Systems, Technische Universitt Darmstadt, Germany
2
Department of Electrical Engineering and Automation, Aalto University, Finland
Correspondence to: pascal.klink@tu-darmstadt.de
Abstract
Curriculum reinforcement learning (CRL) improves the learning speed and stability
of an agent by expos ...


雷达卡


京公网安备 11010802022788号







