Journal article icon

Journal article

Learning with stochastic guidance for robot navigation

Abstract:

Due to the sparse rewards and high degree of environmental variation, reinforcement learning approaches, such as deep deterministic policy gradient (DDPG), are plagued by issues of high variance when applied in complex real-world environments. We present a new framework for overcoming these issues by incorporating a stochastic switch, allowing an agent to choose between high- and low-variance policies. The stochastic switch can be jointly trained with the original DDPG in the same framework. ...

Expand abstract
Publication status:
Published
Peer review status:
Peer reviewed

Actions


Access Document


Files:
Publisher copy:
10.1109/TNNLS.2020.2977924

Authors


More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Computer Science
Role:
Author
ORCID:
0000-0001-8593-2277
More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Computer Science
Role:
Author
ORCID:
0000-0003-4558-2457
More by this author
Institution:
University of Oxford
Oxford college:
Hertford College
Role:
Author
ORCID:
0000-0003-0413-5327
Publisher:
Institute of Electrical and Electronics Engineers
Journal:
IEEE Transactions on Neural Networks and Learning Systems More from this journal
Volume:
32
Issue:
1
Pages:
166-176
Publication date:
2020-03-23
Acceptance date:
2020-02-23
DOI:
EISSN:
2162-2388
ISSN:
2162-237X

Terms of use


Views and Downloads






If you are the owner of this record, you can report an update to it here: Report update to this record

TO TOP