Reference : Imitative Learning for Real-Time Strategy Games
Scientific congresses and symposiums : Paper published in a book
Engineering, computing & technology : Computer science
http://hdl.handle.net/2268/131924
Imitative Learning for Real-Time Strategy Games
English
Gemine, Quentin mailto [Université de Liège - ULg > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Smart grids >]
Safadi, Firas mailto [Université de Liège - ULg > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Dép. d'électric., électron. et informat. (Inst.Montefiore) >]
Fonteneau, Raphaël mailto [Université de Liège - ULg > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Systèmes et modélisation >]
Ernst, Damien mailto [Université de Liège - ULg > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Smart grids >]
2012
Proceedings of the 2012 IEEE Conference on Computational Intelligence and Games
424-429
Yes
No
International
2012 IEEE Conference on Computational Intelligence and Games
11-14 September 2012
Granada
Spain
[en] real-time strategy games ; intelligent agent ; imitative learning ; Starcraft
[en] Over the past decades, video games have become increasingly popular and complex. Virtual worlds have gone a long way since the first arcades and so have the artificial intelligence (AI) techniques used to control agents in these growing environments. Tasks such as world exploration, con- strained pathfinding or team tactics and coordination just to name a few are now default requirements for contemporary video games. However, despite its recent advances, video game AI still lacks the ability to learn. In this paper, we attempt to break the barrier between video game AI and machine learning and propose a generic method allowing real-time strategy (RTS) agents to learn production strategies from a set of recorded games using supervised learning. We test this imitative learning approach on the popular RTS title StarCraft II® and successfully teach a Terran agent facing a Protoss opponent new production strategies.
Fonds de la Recherche Scientifique (Communauté française de Belgique) - F.R.S.-FNRS
Researchers ; Professionals ; Students
http://hdl.handle.net/2268/131924

File(s) associated to this reference

Fulltext file(s):

FileCommentaryVersionSizeAccess
Open access
paper85.pdfAuthor preprint586.86 kBView/Open

Bookmark and Share SFX Query

All documents in ORBi are protected by a user license.