Transfer of Fully Convolutional Policy-Value Networks Between Games and Game Variants - Archive ouverte HAL Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2022

Transfer of Fully Convolutional Policy-Value Networks Between Games and Game Variants

Résumé

In this paper, we use fully convolutional architectures in AlphaZero-like self-play training setups to facilitate transfer between variants of board games as well as distinct games. We explore how to transfer trained parameters of these architectures based on shared semantics of channels in the state and action representations of the Ludii general game system. We use Ludii's large library of games and game variants for extensive transfer learning evaluations, in zero-shot transfer experiments as well as experiments with additional fine-tuning time.

Dates et versions

hal-03594881 , version 1 (03-03-2022)

Identifiants

Citer

Dennis J. N. J. Soemers, Vegard Mella, Eric Piette, Matthew Stephenson, Cameron Browne, et al.. Transfer of Fully Convolutional Policy-Value Networks Between Games and Game Variants. 2022. ⟨hal-03594881⟩
11 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More