Investigating MCTS modifications in general video game playing

Frederik Frydenberg; Kasper R. Andersen; Sebastian Risi; Julian Togelius

doi:10.1109/CIG.2015.7317937

Investigating MCTS modifications in general video game playing

Frederik Frydenberg, Kasper R. Andersen, Sebastian Risi, Julian Togelius

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

Abstract

While Monte Carlo tree search (MCTS) methods have shown promise in a variety of different board games, more complex video games still present significant challenges. Recently, several modifications to the core MCTS algorithm have been proposed with the hope to increase its effectiveness on arcade-style video games. This paper investigates of how well these modifications perform in general video game playing using the general video game AI (GVG-AI) framework and introduces a new MCTS modification called UCT reverse penalty that penalizes the MCTS controller for exploring recently visited children. The results of our experiments show that a combination of two MCTS modifications can improve the performance of the vanilla MCTS controller, but the effectiveness of the modifications highly depends on the particular game being played.

Original language	English (US)
Title of host publication	2015 IEEE Conference on Computational Intelligence and Games, CIG 2015 - Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	107-113
Number of pages	7
ISBN (Electronic)	9781479986217
DOIs	https://doi.org/10.1109/CIG.2015.7317937
State	Published - Nov 4 2015
Event	2015 IEEE Conference on Computational Intelligence and Games, CIG 2015 - Tainan, Taiwan, Province of China Duration: Aug 31 2015 → Sep 2 2015

Publication series

Name	2015 IEEE Conference on Computational Intelligence and Games, CIG 2015 - Proceedings

Other

Other	2015 IEEE Conference on Computational Intelligence and Games, CIG 2015
Country/Territory	Taiwan, Province of China
City	Tainan
Period	8/31/15 → 9/2/15

ASJC Scopus subject areas

Artificial Intelligence
Computer Science Applications
Information Systems

Access to Document

10.1109/CIG.2015.7317937

Cite this

Frydenberg, F., Andersen, K. R., Risi, S., & Togelius, J. (2015). Investigating MCTS modifications in general video game playing. In 2015 IEEE Conference on Computational Intelligence and Games, CIG 2015 - Proceedings (pp. 107-113). Article 7317937 (2015 IEEE Conference on Computational Intelligence and Games, CIG 2015 - Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/CIG.2015.7317937

Investigating MCTS modifications in general video game playing. / Frydenberg, Frederik; Andersen, Kasper R.; Risi, Sebastian et al.
2015 IEEE Conference on Computational Intelligence and Games, CIG 2015 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2015. p. 107-113 7317937 (2015 IEEE Conference on Computational Intelligence and Games, CIG 2015 - Proceedings).

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

Frydenberg, F, Andersen, KR, Risi, S & Togelius, J 2015, Investigating MCTS modifications in general video game playing. in 2015 IEEE Conference on Computational Intelligence and Games, CIG 2015 - Proceedings., 7317937, 2015 IEEE Conference on Computational Intelligence and Games, CIG 2015 - Proceedings, Institute of Electrical and Electronics Engineers Inc., pp. 107-113, 2015 IEEE Conference on Computational Intelligence and Games, CIG 2015, Tainan, Taiwan, Province of China, 8/31/15. https://doi.org/10.1109/CIG.2015.7317937

Frydenberg F, Andersen KR, Risi S, Togelius J. Investigating MCTS modifications in general video game playing. In 2015 IEEE Conference on Computational Intelligence and Games, CIG 2015 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2015. p. 107-113. 7317937. (2015 IEEE Conference on Computational Intelligence and Games, CIG 2015 - Proceedings). doi: 10.1109/CIG.2015.7317937

Frydenberg, Frederik ; Andersen, Kasper R. ; Risi, Sebastian et al. / Investigating MCTS modifications in general video game playing. 2015 IEEE Conference on Computational Intelligence and Games, CIG 2015 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2015. pp. 107-113 (2015 IEEE Conference on Computational Intelligence and Games, CIG 2015 - Proceedings).

@inproceedings{50015b70d57c485385124ebd2e4de0b1,

title = "Investigating MCTS modifications in general video game playing",

abstract = "While Monte Carlo tree search (MCTS) methods have shown promise in a variety of different board games, more complex video games still present significant challenges. Recently, several modifications to the core MCTS algorithm have been proposed with the hope to increase its effectiveness on arcade-style video games. This paper investigates of how well these modifications perform in general video game playing using the general video game AI (GVG-AI) framework and introduces a new MCTS modification called UCT reverse penalty that penalizes the MCTS controller for exploring recently visited children. The results of our experiments show that a combination of two MCTS modifications can improve the performance of the vanilla MCTS controller, but the effectiveness of the modifications highly depends on the particular game being played.",

author = "Frederik Frydenberg and Andersen, {Kasper R.} and Sebastian Risi and Julian Togelius",

note = "Publisher Copyright: {\textcopyright} 2015 IEEE.; 2015 IEEE Conference on Computational Intelligence and Games, CIG 2015 ; Conference date: 31-08-2015 Through 02-09-2015",

year = "2015",

month = nov,

day = "4",

doi = "10.1109/CIG.2015.7317937",

language = "English (US)",

series = "2015 IEEE Conference on Computational Intelligence and Games, CIG 2015 - Proceedings",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "107--113",

booktitle = "2015 IEEE Conference on Computational Intelligence and Games, CIG 2015 - Proceedings",

}

TY - GEN

T1 - Investigating MCTS modifications in general video game playing

AU - Frydenberg, Frederik

AU - Andersen, Kasper R.

AU - Risi, Sebastian

AU - Togelius, Julian

PY - 2015/11/4

Y1 - 2015/11/4

N2 - While Monte Carlo tree search (MCTS) methods have shown promise in a variety of different board games, more complex video games still present significant challenges. Recently, several modifications to the core MCTS algorithm have been proposed with the hope to increase its effectiveness on arcade-style video games. This paper investigates of how well these modifications perform in general video game playing using the general video game AI (GVG-AI) framework and introduces a new MCTS modification called UCT reverse penalty that penalizes the MCTS controller for exploring recently visited children. The results of our experiments show that a combination of two MCTS modifications can improve the performance of the vanilla MCTS controller, but the effectiveness of the modifications highly depends on the particular game being played.

AB - While Monte Carlo tree search (MCTS) methods have shown promise in a variety of different board games, more complex video games still present significant challenges. Recently, several modifications to the core MCTS algorithm have been proposed with the hope to increase its effectiveness on arcade-style video games. This paper investigates of how well these modifications perform in general video game playing using the general video game AI (GVG-AI) framework and introduces a new MCTS modification called UCT reverse penalty that penalizes the MCTS controller for exploring recently visited children. The results of our experiments show that a combination of two MCTS modifications can improve the performance of the vanilla MCTS controller, but the effectiveness of the modifications highly depends on the particular game being played.

UR - http://www.scopus.com/inward/record.url?scp=84964507597&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84964507597&partnerID=8YFLogxK

U2 - 10.1109/CIG.2015.7317937

DO - 10.1109/CIG.2015.7317937

M3 - Conference contribution

AN - SCOPUS:84964507597

T3 - 2015 IEEE Conference on Computational Intelligence and Games, CIG 2015 - Proceedings

SP - 107

EP - 113

BT - 2015 IEEE Conference on Computational Intelligence and Games, CIG 2015 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2015 IEEE Conference on Computational Intelligence and Games, CIG 2015

Y2 - 31 August 2015 through 2 September 2015

ER -

Investigating MCTS modifications in general video game playing

Abstract

Publication series

Other

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this