Loading [MathJax]/extensions/tex2jax.js

A decision heuristic for Monte Carlo tree search doppelkopf agents

Publikation: Beitrag in Buch/Bericht/Sammelwerk/KonferenzbandAufsatz in KonferenzbandForschungPeer-Review

Autorschaft

Externe Organisationen

  • Otto-von-Guericke-Universität Magdeburg

Details

OriginalspracheEnglisch
Titel des Sammelwerks2017 IEEE Symposium Series on Computational Intelligence, SSCI 2017 - Proceedings
Herausgeber (Verlag)Institute of Electrical and Electronics Engineers Inc.
Seiten1-8
Seitenumfang8
ISBN (elektronisch)9781538627259
PublikationsstatusVeröffentlicht - 2 Feb. 2018
Extern publiziertJa
Veranstaltung2017 IEEE Symposium Series on Computational Intelligence, SSCI 2017 - Honolulu, USA / Vereinigte Staaten
Dauer: 27 Nov. 20171 Dez. 2017

Publikationsreihe

Name2017 IEEE Symposium Series on Computational Intelligence, SSCI 2017 - Proceedings
Band2018-January

Abstract

This work builds up on previous research by Sievers and Helmert, who developed an Monte Carlo Tree Search based doppelkopf agent. This four player card game features a larger state space than skat due to the unknown cards of the contestants. Additionally, players face the unique problem of not knowing their teammates at the start of the game. Figuring out the player parties is a key feature of this card game and demands differing play styles depending on the current knowledge of the game state. In this work we enhance the Monte Carlo Tree Search agent created by Sievers and Helmert with a decision heuristic. Our goal is to improve the quality of playouts, by suggesting high quality moves and predicting enemy moves based on a neural network classifier. This classifier is trained on an extensive history of expert player moves recorded during official doppelkopf tournaments. Different network architectures are discussed and evaluated based on their prediction accuracy. The best performing network was tested in a direct comparison with the previous Monte Carlo Tree Search agent by Sievers and Helmert. We show that high quality predictions increase the quality of playouts. Overall, our simulations show that adding the decision heuristic increased the strength of play under comparable computational effort.

ASJC Scopus Sachgebiete

Zitieren

A decision heuristic for Monte Carlo tree search doppelkopf agents. / Dockhorn, Alexander; Doell, Christoph; Hewelt, Matthias et al.
2017 IEEE Symposium Series on Computational Intelligence, SSCI 2017 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2018. S. 1-8 (2017 IEEE Symposium Series on Computational Intelligence, SSCI 2017 - Proceedings; Band 2018-January).

Publikation: Beitrag in Buch/Bericht/Sammelwerk/KonferenzbandAufsatz in KonferenzbandForschungPeer-Review

Dockhorn, A, Doell, C, Hewelt, M & Kruse, R 2018, A decision heuristic for Monte Carlo tree search doppelkopf agents. in 2017 IEEE Symposium Series on Computational Intelligence, SSCI 2017 - Proceedings. 2017 IEEE Symposium Series on Computational Intelligence, SSCI 2017 - Proceedings, Bd. 2018-January, Institute of Electrical and Electronics Engineers Inc., S. 1-8, 2017 IEEE Symposium Series on Computational Intelligence, SSCI 2017, Honolulu, USA / Vereinigte Staaten, 27 Nov. 2017. https://doi.org/10.1109/SSCI.2017.8285181
Dockhorn, A., Doell, C., Hewelt, M., & Kruse, R. (2018). A decision heuristic for Monte Carlo tree search doppelkopf agents. In 2017 IEEE Symposium Series on Computational Intelligence, SSCI 2017 - Proceedings (S. 1-8). (2017 IEEE Symposium Series on Computational Intelligence, SSCI 2017 - Proceedings; Band 2018-January). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/SSCI.2017.8285181
Dockhorn A, Doell C, Hewelt M, Kruse R. A decision heuristic for Monte Carlo tree search doppelkopf agents. in 2017 IEEE Symposium Series on Computational Intelligence, SSCI 2017 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2018. S. 1-8. (2017 IEEE Symposium Series on Computational Intelligence, SSCI 2017 - Proceedings). doi: 10.1109/SSCI.2017.8285181
Dockhorn, Alexander ; Doell, Christoph ; Hewelt, Matthias et al. / A decision heuristic for Monte Carlo tree search doppelkopf agents. 2017 IEEE Symposium Series on Computational Intelligence, SSCI 2017 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2018. S. 1-8 (2017 IEEE Symposium Series on Computational Intelligence, SSCI 2017 - Proceedings).
Download
@inproceedings{d600c2593c324cecbe3abb49cd4d8565,
title = "A decision heuristic for Monte Carlo tree search doppelkopf agents",
abstract = "This work builds up on previous research by Sievers and Helmert, who developed an Monte Carlo Tree Search based doppelkopf agent. This four player card game features a larger state space than skat due to the unknown cards of the contestants. Additionally, players face the unique problem of not knowing their teammates at the start of the game. Figuring out the player parties is a key feature of this card game and demands differing play styles depending on the current knowledge of the game state. In this work we enhance the Monte Carlo Tree Search agent created by Sievers and Helmert with a decision heuristic. Our goal is to improve the quality of playouts, by suggesting high quality moves and predicting enemy moves based on a neural network classifier. This classifier is trained on an extensive history of expert player moves recorded during official doppelkopf tournaments. Different network architectures are discussed and evaluated based on their prediction accuracy. The best performing network was tested in a direct comparison with the previous Monte Carlo Tree Search agent by Sievers and Helmert. We show that high quality predictions increase the quality of playouts. Overall, our simulations show that adding the decision heuristic increased the strength of play under comparable computational effort.",
author = "Alexander Dockhorn and Christoph Doell and Matthias Hewelt and Rudolf Kruse",
note = "Publisher Copyright: {\textcopyright} 2017 IEEE.; 2017 IEEE Symposium Series on Computational Intelligence, SSCI 2017 ; Conference date: 27-11-2017 Through 01-12-2017",
year = "2018",
month = feb,
day = "2",
doi = "10.1109/SSCI.2017.8285181",
language = "English",
series = "2017 IEEE Symposium Series on Computational Intelligence, SSCI 2017 - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "1--8",
booktitle = "2017 IEEE Symposium Series on Computational Intelligence, SSCI 2017 - Proceedings",
address = "United States",

}

Download

TY - GEN

T1 - A decision heuristic for Monte Carlo tree search doppelkopf agents

AU - Dockhorn, Alexander

AU - Doell, Christoph

AU - Hewelt, Matthias

AU - Kruse, Rudolf

N1 - Publisher Copyright: © 2017 IEEE.

PY - 2018/2/2

Y1 - 2018/2/2

N2 - This work builds up on previous research by Sievers and Helmert, who developed an Monte Carlo Tree Search based doppelkopf agent. This four player card game features a larger state space than skat due to the unknown cards of the contestants. Additionally, players face the unique problem of not knowing their teammates at the start of the game. Figuring out the player parties is a key feature of this card game and demands differing play styles depending on the current knowledge of the game state. In this work we enhance the Monte Carlo Tree Search agent created by Sievers and Helmert with a decision heuristic. Our goal is to improve the quality of playouts, by suggesting high quality moves and predicting enemy moves based on a neural network classifier. This classifier is trained on an extensive history of expert player moves recorded during official doppelkopf tournaments. Different network architectures are discussed and evaluated based on their prediction accuracy. The best performing network was tested in a direct comparison with the previous Monte Carlo Tree Search agent by Sievers and Helmert. We show that high quality predictions increase the quality of playouts. Overall, our simulations show that adding the decision heuristic increased the strength of play under comparable computational effort.

AB - This work builds up on previous research by Sievers and Helmert, who developed an Monte Carlo Tree Search based doppelkopf agent. This four player card game features a larger state space than skat due to the unknown cards of the contestants. Additionally, players face the unique problem of not knowing their teammates at the start of the game. Figuring out the player parties is a key feature of this card game and demands differing play styles depending on the current knowledge of the game state. In this work we enhance the Monte Carlo Tree Search agent created by Sievers and Helmert with a decision heuristic. Our goal is to improve the quality of playouts, by suggesting high quality moves and predicting enemy moves based on a neural network classifier. This classifier is trained on an extensive history of expert player moves recorded during official doppelkopf tournaments. Different network architectures are discussed and evaluated based on their prediction accuracy. The best performing network was tested in a direct comparison with the previous Monte Carlo Tree Search agent by Sievers and Helmert. We show that high quality predictions increase the quality of playouts. Overall, our simulations show that adding the decision heuristic increased the strength of play under comparable computational effort.

UR - http://www.scopus.com/inward/record.url?scp=85046116412&partnerID=8YFLogxK

U2 - 10.1109/SSCI.2017.8285181

DO - 10.1109/SSCI.2017.8285181

M3 - Conference contribution

T3 - 2017 IEEE Symposium Series on Computational Intelligence, SSCI 2017 - Proceedings

SP - 1

EP - 8

BT - 2017 IEEE Symposium Series on Computational Intelligence, SSCI 2017 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2017 IEEE Symposium Series on Computational Intelligence, SSCI 2017

Y2 - 27 November 2017 through 1 December 2017

ER -

Von denselben Autoren