Improved Saddle Point Prediction in Stochastic Two-Player Zero-Sum Games with a Deep Learning Approach - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue Engineering Applications of Artificial Intelligence Année : 2023

Improved Saddle Point Prediction in Stochastic Two-Player Zero-Sum Games with a Deep Learning Approach

Dawen Wu
Abdel Lisser

Résumé

In this paper, we propose a novel deep learning approach for predicting saddle points in stochastic twoplayer zero-sum games. Our method combines neurodynamic optimization and deep neural networks. First, we model the stochastic two-player zero-sum game as an ordinary differential equation (ODE) system using neurodynamic optimization. Second, we develop a neural network to approximate the solution to the ODE system, which includes the saddle point prediction for the game problem. Third, we introduce a specialized algorithm for training the neural network to enhance the accuracy of the saddle point prediction. Our experiments demonstrate that our model outperforms existing approaches, yielding faster convergence and more accurate saddle point predictions.
Fichier principal
Vignette du fichier
No__8_EAAI_revision (1).pdf (631.67 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04370979 , version 1 (03-01-2024)

Identifiants

Citer

Dawen Wu, Abdel Lisser. Improved Saddle Point Prediction in Stochastic Two-Player Zero-Sum Games with a Deep Learning Approach. Engineering Applications of Artificial Intelligence, 2023, 126, pp.106664. ⟨10.1016/j.engappai.2023.106664⟩. ⟨hal-04370979⟩
13 Consultations
13 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More