CCGnet: A deep learning approach to predict Nash equilibrium of chance-constrained games
Résumé
This paper proposes a novel method for efficiently finding the Nash equilibrium in a chance-constrained games (CCG). Conventional numerical integration methods require significant computational time to solve multiple instances of CCG. We introduce CCGnet, a deep learning approach which can solve efficiently multiple instances of CCG in a one-shot manner. CCGnet uses a specialized network structure and training algorithm based on neurodynamic optimization. We present the strong performance of CCGnet in practice and show that our proposed method outperforms conventional methods.
Origine : Fichiers produits par l'(les) auteur(s)