Learning a Representation of a Believable Virtual Character's Environment with an Imitation Algorithm - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2010

Learning a Representation of a Believable Virtual Character's Environment with an Imitation Algorithm

Résumé

In video games, virtual characters' decision systems often use a simplified representation of the world. To increase both their autonomy and believability we want those characters to be able to learn this representation from human players. We propose to use a model called growing neural gas to learn by imitation the topology of the environment. The implementation of the model, the modifications and the parameters we used are detailed. Then, the quality of the learned representations and their evolution during the learning are studied using different measures. Improvements for the growing neural gas to give more information to the character's model are given in the conclusion.
Fichier principal
Vignette du fichier
goar.pdf (189.43 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-00550707 , version 1 (29-12-2010)

Identifiants

Citer

Fabien Tencé, Cédric Buche, Pierre de Loor, Olivier Marc Marc. Learning a Representation of a Believable Virtual Character's Environment with an Imitation Algorithm. GAMEON-ARABIA'10, Dec 2010, Egypt. pp.141-145. ⟨hal-00550707⟩

Collections

UNIV-BREST ENIB
52 Consultations
47 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More