Player co-modelling in a strategy board game: discovering how to play fast

Simple item page
dc.creatorKalles, Dimitris
dc.date2006-11-30
dc.date.accessioned2026-07-07T07:31:48Z
dc.date.available2026-07-07T07:31:48Z
dc.descriptionIn this paper we experiment with a 2-player strategy board game where playing models are evolved using reinforcement learning and neural networks. The models are evolved to speed up automatic game development based on human involvement at varying levels of sophistication and density when compared to fully autonomous playing. The experimental results suggest a clear and measurable association between the ability to win games and the ability to do that fast, while at the same time demonstrating that there is a minimum level of human involvement beyond which no learning really occurs.
dc.descriptionContains 19 pages, 6 figures, 7 tables. Submitted to a journal
dc.identifierhttps://arxiv.org/abs/cs/0611164
dc.identifierhttp://arxiv.org/abs/cs/0611164
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/118886
dc.subjectArtificial Intelligence
dc.subjectMachine Learning
dc.titlePlayer co-modelling in a strategy board game: discovering how to play fast
dc.typetext

Files

Collections

arXiv