Performance Investigation of UCB Policy in Q-learning

Koki Saito, Akira Notsu, Seiki Ubukata, Katsuhiro Honda. Performance Investigation of UCB Policy in Q-learning. In 14th IEEE International Conference on Machine Learning and Applications, ICMLA 2015, Miami, FL, USA, December 9-11, 2015. pages 777-780, IEEE, 2015. [doi]

Abstract

Abstract is missing.