Scalable Robust Learning from Demonstration with Leveraged Deep Neural Networks
- Authors
- Choi, Sungjoon; Lee, Kyungjae; Oh, Songhwai
- Issue Date
- Sep-2017
- Publisher
- IEEE
- Citation
- 2017 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS), pp 3926 - 3931
- Pages
- 6
- Journal Title
- 2017 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS)
- Start Page
- 3926
- End Page
- 3931
- URI
- https://scholarworks.bwise.kr/cau/handle/2019.sw.cau/59375
- DOI
- 10.1109/IROS.2017.8206244
- ISSN
- 2153-0858
- Abstract
- In this paper, we propose a novel algorithm for learning from demonstration, which can learn a policy function robustly from a large number of demonstrations with mixed qualities. While most of the existing approaches assume that demonstrations are collected from skillful experts, the proposed method alleviates such restrictions by estimating the proficiency level of each demonstration using the proposed leverage optimization. Furthermore, a novel leveraged cost function is proposed to represent a policy function using deep neural networks by reformulating the objective function of leveraged Gaussian process regression using the representer theorem. The proposed method is successfully applied to autonomous track driving tasks, where a large number of demonstrations with mixed qualities are given as training data without labels.
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - College of Software > Department of Artificial Intelligence > 1. Journal Articles
![qrcode](https://api.qrserver.com/v1/create-qr-code/?size=55x55&data=https://scholarworks.bwise.kr/cau/handle/2019.sw.cau/59375)
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.