MODEL-FREE LEARNING FROM DEMONSTRATION

Erik A. Billing, Thomas Hellström, Lars-Erik Janlert

2010

Abstract

A novel robot learning algorithm called Predictive Sequence Learning (PSL) is presented and evaluated. PSL is a model-free prediction algorithm inspired by the dynamic temporal difference algorithm S-Learning. While S-Learning has previously been applied as a reinforcement learning algorithm for robots, PSL is here applied to a Learning from Demonstration problem. The proposed algorithm is evaluated on four tasks using a Khepera II robot. PSL builds a model from demonstrated data which is used to repeat the demonstrated behavior. After training, PSL can control the robot by continually predicting the next action, based on the sequence of passed sensor and motor events. PSL was able to successfully learn and repeat the first three (elementary) tasks, but it was unable to successfully repeat the fourth (composed) behavior. The results indicate that PSL is suitable for learning problems up to a certain complexity, while higher level coordination is required for learning more complex behaviors.

Paper Citation

in Harvard Style

A. Billing E., Hellström T. and Janlert L. (2010). MODEL-FREE LEARNING FROM DEMONSTRATION . In Proceedings of the 2nd International Conference on Agents and Artificial Intelligence - Volume 2: ICAART, ISBN 978-989-674-022-1, pages 62-71. DOI: 10.5220/0002729500620071

in Bibtex Style

@conference{icaart10,
author={Erik A. Billing and Thomas Hellström and Lars-Erik Janlert},
title={MODEL-FREE LEARNING FROM DEMONSTRATION},
booktitle={Proceedings of the 2nd International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,},
year={2010},
pages={62-71},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0002729500620071},
isbn={978-989-674-022-1},
}

in EndNote Style

TY - CONF
JO - Proceedings of the 2nd International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,
TI - MODEL-FREE LEARNING FROM DEMONSTRATION
SN - 978-989-674-022-1
AU - A. Billing E.
AU - Hellström T.
AU - Janlert L.
PY - 2010
SP - 62
EP - 71
DO - 10.5220/0002729500620071