MG-CNN: A Deep CNN To Predict Saddle Points Of Matrix Games - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue Neural Networks Année : 2022

MG-CNN: A Deep CNN To Predict Saddle Points Of Matrix Games

Dawen Wu
Abdel Lisser

Résumé

Finding the saddle point of a matrix game is a classical problem that arises in various fields, e.g., economics, computer science, and engineering. The standard problem-solving methods consist of formulating the problem as a linear program (LP). However, this approach seems to be inappropriate, especially when multiple instances need to be solved. In this paper, we propose a Convolutional Neural Network based approach, which is able to predict both the strategy profile (x, y) and the optimal value v of the game. We call this approach Matrix Game-Conventional Neural Network or MG-CNN for short. Thanks to a global pooling technique, MG-CNN can solve matrix games with different shapes. We propose a specialized algorithm to train MG-CNN, which includes both data generation and model training. Our numerical experiments show that MG-CNN outperforms standard LP solvers in terms of computational CPU time and provides a high quality prediction.
Fichier principal
Vignette du fichier
No__6_Maple_leaf__manuscript__1st_revision_ (5).pdf (491.45 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04370990 , version 1 (03-01-2024)

Identifiants

Citer

Dawen Wu, Abdel Lisser. MG-CNN: A Deep CNN To Predict Saddle Points Of Matrix Games. Neural Networks, 2022, 156, pp.49-57. ⟨10.1016/j.neunet.2022.09.014⟩. ⟨hal-04370990⟩
18 Consultations
17 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More