Curriculum learning for robotic agents

• Main Author: Kurkcu, Anil
• Other Authors: Domenico Campolo
• Format: Thesis-Doctor of Philosophy
• Language: English
• Published: Nanyang Technological University 2022
• Subjects: Engineering::Mechanical engineering::Robots; Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence
• Online Access: https://hdl.handle.net/10356/160311
• Institution: Nanyang Technological University

Model-free deep RL algorithms, rooted in the concept of tabula rasa, suffer from poor sample efficiency, which is a major drawback for these methods to be applicable to real-world robotics problems. To improve sample efficiency, curriculum learning leverages prior knowledge in a way to solve diff...