Advanced Dynamic Scripting for Fighting Game AI - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2015

Advanced Dynamic Scripting for Fighting Game AI

Kevin Majchrzak
  • Fonction : Auteur
  • PersonId : 1030212
Jan Quadflieg
  • Fonction : Auteur
  • PersonId : 1030213
Günter Rudolph
  • Fonction : Auteur
  • PersonId : 1030214

Résumé

We present an advanced version of dynamic scripting, which we apply to an agent created for the Fighting Game AI Competition. In contrast to the original method, our new approach is able to successfully adapt an agent’s behavior in real-time scenarios. Based on a set of rules created with expert knowledge, a script containing a subset of these rules is created online to control our agent. Our method uses reinforcement learning to learn which rules to include in the script and how to arrange them. Results show that the algorithm successfully adapts the agent’s behavior in tests against three other agents, allowing our agent to win most evaluations in our tests and the CIG 2014 competition.
Fichier principal
Vignette du fichier
371182_1_En_7_Chapter.pdf (1.73 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01758421 , version 1 (04-04-2018)

Licence

Paternité

Identifiants

Citer

Kevin Majchrzak, Jan Quadflieg, Günter Rudolph. Advanced Dynamic Scripting for Fighting Game AI. 14th International Conference on Entertainment Computing (ICEC), Sep 2015, Trondheim, Norway. pp.86-99, ⟨10.1007/978-3-319-24589-8_7⟩. ⟨hal-01758421⟩
284 Consultations
1291 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More