Self-supervised Learning for Predicting Invisible Enemy Information in StarCraft II

Insung Baek; Jinsoo Bae; Keewon Jeong; Young Jae Lee; Uk Jo; Jaehoon Kim; Seoung Bum Kim

doi:10.1007/978-3-031-16072-1_13

Self-supervised Learning for Predicting Invisible Enemy Information in StarCraft II

Insung Baek, Jinsoo Bae, Keewon Jeong, Young Jae Lee, Uk Jo, Jaehoon Kim, Seoung Bum Kim

School of Industrial Management Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

In real-time strategy games such as StarCraft II, players gather resources, make buildings, produce various units, and create strategies to win the game. Especially, accurately predicting enemy information is essential to victory in StarCraft II because the enemy situation is obscured by the fog of war. However, it is challenging to predict the enemy information because the situation changes over time, and various strategies are used. Also, previous studies for predicting invisible enemy information in StarCraft do not use self-supervised learning, which is extracting effective feature spaces. In this study, we propose a deep learning model combined with a contrastive self-supervised learning to predict invisible enemy information to improve the model performance. The effectiveness of the proposed method is demonstrated by quantitatively and qualitatively.

Original language	English
Title of host publication	Intelligent Systems and Applications - Proceedings of the 2022 Intelligent Systems Conference IntelliSys Volume 1
Editors	Kohei Arai
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	167-172
Number of pages	6
ISBN (Print)	9783031160714
DOIs	https://doi.org/10.1007/978-3-031-16072-1_13
Publication status	Published - 2023
Event	Intelligent Systems Conference, IntelliSys 2022 - Virtual, Online Duration: 2022 Sept 1 → 2022 Sept 2

Publication series

Name	Lecture Notes in Networks and Systems
Volume	542 LNNS
ISSN (Print)	2367-3370
ISSN (Electronic)	2367-3389

Conference

Conference	Intelligent Systems Conference, IntelliSys 2022
City	Virtual, Online
Period	22/9/1 → 22/9/2

Bibliographical note

Publisher Copyright:
© 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Keywords

Contrastive learning
Deep learning model
Self-supervised learning
StarCraft II

ASJC Scopus subject areas

Control and Systems Engineering
Signal Processing
Computer Networks and Communications

Access to Document

10.1007/978-3-031-16072-1_13

Cite this

Baek, I., Bae, J., Jeong, K., Lee, Y. J., Jo, U., Kim, J., & Kim, S. B. (2023). Self-supervised Learning for Predicting Invisible Enemy Information in StarCraft II. In K. Arai (Ed.), Intelligent Systems and Applications - Proceedings of the 2022 Intelligent Systems Conference IntelliSys Volume 1 (pp. 167-172). (Lecture Notes in Networks and Systems; Vol. 542 LNNS). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-3-031-16072-1_13

Self-supervised Learning for Predicting Invisible Enemy Information in StarCraft II. / Baek, Insung; Bae, Jinsoo; Jeong, Keewon et al.
Intelligent Systems and Applications - Proceedings of the 2022 Intelligent Systems Conference IntelliSys Volume 1. ed. / Kohei Arai. Springer Science and Business Media Deutschland GmbH, 2023. p. 167-172 (Lecture Notes in Networks and Systems; Vol. 542 LNNS).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Baek, I, Bae, J, Jeong, K, Lee, YJ, Jo, U, Kim, J & Kim, SB 2023, Self-supervised Learning for Predicting Invisible Enemy Information in StarCraft II. in K Arai (ed.), Intelligent Systems and Applications - Proceedings of the 2022 Intelligent Systems Conference IntelliSys Volume 1. Lecture Notes in Networks and Systems, vol. 542 LNNS, Springer Science and Business Media Deutschland GmbH, pp. 167-172, Intelligent Systems Conference, IntelliSys 2022, Virtual, Online, 22/9/1. https://doi.org/10.1007/978-3-031-16072-1_13

Baek I, Bae J, Jeong K, Lee YJ, Jo U, Kim J et al. Self-supervised Learning for Predicting Invisible Enemy Information in StarCraft II. In Arai K, editor, Intelligent Systems and Applications - Proceedings of the 2022 Intelligent Systems Conference IntelliSys Volume 1. Springer Science and Business Media Deutschland GmbH. 2023. p. 167-172. (Lecture Notes in Networks and Systems). doi: 10.1007/978-3-031-16072-1_13

Baek, Insung ; Bae, Jinsoo ; Jeong, Keewon et al. / Self-supervised Learning for Predicting Invisible Enemy Information in StarCraft II. Intelligent Systems and Applications - Proceedings of the 2022 Intelligent Systems Conference IntelliSys Volume 1. editor / Kohei Arai. Springer Science and Business Media Deutschland GmbH, 2023. pp. 167-172 (Lecture Notes in Networks and Systems).

@inproceedings{c162e0fd39724ca5a0212badb27e5380,

title = "Self-supervised Learning for Predicting Invisible Enemy Information in StarCraft II",

abstract = "In real-time strategy games such as StarCraft II, players gather resources, make buildings, produce various units, and create strategies to win the game. Especially, accurately predicting enemy information is essential to victory in StarCraft II because the enemy situation is obscured by the fog of war. However, it is challenging to predict the enemy information because the situation changes over time, and various strategies are used. Also, previous studies for predicting invisible enemy information in StarCraft do not use self-supervised learning, which is extracting effective feature spaces. In this study, we propose a deep learning model combined with a contrastive self-supervised learning to predict invisible enemy information to improve the model performance. The effectiveness of the proposed method is demonstrated by quantitatively and qualitatively.",

keywords = "Contrastive learning, Deep learning model, Self-supervised learning, StarCraft II",

author = "Insung Baek and Jinsoo Bae and Keewon Jeong and Lee, {Young Jae} and Uk Jo and Jaehoon Kim and Kim, {Seoung Bum}",

note = "Publisher Copyright: {\textcopyright} 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.; Intelligent Systems Conference, IntelliSys 2022 ; Conference date: 01-09-2022 Through 02-09-2022",

year = "2023",

doi = "10.1007/978-3-031-16072-1_13",

language = "English",

isbn = "9783031160714",

series = "Lecture Notes in Networks and Systems",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "167--172",

editor = "Kohei Arai",

booktitle = "Intelligent Systems and Applications - Proceedings of the 2022 Intelligent Systems Conference IntelliSys Volume 1",

address = "Germany",

}

TY - GEN

T1 - Self-supervised Learning for Predicting Invisible Enemy Information in StarCraft II

AU - Baek, Insung

AU - Bae, Jinsoo

AU - Jeong, Keewon

AU - Lee, Young Jae

AU - Jo, Uk

AU - Kim, Jaehoon

AU - Kim, Seoung Bum

PY - 2023

Y1 - 2023

N2 - In real-time strategy games such as StarCraft II, players gather resources, make buildings, produce various units, and create strategies to win the game. Especially, accurately predicting enemy information is essential to victory in StarCraft II because the enemy situation is obscured by the fog of war. However, it is challenging to predict the enemy information because the situation changes over time, and various strategies are used. Also, previous studies for predicting invisible enemy information in StarCraft do not use self-supervised learning, which is extracting effective feature spaces. In this study, we propose a deep learning model combined with a contrastive self-supervised learning to predict invisible enemy information to improve the model performance. The effectiveness of the proposed method is demonstrated by quantitatively and qualitatively.

AB - In real-time strategy games such as StarCraft II, players gather resources, make buildings, produce various units, and create strategies to win the game. Especially, accurately predicting enemy information is essential to victory in StarCraft II because the enemy situation is obscured by the fog of war. However, it is challenging to predict the enemy information because the situation changes over time, and various strategies are used. Also, previous studies for predicting invisible enemy information in StarCraft do not use self-supervised learning, which is extracting effective feature spaces. In this study, we propose a deep learning model combined with a contrastive self-supervised learning to predict invisible enemy information to improve the model performance. The effectiveness of the proposed method is demonstrated by quantitatively and qualitatively.

KW - Contrastive learning

KW - Deep learning model

KW - Self-supervised learning

KW - StarCraft II

UR - http://www.scopus.com/inward/record.url?scp=85138000145&partnerID=8YFLogxK

U2 - 10.1007/978-3-031-16072-1_13

DO - 10.1007/978-3-031-16072-1_13

M3 - Conference contribution

AN - SCOPUS:85138000145

SN - 9783031160714

T3 - Lecture Notes in Networks and Systems

SP - 167

EP - 172

BT - Intelligent Systems and Applications - Proceedings of the 2022 Intelligent Systems Conference IntelliSys Volume 1

A2 - Arai, Kohei

PB - Springer Science and Business Media Deutschland GmbH

T2 - Intelligent Systems Conference, IntelliSys 2022

Y2 - 1 September 2022 through 2 September 2022

ER -

Self-supervised Learning for Predicting Invisible Enemy Information in StarCraft II

Abstract

Publication series

Conference

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this