Wide and Deep Reinforcement Learning for Grid-based Action Games

Juan Montoya, Christian Borgelt

2019

Abstract

For the last decade Deep Reinforcement Learning has undergone exponential development; however, less has been done to integrate linear methods into it. Our Wide and Deep Reinforcement Learning framework provides a tool that combines linear and non-linear methods into one. For practical implementations, our framework can help integrate expert knowledge while improving the performance of existing Deep Reinforcement Learning algorithms. Our research aims to generate a simple practical framework to extend such algorithms. To test this framework we develop an extension of the popular Deep Q-Networks algorithm, which we name Wide Deep Q-Networks. We analyze its performance compared to Deep Q-Networks and Linear Agents, as well as human players. We apply our new algorithm to Berkley’s Pac-Man environment. Our algorithm considerably outperforms Deep Q-Networks’ both in terms of learning speed and ultimate performance showing its potential for boosting existing algorithms.

Download


Paper Citation


in Harvard Style

Montoya J. and Borgelt C. (2019). Wide and Deep Reinforcement Learning for Grid-based Action Games.In Proceedings of the 11th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART, ISBN 978-989-758-350-6, pages 50-59. DOI: 10.5220/0007313200500059


in Bibtex Style

@conference{icaart19,
author={Juan Montoya and Christian Borgelt},
title={Wide and Deep Reinforcement Learning for Grid-based Action Games},
booktitle={Proceedings of the 11th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,},
year={2019},
pages={50-59},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0007313200500059},
isbn={978-989-758-350-6},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 11th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,
TI - Wide and Deep Reinforcement Learning for Grid-based Action Games
SN - 978-989-758-350-6
AU - Montoya J.
AU - Borgelt C.
PY - 2019
SP - 50
EP - 59
DO - 10.5220/0007313200500059