An internet-assisted Dixit-playing AI

Dimitris Vatsakis; Paris Mavromoustakos Blom; Pieter Spronck

doi:10.1145/3555858.3555863

An internet-assisted Dixit-playing AI

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific › peer-review

289 Downloads (Pure)

Abstract

This paper investigates the development of an Artificial Intelligence
(AI) agent which plays the voting phase of the board game Dixit.
Given a set of open cards and a lexical “hint” provided by a player,
our algorithm aims to predict which card the hint originally refers
to. The AI agent is developed using Machine Learning (ML) algo-
rithms for Natural Language Processing (NLP). The AI agent is
equipped with models that explore data of human-played games
and retrieves information from the internet to deal with any short-
age of information. We show that the Dixit AI agent we developed
is more accurate than the average human player in finding the card
which corresponds to a hint.

Original language	English
Title of host publication	Proceedings of the FDG2022
Subtitle of host publication	Proceedings of the 17th International Conference on the Foundations of Digital Games
Place of Publication	New York, NY, United States
Publisher	Association for Computing Machinery
Pages	1-7
Number of pages	7
ISBN (Print)	9781450397957
DOIs	https://doi.org/10.1145/3555858.3555863
Publication status	Published - 4 Nov 2022
Event	FDG22: 17th International Conference on the Foundations of Digital Games - Athens, Greece Duration: 5 Sept 2022 → 8 Sept 2022

Conference

Conference	FDG22: 17th International Conference on the Foundations of Digital Games
Country/Territory	Greece
City	Athens
Period	5/09/22 → 8/09/22

Keywords

Gaming
Dixit
Data Analysis

Access to Document

10.1145/3555858.3555863

VatsakisFDG2022

Cite this

@inproceedings{657dc1bc19ef4aa2aeea6780850f3bba,

title = "An internet-assisted Dixit-playing AI",

abstract = "This paper investigates the development of an Artificial Intelligence (AI) agent which plays the voting phase of the board game Dixit. Given a set of open cards and a lexical {\textquotedblleft}hint{\textquotedblright} provided by a player, our algorithm aims to predict which card the hint originally refers to. The AI agent is developed using Machine Learning (ML) algo- rithms for Natural Language Processing (NLP). The AI agent is equipped with models that explore data of human-played games and retrieves information from the internet to deal with any short- age of information. We show that the Dixit AI agent we developed is more accurate than the average human player in finding the card which corresponds to a hint.",

keywords = "Gaming, Dixit, Data Analysis",

author = "Dimitris Vatsakis and \{Mavromoustakos Blom\}, Paris and Pieter Spronck",

year = "2022",

month = nov,

day = "4",

doi = "10.1145/3555858.3555863",

language = "English",

isbn = " 9781450397957",

pages = "1--7",

booktitle = "Proceedings of the FDG2022",

publisher = "Association for Computing Machinery",

address = "United States",

note = "FDG22: 17th International Conference on the Foundations of Digital Games ; Conference date: 05-09-2022 Through 08-09-2022",

}

Vatsakis, D, Mavromoustakos Blom, P & Spronck, P 2022, An internet-assisted Dixit-playing AI. in Proceedings of the FDG2022: Proceedings of the 17th International Conference on the Foundations of Digital Games., 40, Association for Computing Machinery, New York, NY, United States, pp. 1-7, FDG22: 17th International Conference on the Foundations of Digital Games, Athens, Greece, 5/09/22. https://doi.org/10.1145/3555858.3555863

An internet-assisted Dixit-playing AI. / Vatsakis, Dimitris; Mavromoustakos Blom, Paris ; Spronck, Pieter.
Proceedings of the FDG2022: Proceedings of the 17th International Conference on the Foundations of Digital Games. New York, NY, United States: Association for Computing Machinery, 2022. p. 1-7 40.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific › peer-review

TY - GEN

T1 - An internet-assisted Dixit-playing AI

AU - Vatsakis, Dimitris

AU - Mavromoustakos Blom, Paris

AU - Spronck, Pieter

PY - 2022/11/4

Y1 - 2022/11/4

N2 - This paper investigates the development of an Artificial Intelligence (AI) agent which plays the voting phase of the board game Dixit. Given a set of open cards and a lexical “hint” provided by a player, our algorithm aims to predict which card the hint originally refers to. The AI agent is developed using Machine Learning (ML) algo- rithms for Natural Language Processing (NLP). The AI agent is equipped with models that explore data of human-played games and retrieves information from the internet to deal with any short- age of information. We show that the Dixit AI agent we developed is more accurate than the average human player in finding the card which corresponds to a hint.

AB - This paper investigates the development of an Artificial Intelligence (AI) agent which plays the voting phase of the board game Dixit. Given a set of open cards and a lexical “hint” provided by a player, our algorithm aims to predict which card the hint originally refers to. The AI agent is developed using Machine Learning (ML) algo- rithms for Natural Language Processing (NLP). The AI agent is equipped with models that explore data of human-played games and retrieves information from the internet to deal with any short- age of information. We show that the Dixit AI agent we developed is more accurate than the average human player in finding the card which corresponds to a hint.

KW - Gaming

KW - Dixit

KW - Data Analysis

U2 - 10.1145/3555858.3555863

DO - 10.1145/3555858.3555863

M3 - Conference contribution

SN - 9781450397957

SP - 1

EP - 7

BT - Proceedings of the FDG2022

PB - Association for Computing Machinery

CY - New York, NY, United States

T2 - FDG22: 17th International Conference on the Foundations of Digital Games

Y2 - 5 September 2022 through 8 September 2022

ER -

An internet-assisted Dixit-playing AI

Abstract

Conference

Keywords

Access to Document

Fingerprint

Cite this