HUSCAP logo Hokkaido Univ. logo

Hokkaido University Collection of Scholarly and Academic Papers >
Graduate School of Information Science and Technology / Faculty of Information Science and Technology >
Peer-reviewed Journal Articles, etc >

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

Files in This Item:
prima2018.pdf751.85 kBPDFView/Open
Please use this identifier to cite or link to this item:http://hdl.handle.net/2115/72064

Title: Effect of Viewing Directions on Deep Reinforcement Learning in 3D Virtual Environment Minecraft
Authors: Matsui, Taiju Browse this author
Oyama, Satoshi Browse this author →KAKEN DB
Kurihara, Masahito Browse this author →KAKEN DB
Issue Date: 2018
Publisher: Springer, Cham
Citation: 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)
Journal Title: Lecture Notes in Artificial Intelligence (LNAI)
Volume: 11224
Start Page: 527
End Page: 534
Publisher DOI: 10.1007/978-3-030-03098-8_38
Abstract: 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.
Conference Name: International Conference on Principles and Practice of Multi-Agent Systems
Conference Sequence: 21
Conference Place: Tokyo
Rights: The final publication is available at Springer via https://dx.doi.org/10.1007/978-3-030-03098-8_38
Type: proceedings (author version)
URI: http://hdl.handle.net/2115/72064
Appears in Collections:情報科学院・情報科学研究院 (Graduate School of Information Science and Technology / Faculty of Information Science and Technology) > 雑誌発表論文等 (Peer-reviewed Journal Articles, etc)

Submitter: 小山 聡

Export metadata:

OAI-PMH ( junii2 , jpcoar )

MathJax is now OFF:


 

Feedback - Hokkaido University