TY - GEN
T1 - AI-based playtesting of contemporary board games
AU - Mesentier Silva, Fernando De
AU - Lee, Scott
AU - Togelius, Julian
AU - Nealen, Andy
N1 - Funding Information:
Authors thank the support of CAPES, Coordena¸cão de Aperfei¸coa-mento de Pessoal de Nível Superior - Brazil.
Publisher Copyright:
© 2017 ACM.
PY - 2017/8/14
Y1 - 2017/8/14
N2 - Ticket to Ride is a popular contemporary board game for two to four players, featuring a number of expansions with additional maps and tweaks to the core game mechanics. In this paper, four different game-playing agents that embody different playing styles are defined and used to analyze Ticket to Ride. Different playing styles are shown to be effective depending on the map and rule variation, and also depending on how many players play the game. The performance profiles of the different agents can be used to characterize maps and identify the most similar maps in the space of playstyles. Further analysis of the automatically played games reveal which cities on the map are most desirable, and that the relative attractiveness of cities is remarkably consistent across numbers of players. Finally, the automated analysis also reveals two classes of failures states, where the agents find states which are not covered by the game rules; this is akin to finding bugs in the rules. We see the analysis performed here as a possible template for AI-based playtesting of contemporary board games.
AB - Ticket to Ride is a popular contemporary board game for two to four players, featuring a number of expansions with additional maps and tweaks to the core game mechanics. In this paper, four different game-playing agents that embody different playing styles are defined and used to analyze Ticket to Ride. Different playing styles are shown to be effective depending on the map and rule variation, and also depending on how many players play the game. The performance profiles of the different agents can be used to characterize maps and identify the most similar maps in the space of playstyles. Further analysis of the automatically played games reveal which cities on the map are most desirable, and that the relative attractiveness of cities is remarkably consistent across numbers of players. Finally, the automated analysis also reveals two classes of failures states, where the agents find states which are not covered by the game rules; this is akin to finding bugs in the rules. We see the analysis performed here as a possible template for AI-based playtesting of contemporary board games.
KW - Artificial Intelligence
KW - Board Games
KW - Contemporary Board Games
KW - Playtesting
KW - Ticket to Ride
UR - http://www.scopus.com/inward/record.url?scp=85030788695&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85030788695&partnerID=8YFLogxK
U2 - 10.1145/3102071.3102105
DO - 10.1145/3102071.3102105
M3 - Conference contribution
AN - SCOPUS:85030788695
T3 - ACM International Conference Proceeding Series
BT - Proceedings of the 12th International Conference on the Foundations of Digital Games, FDG 2017
A2 - Canossa, Alessandro
A2 - Sicart, Miguel
A2 - Harteveld, Casper
A2 - Zhu, Jichen
A2 - Deterding, Sebastian
PB - Association for Computing Machinery
T2 - 12th International Conference on the Foundations of Digital Games, FDG 2017
Y2 - 14 August 2017 through 17 August 2017
ER -