CoachGAN: Fast Adversarial Transfer Learning between Differently Shaped Entities

Mehdi Mounsif, Sébastien Lengagne, Benoit Thuilot, Lounis Adouane

2020

Abstract

In the last decade, robots have been taking an increasingly important place in our societies, and shall the current trend keep the same dynamic,their presence and activities will likely become ubiquitous. As robots will certainly be produced by various industrial actors, it is reasonable to assume that a very diverse robot population will be used by mankind for a broad panel of tasks. As such, it appears probable that robots with a distinct morphology will be required to perform the same task. As an important part of these tasks requires learning-based control and given the millions of interactions steps needed by these approaches to create a single agent, it appears highly desirable to be able to transfer skills from one agent to another despite a potentially different kinematic structure. Correspondingly, this paper introduces a new method, CoachGAN, based on an adversarial framework that allows fast transfer of capacities between a teacher and a student agent. The CoachGAN approach aims at embedding the teacher’s way of solving the task within a critic network. Enhanced with the intermediate state variable (ISV) that translates a student state in its teacher equivalent, the critic is then able to guide the student policy in a supervised way in a fraction of the initial training time and without the student having any interaction with the target domain. To demonstrate the flexibility of this approach, CoachGAN is evaluated over a custom tennis task, using various ways to define the intermediate state variables.

Download


Paper Citation


in Harvard Style

Mounsif M., Lengagne S., Thuilot B. and Adouane L. (2020). CoachGAN: Fast Adversarial Transfer Learning between Differently Shaped Entities.In Proceedings of the 17th International Conference on Informatics in Control, Automation and Robotics - Volume 1: ICINCO, ISBN 978-989-758-442-8, pages 89-96. DOI: 10.5220/0009972200890096


in Bibtex Style

@conference{icinco20,
author={Mehdi Mounsif and Sébastien Lengagne and Benoit Thuilot and Lounis Adouane},
title={CoachGAN: Fast Adversarial Transfer Learning between Differently Shaped Entities},
booktitle={Proceedings of the 17th International Conference on Informatics in Control, Automation and Robotics - Volume 1: ICINCO,},
year={2020},
pages={89-96},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0009972200890096},
isbn={978-989-758-442-8},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 17th International Conference on Informatics in Control, Automation and Robotics - Volume 1: ICINCO,
TI - CoachGAN: Fast Adversarial Transfer Learning between Differently Shaped Entities
SN - 978-989-758-442-8
AU - Mounsif M.
AU - Lengagne S.
AU - Thuilot B.
AU - Adouane L.
PY - 2020
SP - 89
EP - 96
DO - 10.5220/0009972200890096