Multi-Modal Imitation Learning from Unstructured Demonstrations using Generative Adversarial Nets
Karol Hausman, Yevgen Chebotar, Stefan Schaal, Gaurav Sukhatme, Joseph J. Lim
Abstract
Imitation learning has traditionally been applied to learn a single task from demonstrations thereof. The requirement of structured and isolated demonstrations limits the scalability of imitation learning approaches as they are difficult to apply to real-world scenarios, where robots have to be able to execute a multitude of tasks. In this paper, we propose a multi-modal imitation learning framework that is able to segment and imitate skills from unlabelled and unstructured demonstrations by learning skill segmentation and imitation learning jointly. The extensive simulation results indicate that our method can efficiently separate the demonstrations into individual skills and learn to imitate them using a single multi-modal policy.
BibTeX
@inproceedings{NIPS2017_632cee94,
author = {Hausman, Karol and Chebotar, Yevgen and Schaal, Stefan and Sukhatme, Gaurav and Lim, Joseph J},
booktitle = {Advances in Neural Information Processing Systems},
editor = {I. Guyon and U. Von Luxburg and S. Bengio and H. Wallach and R. Fergus and S. Vishwanathan and R. Garnett},
pages = {},
publisher = {Curran Associates, Inc.},
title = {Multi-Modal Imitation Learning from Unstructured Demonstrations using Generative Adversarial Nets},
url = {https://proceedings.neurips.cc/paper_files/paper/2017/file/632cee946db83e7a52ce5e8d6f0fed35-Paper.pdf},
volume = {30},
year = {2017}
}