Behavioral Repertoire via Generative Adversarial Policy Networks

Marija Jegorova, Stephane Doncieux, Timothy Hospedales

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Learning algorithms are enabling robots to solve increasingly challenging real-world tasks. These approaches often rely on demonstrations and reproduce the behavior shown. Unexpected changes in the environment may require using different behaviors to achieve the same effect, for instance to reach and grasp an object in changing clutter. An emerging paradigm addressing this robustness issue is to learn a diverse set of successful behaviors for a given task, from which a robot can select the most suitable policy when faced with a new environment. In this paper, we explore a novel realization of this vision by learning a generative model over policies. Rather than learning a single policy, or a small fixed repertoire, our generative model for policies compactly encodes an unbounded number of policies and allows novel controller variants to be sampled. Leveraging our generative policy network, a robot can sample novel behaviors until it finds one that works for a new environment. We demonstrate this idea with an application of robust ball-throwing in the presence of obstacles. We show that this approach achieves a greater diversity of behaviors than an existing evolutionary approach, while maintaining good efficacy of sampled behaviors, allowing a Baxter robot to hit targets more often when ball throwing in the presence of obstacles.
Original languageEnglish
Title of host publication 2019 Joint IEEE 9th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob)
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Pages320-326
Number of pages7
ISBN (Electronic)978-1-5386-8128-2
ISBN (Print)978-1-5386-8129-9
DOIs
Publication statusPublished - 30 Sep 2019
Event9th Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics - Oslo, Norway
Duration: 19 Aug 201922 Aug 2019
https://icdl-epirob2019.org/

Publication series

Name
PublisherInstitute of Electrical and Electronics Engineers
ISSN (Print)2161-9484
ISSN (Electronic)2161-9484

Conference

Conference9th Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics
Abbreviated titleICDL-EPIROB 2019
CountryNorway
CityOslo
Period19/08/1922/08/19
Internet address

Fingerprint Dive into the research topics of 'Behavioral Repertoire via Generative Adversarial Policy Networks'. Together they form a unique fingerprint.

Cite this