Generating Adequate Representations for Learning from Interaction in Complex Multiagent Simulations - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2005

Generating Adequate Representations for Learning from Interaction in Complex Multiagent Simulations

Vincent Corruble
Geber Ramalho
  • Fonction : Auteur
  • PersonId : 996796

Résumé

Wargames are an example of complex multiagent simulations for which, specifying agent behavior adequately in advance for all potential situations is not feasible. In this context, we have applied reinforcement learning as an adaptive approach to design strategies for these simulations. In this paper, we introduce our approach and focus on a novel algorithm for generating representations with adequate granularities for commanders of a military hierarchy.
Fichier non déposé

Dates et versions

hal-01420551 , version 1 (20-12-2016)

Identifiants

Citer

Charles Madeira, Vincent Corruble, Geber Ramalho. Generating Adequate Representations for Learning from Interaction in Complex Multiagent Simulations. International Conference on Intelligent Agent Technology, Sep 2005, Compiegne, France. pp.512-515, ⟨10.1109/IAT.2005.79⟩. ⟨hal-01420551⟩
61 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More