An automated technique for drafting territories in the board game risk

Richard Gibson, Neesha Desai, Richard Zhao

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

In the standard rules of the board game Risk, players take turns selecting or "drafting" the 42 territories on the board until all territories are owned. We present a technique for drafting territories in Risk that combines theMonte Carlo tree search algorithm UCT with an automated evaluation function. Created through supervised machine learning, this function scores outcomes of drafts in order to shorten the length of a UCT simulation. Using this approach, we augment an existing bot for the computer game Lux Delux, a clone of Risk. Our drafting technique is shown to greatly improve performance against the strongest opponents supplied with Lux Delux. The evidence provided indicates that territory drafting is important to overall success in Risk.

Original languageEnglish (US)
Title of host publicationProceedings of the 6th AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, AIIDE 2010
Pages15-20
Number of pages6
StatePublished - Dec 1 2010
Event6th AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, AIIDE 2010 - Stanford, CA, United States
Duration: Oct 11 2010Oct 13 2010

Publication series

NameProceedings of the 6th AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, AIIDE 2010

Other

Other6th AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, AIIDE 2010
CountryUnited States
CityStanford, CA
Period10/11/1010/13/10

Fingerprint

Computer games
Function evaluation
Trees (mathematics)
Learning systems
Board Games
Simulation
Clone
Opponents
Evaluation
Draft
Players
Computer Games
Machine Learning
Length

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence
  • Visual Arts and Performing Arts

Cite this

Gibson, R., Desai, N., & Zhao, R. (2010). An automated technique for drafting territories in the board game risk. In Proceedings of the 6th AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, AIIDE 2010 (pp. 15-20). (Proceedings of the 6th AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, AIIDE 2010).
Gibson, Richard ; Desai, Neesha ; Zhao, Richard. / An automated technique for drafting territories in the board game risk. Proceedings of the 6th AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, AIIDE 2010. 2010. pp. 15-20 (Proceedings of the 6th AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, AIIDE 2010).
@inproceedings{0e1765595dbc4ac3a0692cf099a6bbf8,
title = "An automated technique for drafting territories in the board game risk",
abstract = "In the standard rules of the board game Risk, players take turns selecting or {"}drafting{"} the 42 territories on the board until all territories are owned. We present a technique for drafting territories in Risk that combines theMonte Carlo tree search algorithm UCT with an automated evaluation function. Created through supervised machine learning, this function scores outcomes of drafts in order to shorten the length of a UCT simulation. Using this approach, we augment an existing bot for the computer game Lux Delux, a clone of Risk. Our drafting technique is shown to greatly improve performance against the strongest opponents supplied with Lux Delux. The evidence provided indicates that territory drafting is important to overall success in Risk.",
author = "Richard Gibson and Neesha Desai and Richard Zhao",
year = "2010",
month = "12",
day = "1",
language = "English (US)",
isbn = "9781577354789",
series = "Proceedings of the 6th AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, AIIDE 2010",
pages = "15--20",
booktitle = "Proceedings of the 6th AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, AIIDE 2010",

}

Gibson, R, Desai, N & Zhao, R 2010, An automated technique for drafting territories in the board game risk. in Proceedings of the 6th AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, AIIDE 2010. Proceedings of the 6th AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, AIIDE 2010, pp. 15-20, 6th AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, AIIDE 2010, Stanford, CA, United States, 10/11/10.

An automated technique for drafting territories in the board game risk. / Gibson, Richard; Desai, Neesha; Zhao, Richard.

Proceedings of the 6th AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, AIIDE 2010. 2010. p. 15-20 (Proceedings of the 6th AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, AIIDE 2010).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - An automated technique for drafting territories in the board game risk

AU - Gibson, Richard

AU - Desai, Neesha

AU - Zhao, Richard

PY - 2010/12/1

Y1 - 2010/12/1

N2 - In the standard rules of the board game Risk, players take turns selecting or "drafting" the 42 territories on the board until all territories are owned. We present a technique for drafting territories in Risk that combines theMonte Carlo tree search algorithm UCT with an automated evaluation function. Created through supervised machine learning, this function scores outcomes of drafts in order to shorten the length of a UCT simulation. Using this approach, we augment an existing bot for the computer game Lux Delux, a clone of Risk. Our drafting technique is shown to greatly improve performance against the strongest opponents supplied with Lux Delux. The evidence provided indicates that territory drafting is important to overall success in Risk.

AB - In the standard rules of the board game Risk, players take turns selecting or "drafting" the 42 territories on the board until all territories are owned. We present a technique for drafting territories in Risk that combines theMonte Carlo tree search algorithm UCT with an automated evaluation function. Created through supervised machine learning, this function scores outcomes of drafts in order to shorten the length of a UCT simulation. Using this approach, we augment an existing bot for the computer game Lux Delux, a clone of Risk. Our drafting technique is shown to greatly improve performance against the strongest opponents supplied with Lux Delux. The evidence provided indicates that territory drafting is important to overall success in Risk.

UR - http://www.scopus.com/inward/record.url?scp=84883107034&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84883107034&partnerID=8YFLogxK

M3 - Conference contribution

SN - 9781577354789

T3 - Proceedings of the 6th AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, AIIDE 2010

SP - 15

EP - 20

BT - Proceedings of the 6th AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, AIIDE 2010

ER -

Gibson R, Desai N, Zhao R. An automated technique for drafting territories in the board game risk. In Proceedings of the 6th AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, AIIDE 2010. 2010. p. 15-20. (Proceedings of the 6th AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment, AIIDE 2010).