Position-Based Multiple-Play Bandits with Thompson Sampling
Published in IDA2021, 2021
Recommended citation: Gauthier, C.-S.; Gaudel, R.; Fromont, E. Position-based multiple-play bandits with thompson sampling. IDA’21, 2021. https://hal.archives-ouvertes.fr/hal-03163763/document
This paper present PB-MHB a algorithm based on Thompson Sampling bandits and Metropolis Hasting method to adresse list recommendation under the Position Based Model.
Download paper here You can consult an extended version of this paper here Code to reproduce our experiment is available here
Recommended citation: Gauthier, C.-S.; Gaudel, R.; Fromont, E. Position-based multiple-play bandits with thompson sampling. IDA’21, 2021.