Vis enkel innførsel

dc.contributor.advisorDowning, Keithnb_NO
dc.contributor.authorNilsen, Tobias Laupsanb_NO
dc.date.accessioned2014-12-19T13:39:34Z
dc.date.available2014-12-19T13:39:34Z
dc.date.created2013-04-28nb_NO
dc.date.issued2013nb_NO
dc.identifier618489nb_NO
dc.identifierntnudaim:8464nb_NO
dc.identifier.urihttp://hdl.handle.net/11250/253141
dc.description.abstractThis thesis explores the use of supervised learning in combination with evolutionary algorithms. The two techniques are used alone and in combination to train an artificial neural network to solve a small scale combat scenario in the real time strategy game StarCraft. The thesis focuses on whether or not it is indeed beneficial to use the two in combination and how injecting human knowledge through logged examples influences the results of the evolutionary algorithm. In the small scale combat scenario a number of agents must cooperate to defeat an equal number number of enemies. The different approaches to training the network are tested and it is found that using human knowledge to create an initial population for the evolutionary algorithm dramatically improves performance compared to the other approaches, and is able to produce solutions to the scenario of high quality.nb_NO
dc.languageengnb_NO
dc.publisherInstitutt for datateknikk og informasjonsvitenskapnb_NO
dc.titleThe Effects of Supervised Learning on Neuro-evolution in StarCraftnb_NO
dc.typeMaster thesisnb_NO
dc.source.pagenumber57nb_NO
dc.contributor.departmentNorges teknisk-naturvitenskapelige universitet, Fakultet for informasjonsteknologi, matematikk og elektroteknikk, Institutt for datateknikk og informasjonsvitenskapnb_NO


Tilhørende fil(er)

Thumbnail
Thumbnail
Thumbnail

Denne innførselen finnes i følgende samling(er)

Vis enkel innførsel