Training an Agent to Find and Reach an Object in Different Environments using Visual Reinforcement Learning and Transfer Learning

Evelyn Batista, Wouter Caarls, Leonardo Forero, Marco Pacheco

Abstract

This paper consists of a study on deep learning by visual reinforcement for autonomous robots through transfer learning techniques. The simulation environments tested in this study are realistic environments where the challenge of the robot was to learn and transfer knowledge in different contexts, taking advantage of the experience of previous environments in future environments. This type of approach, besides adding knowledge to autonomous robots, reduces the number of training epochs for the algorithm even in complex environments, justifying the use of transfer learning techniques.

Download


Paper Citation


in Harvard Style

Batista E., Caarls W., Forero L. and Pacheco M. (2021). Training an Agent to Find and Reach an Object in Different Environments using Visual Reinforcement Learning and Transfer Learning.In Proceedings of the 13th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART, ISBN 978-989-758-484-8, pages 732-741. DOI: 10.5220/0010236807320741


in Bibtex Style

@conference{icaart21,
author={Evelyn Batista and Wouter Caarls and Leonardo Forero and Marco Pacheco},
title={Training an Agent to Find and Reach an Object in Different Environments using Visual Reinforcement Learning and Transfer Learning},
booktitle={Proceedings of the 13th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,},
year={2021},
pages={732-741},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010236807320741},
isbn={978-989-758-484-8},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 13th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,
TI - Training an Agent to Find and Reach an Object in Different Environments using Visual Reinforcement Learning and Transfer Learning
SN - 978-989-758-484-8
AU - Batista E.
AU - Caarls W.
AU - Forero L.
AU - Pacheco M.
PY - 2021
SP - 732
EP - 741
DO - 10.5220/0010236807320741