We present a general, two-stage reinforcement learning approach to create robust policies that can be deployed on real robots without any additional training using a single demonstration generated by trajectory optimization. The demonstration is used in the first stage as a starting point to facilitate initial exploration. In the second stage, the relevant task reward is optimized directly and a policy robust to environment uncertainties is computed. We demonstrate and examine in detail the performance and robustness of our approach on highly dynamic hopping and bounding tasks on a quadruped robot.
@article{arxiv.2107.06629,
title = {Model-free Reinforcement Learning for Robust Locomotion using Demonstrations from Trajectory Optimization},
author = {Miroslav Bogdanovic and Majid Khadiv and Ludovic Righetti},
journal= {arXiv preprint arXiv:2107.06629},
year = {2022}
}