TY - GEN
T1 - Reinforced iLQR
T2 - 2021 IEEE International Conference on Robotics and Automation, ICRA 2021
AU - Zong, Tongyu
AU - Sun, Liyang
AU - Liu, Yong
N1 - Publisher Copyright:
© 2021 IEEE
PY - 2021
Y1 - 2021
N2 - Robot locomotion is a major challenge in robotics. Model-based approaches are vulnerable to model errors, and incur high computation overhead resulted from long control horizon. Model-free approaches are trained with a large number of training samples, which are expensive to obtain. In this paper, we develop a hybrid control and learning framework, called Reinforced iLQR (RiLQR), which combines the advantages of model-based iLQR control with model-free RL policy learning to simultaneously achieve high sample efficiency, low computation overhead, and high robustness against model errors in robot locomotion. Through extensive evaluation on the Mujoco platform, we demonstrate that RiLQR outperforms the state-of-the-art model-based and model-free baselines by big margins in a set of tasks with different complexities.
AB - Robot locomotion is a major challenge in robotics. Model-based approaches are vulnerable to model errors, and incur high computation overhead resulted from long control horizon. Model-free approaches are trained with a large number of training samples, which are expensive to obtain. In this paper, we develop a hybrid control and learning framework, called Reinforced iLQR (RiLQR), which combines the advantages of model-based iLQR control with model-free RL policy learning to simultaneously achieve high sample efficiency, low computation overhead, and high robustness against model errors in robot locomotion. Through extensive evaluation on the Mujoco platform, we demonstrate that RiLQR outperforms the state-of-the-art model-based and model-free baselines by big margins in a set of tasks with different complexities.
UR - http://www.scopus.com/inward/record.url?scp=85125444759&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85125444759&partnerID=8YFLogxK
U2 - 10.1109/ICRA48506.2021.9561223
DO - 10.1109/ICRA48506.2021.9561223
M3 - Conference contribution
AN - SCOPUS:85125444759
T3 - Proceedings - IEEE International Conference on Robotics and Automation
SP - 5906
EP - 5913
BT - 2021 IEEE International Conference on Robotics and Automation, ICRA 2021
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 30 May 2021 through 5 June 2021
ER -