| Regret bounds for restless Markov bandits R Ortner, D Ryabko, P Auer, R Munos Theoretical Computer Science 558, 62-76, 2014 | 80 | 2014 |
| Online Regret Bounds for Undiscounted Continuous Reinforcement Learning R Ortner, D Ryabko NIPS, 1772-1780, 2012 | 68 | 2012 |
| Nonparametric statistical inference for ergodic processes D Ryabko, B Ryabko Information Theory, IEEE Transactions on 56 (3), 1430-1435, 2010 | 46* | 2010 |
| Consistent algorithms for clustering time series A Khaleghi, D Ryabko, J Mary, P Preux Journal of Machine Learning Research 17 (3), 1-32, 2016 | 41 | 2016 |
| Asymptotically optimal perfect steganographic systems BY Ryabko, DB Ryabko Problems of Information Transmission 45 (2), 184-190, 2009 | 40* | 2009 |
| Clustering processes D Ryabko arXiv preprint arXiv:1004.5194, 2010 | 39 | 2010 |
| Selecting the state-representation in reinforcement learning OA Maillard, R Munos, D Ryabko arXiv preprint arXiv:1302.2552, 2013 | 36 | 2013 |
| Discrimination between B-processes is impossible D Ryabko Journal of Theoretical Probability 23 (2), 565-575, 2010 | 31* | 2010 |
| Online clustering of processes A Khaleghi, D Ryabko, J Mary, P Preux Artificial Intelligence and Statistics, 601-609, 2012 | 29 | 2012 |
| Optimal regret bounds for selecting the state representation in reinforcement learning OA Maillard, P Nguyen, R Ortner, D Ryabko International Conference on Machine Learning, 543-551, 2013 | 26 | 2013 |
| On the possibility of learning in reactive environments with arbitrary dependence D Ryabko, M Hutter Theoretical Computer Science 405 (3), 274-284, 2008 | 26* | 2008 |
| Improved regret bounds for undiscounted continuous reinforcement learning K Lakshmanan, R Ortner, D Ryabko International Conference on Machine Learning, 524-532, 2015 | 23 | 2015 |
| Constructing perfect steganographic systems B Ryabko, D Ryabko Information and Computation 209 (9), 1223-1230, 2011 | 23 | 2011 |
| Selecting near-optimal approximate state representations in reinforcement learning R Ortner, OA Maillard, D Ryabko International Conference on Algorithmic Learning Theory, 140-154, 2014 | 22 | 2014 |
| Testing composite hypotheses about discrete ergodic processes D Ryabko test 21 (2), 317-329, 2012 | 22* | 2012 |
| Predicting non-stationary processes D Ryabko, M Hutter Applied Mathematics Letters 21 (5), 477-482, 2008 | 22* | 2008 |
| Pattern recognition for conditionally independent data D Ryabko The Journal of Machine Learning Research 7, 645-664, 2006 | 22* | 2006 |
| Locating Changes in Highly Dependent Data with Unknown Number of Change Points. A Khaleghi, D Ryabko NIPS, 3095-3103, 2012 | 21 | 2012 |
| A binary-classification-based metric between time-series distributions and its use in statistical and learning problems D Ryabko, J Mary The Journal of Machine Learning Research 14 (1), 2837-2856, 2013 | 20* | 2013 |
| Asymptotically consistent estimation of the number of change points in highly dependent time series A Khaleghi, D Ryabko International Conference on Machine Learning, 539-547, 2014 | 18 | 2014 |
Boris RyabkoInstitute of Computational Technologies SB RASVerified email at ryabko.net
