From minimax value to low-regret algorithms for online Markov decision processes. Guan, P., Raginsky, M., & Willett, R. In American Control Conference, 2014.
bibtex   
@inproceedings{minimaxMDP_ACC,
author = {P. Guan and M. Raginsky and R. Willett},
title = {From minimax value to low-regret algorithms for online {M}arkov decision processes},
booktitle={American Control Conference},
year = 2014}

Downloads: 0