Mining Balanced Sequential Patterns in RTS Games 1

Guillaume Bosc 1 Mehdi Kaytoue 1 Chedy Raïssi 2 Jean-François Boulicaut 1 Philip Tan 3
1 DM2L - Data Mining and Machine Learning
LIRIS - Laboratoire d'InfoRmatique en Image et Systèmes d'information
2 ORPAILLEUR - Knowledge representation, reasonning
Inria Nancy - Grand Est, LORIA - NLPKD - Department of Natural Language Processing & Knowledge Discovery
3 GameLab MIT
MIT - Massachusetts Institute of Technology
Abstract : The video game industry has grown enormously over the last twenty years, bringing new challenges to the artificial intelli-gence and data analysis communities. We tackle here the problem of automatic discovery of strategies in real-time strategy games through pattern mining. Such patterns are the basic units for many tasks such as automated agent design, but also to build tools for the profession-ally played video games in the electronic sports scene. Our formal-ization relies on a sequential pattern mining approach and a novel measure, the balance measure, telling how a strategy is likely to win. We experiment our methodology on a real-time strategy game that is professionally played in the electronic sport community.
Document type :
Conference papers
Complete list of metadatas

Cited literature [8 references]  Display  Hide  Download

https://hal.inria.fr/hal-01100933
Contributor : Chedy Raïssi <>
Submitted on : Wednesday, January 7, 2015 - 1:25:46 PM
Last modification on : Thursday, February 7, 2019 - 3:59:54 PM
Long-term archiving on : Wednesday, April 8, 2015 - 12:05:35 PM

File

FAIA263-0975.pdf
Files produced by the author(s)

Licence


Copyright

Identifiers

Citation

Guillaume Bosc, Mehdi Kaytoue, Chedy Raïssi, Jean-François Boulicaut, Philip Tan. Mining Balanced Sequential Patterns in RTS Games 1. ECAI 2014 - 21st European Conference on Artificial Intelligence, Aug 2014, Prague, Czech Republic. ⟨10.3233/978-1-61499-419-0-975⟩. ⟨hal-01100933⟩

Share

Metrics

Record views

1094

Files downloads

328