Video Game Agents with Human-like Behavior using the Deep Q-Network and Biological Constraints

Takahiro Morita, Hiroshi Hosobe

2023

Abstract

Video game agents that surpass humans always select the optimal behavior, which may make them look mechanical and uninteresting to human players and audience. Since score-oriented game agents have been almost achieved, a next goal should be to entertain human players and audience by realizing agents that reproduce human-like behavior. A previous method implemented such game agents by introducing biological constraints into Q-learning and A* search. In this paper, we propose video game agents with more entertaining and more practical human-like behavior by applying biological constraints into the deep Q-network (DQN). Especially, to reduce the problem of the conspicuous mechanical behavior found in the previous method, we propose an additional biological constraint “confusion”. We implemented our method in the video game “Infinite Mario Bros.” and conducted a subjective evaluation. The results indicated that the agents implemented with our method were rated more human-like than those implemented with the previous method.

Paper Citation

in Harvard Style

Morita T. and Hosobe H. (2023). Video Game Agents with Human-like Behavior using the Deep Q-Network and Biological Constraints. In Proceedings of the 15th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART, ISBN 978-989-758-623-1, pages 525-531. DOI: 10.5220/0011697500003393

in Bibtex Style

@conference{icaart23,
author={Takahiro Morita and Hiroshi Hosobe},
title={Video Game Agents with Human-like Behavior using the Deep Q-Network and Biological Constraints},
booktitle={Proceedings of the 15th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART,},
year={2023},
pages={525-531},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011697500003393},
isbn={978-989-758-623-1},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 15th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART,
TI - Video Game Agents with Human-like Behavior using the Deep Q-Network and Biological Constraints
SN - 978-989-758-623-1
AU - Morita T.
AU - Hosobe H.
PY - 2023
SP - 525
EP - 531
DO - 10.5220/0011697500003393