Knowledge Transfer using Model-Based Deep Reinforcement Learning

• Published in: 2021 Southern African Universities Power Engineering Conference/Robotics and Mechatronics/Pattern Recognition Association of South Africa (SAUPEC/RobMech/PRASA) pp. 1 - 6
• Main Authors: Boloka, Tlou, Makondo, Ndivhuwo, Rosman, Benjamin
• Format: Conference Proceeding
• Language: English
• Published: IEEE 27.01.2021
• Subjects: Complexity theory; Convergence; Knowledge transfer; Reinforcement learning; Robots; Safety; Task analysis

Deep reinforcement learning has recently been adopted for robot behavior learning, where robot skills are acquired and adapted from data generated by the robot while interacting with its environment through a trial-and-error process. Despite this success, most model-free deep reinforcement learning...