Using CNN for solving two-player zero-sum games - Archive ouverte HAL Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2021

Using CNN for solving two-player zero-sum games

Dawen Wu
  • Fonction : Auteur
  • PersonId : 1110021

Résumé

We study a two-player zero-sum game (matrix game for short) with the objective to find the saddle point and its value. We develop a novel convolutional neural network (CNN for short) approach to achieve the goal. We propose a complete training pipeline, including a specific CNN model structure to handle varying game size, generating training dataset and model fitting. The experiment results show that our proposed method outperforms the traditional linear programming (LP for short) method in terms of computational efforts.
Fichier principal
Vignette du fichier
CNN_saddle_point_revise__clean_version_.pdf (515.83 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03341813 , version 1 (13-09-2021)

Identifiants

  • HAL Id : hal-03341813 , version 1

Citer

Dawen Wu, Abdel Lisser. Using CNN for solving two-player zero-sum games. 2021. ⟨hal-03341813⟩
54 Consultations
497 Téléchargements

Partager

Gmail Facebook X LinkedIn More