Effect of Viewing Directions on Deep Reinforcement Learning in 3D Virtual Environment Minecraft

Matsui, Taiju; Oyama, Satoshi; Kurihara, Masahito

Effect of Viewing Directions on Deep Reinforcement Learning in 3D Virtual Environment Minecraft

Matsui, Taiju; Oyama, Satoshi; Kurihara, Masahito

Lecture Notes in Artificial Intelligence (LNAI), 2018, 11224, 527-534

Permalink : https://hdl.handle.net/2115/72064

このアイテムのアクセス数:863件（2026-08-12 08:19 集計）

閲覧可能ファイル

ファイル	フォーマット	サイズ	閲覧回数	説明
rima2018	pdf	751 KB	814

論文情報

ファイル出力 EndNote Basic出力 Mendeley出力

アクセス権	open access
URI	https://hdl.handle.net/2115/72064
タイトル	Effect of Viewing Directions on Deep Reinforcement Learning in 3D Virtual Environment Minecraft
著者	Matsui, Taiju ; Oyama, Satoshi ; Kurihara, Masahito
著者名 Matsui, Taiju
e-Rad_Researcher 30346100 著者名 Oyama, Satoshi
e-Rad_Researcher 50133707 著者名 Kurihara, Masahito
言語	英語
発行日	2018
出版者	Springer, Cham
収録物名	Lecture Notes in Artificial Intelligence (LNAI)
巻(号)	11224
ページ	527-534
抄録	Deep reinforcement learning, which has recently attracted the interest of AI researchers, combines deep neural networks (DNNs) and reinforcement learning (RL). By approximating a function in RL with a DNN, it enables an agent to learn in a complex environment rep- resented by low-level features such as the pixels used in a 3D video game. However, learning from low-level features is sometimes problematic. For example, a small difference in input pixels results in completely different behaviors of an agent. In this study, as an example of such problems, we focus on the viewing directions of an agent in a 3D virtual environment (Minecraft) and analyze their effect on the efficiency of deep reinforce- ment learning.
会議記述	会議名 International Conference on Principles and Practice of Multi-Agent Systems 回次 21 開催地 Tokyo 開催国 Japan
資源タイプ	会議発表論文
出版タイプ	Accepted Manuscript
権利情報	The final publication is available at Springer via https://dx.doi.org/10.1007/978-3-030-03098-8_38
PISSN	0302-9743
EISSN	1611-3349
関連情報	ISBN 978-3-030-03098-8
関連情報 (isVersionOf)	出版社版DOI https://doi.org/10.1007/978-3-030-03098-8_38
関連情報 (isPartOf)	Title PRIMA 2018: Principles and Practice of Multi-Agent Systems. PRIMA 2018. Lecture Notes in Computer Science (LNCS), vol 11224. Springer, Cham, ISBN: 978-3-030-03097-1, ISBN: 978-3-030-03098-8 (eBook)