Reinforced iLQR: A Sample-Efficient Robot Locomotion Learning
Authors:
- 30 May 2021
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 5906-5913
Abstract
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.Keywords
This publication has 18 references indexed in Scilit:
- Optimization-based locomotion planning, estimation, and control design for the atlas humanoid robotAutonomous Robots, 2015
- Value function approximation and model predictive control2013
- Efficient parallel coordinate descent algorithm for convex optimization problems with separable constraints: Application to distributed MPCJournal of Process Control, 2013
- Synthesis and stabilization of complex behaviors through online trajectory optimization2012
- MuJoCo: A physics engine for model-based control2012
- A generalized iterative LQG method for locally-optimal feedback control of constrained nonlinear stochastic systems2005
- The explicit linear quadratic regulator for constrained systemsAutomatica, 2002
- Dyna, an integrated architecture for learning, planning, and reactingACM SIGART Bulletin, 1991
- Planning by Incremental Dynamic Programming1991
- Integrated Architectures for Learning, Planning, and Reacting Based on Approximating Dynamic Programming1990