Alexander Nazin, Boris Miller. On effectiveness of the Mirror Decent Algorithm for a stochastic multi-armed bandit governed by a stationary finite Markov chain. In 2013 Australian Control Conference, Fremantle, WA, Australia, November 4-5, 2013. pages 244-250, IEEE, 2013. [doi]
@inproceedings{NazinM13-0, title = {On effectiveness of the Mirror Decent Algorithm for a stochastic multi-armed bandit governed by a stationary finite Markov chain}, author = {Alexander Nazin and Boris Miller}, year = {2013}, doi = {10.1109/AUCC.2013.6697280}, url = {https://doi.org/10.1109/AUCC.2013.6697280}, researchr = {https://researchr.org/publication/NazinM13-0}, cites = {0}, citedby = {0}, pages = {244-250}, booktitle = {2013 Australian Control Conference, Fremantle, WA, Australia, November 4-5, 2013}, publisher = {IEEE}, }