ITU

Investigating MCTS Modifications in General Video Game Playing

Research output: Conference Article in Proceeding or Book/Report chapterArticle in proceedingsResearchpeer-review

Standard

Investigating MCTS Modifications in General Video Game Playing. / Frydenberg, Frederik; Andersen, Kasper; Risi, Sebastian; Togelius, Julian.

Proceedings of the 2015 IEEE Conference on Computational Intelligence and Games. IEEE Computer Society Press, 2015. p. 107-113.

Research output: Conference Article in Proceeding or Book/Report chapterArticle in proceedingsResearchpeer-review

Harvard

Frydenberg, F, Andersen, K, Risi, S & Togelius, J 2015, Investigating MCTS Modifications in General Video Game Playing. in Proceedings of the 2015 IEEE Conference on Computational Intelligence and Games. IEEE Computer Society Press, pp. 107-113. https://doi.org/10.1109/CIG.2015.7317937

APA

Frydenberg, F., Andersen, K., Risi, S., & Togelius, J. (2015). Investigating MCTS Modifications in General Video Game Playing. In Proceedings of the 2015 IEEE Conference on Computational Intelligence and Games (pp. 107-113). IEEE Computer Society Press. https://doi.org/10.1109/CIG.2015.7317937

Vancouver

Frydenberg F, Andersen K, Risi S, Togelius J. Investigating MCTS Modifications in General Video Game Playing. In Proceedings of the 2015 IEEE Conference on Computational Intelligence and Games. IEEE Computer Society Press. 2015. p. 107-113 https://doi.org/10.1109/CIG.2015.7317937

Author

Frydenberg, Frederik ; Andersen, Kasper ; Risi, Sebastian ; Togelius, Julian. / Investigating MCTS Modifications in General Video Game Playing. Proceedings of the 2015 IEEE Conference on Computational Intelligence and Games. IEEE Computer Society Press, 2015. pp. 107-113

Bibtex

@inproceedings{baa5959c04d14d1cb6ea6584bf8f783b,
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 Kasper Andersen and Sebastian Risi and Julian Togelius",
year = "2015",
doi = "10.1109/CIG.2015.7317937",
language = "English",
isbn = "978-1-4799-8621-7",
pages = "107--113",
booktitle = "Proceedings of the 2015 IEEE Conference on Computational Intelligence and Games",
publisher = "IEEE Computer Society Press",
address = "United States",

}

RIS

TY - GEN

T1 - Investigating MCTS Modifications in General Video Game Playing

AU - Frydenberg, Frederik

AU - Andersen, Kasper

AU - Risi, Sebastian

AU - Togelius, Julian

PY - 2015

Y1 - 2015

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.

U2 - 10.1109/CIG.2015.7317937

DO - 10.1109/CIG.2015.7317937

M3 - Article in proceedings

SN - 978-1-4799-8621-7

SP - 107

EP - 113

BT - Proceedings of the 2015 IEEE Conference on Computational Intelligence and Games

PB - IEEE Computer Society Press

ER -

ID: 80608186