1. Recherche
45 résultats  enregistrer la recherche


  • 1
  • 2
hal-01057562v1  Communication dans un congrès
Ronald Ortner, Odalric-Ambrym Maillard, Daniil Ryabko. Selecting Near-Optimal Approximate State Representations in Reinforcement Learning
International Conference on Algorithmic Learning Theory (ALT), Oct 2014, Bled, Slovenia. Springer, 8776, pp.140-154, 2014, LNCS
hal-00823230v1  Communication dans un congrès
Phuong Nguyen, Odalric-Ambrym Maillard, Daniil Ryabko, Ronald Ortner. Competing with an Infinite Set of Models in Reinforcement Learning
AISTATS, 2013, Arizona, United States. 31, pp.463-471, 2013, JMLR W&CP
...
hal-00771128v1  Communication dans un congrès
Daniil Ryabko. ASYMPTOTIC STATISTICAL ANALYSIS OF STATIONARY ERGODIC TIME SERIES
WITMSE 2012, Aug 2012, Amsterdam, Netherlands. 2012
hal-00823233v1  Communication dans un congrès
Daniil Ryabko. Time-series information and learning
ISIT - International Symposium on Information Theory, 2013, Istanbul, Turkey. pp.1392-1395, 2013
...
inria-00477238v2  Communication dans un congrès
Daniil Ryabko. Clustering processes
27th International Conference on Machine Learning, Jun 2010, Haifa, Israel. pp.919-926, 2010
...
inria-00440669v3  Communication dans un congrès
Daniil Ryabko. Sequence prediction in realizable and non-realizable cases
Conference on Learning Theory, 2010, Haifa, Israel. pp.119-131, 2010, COLT
...
inria-00319076v7  Communication dans un congrès
Daniil Ryabko. An impossibility result for process discrimination
International Symposium on Information Theory, 2009, Seoul, South Korea. pp.1734-1738, 2009
hal-00351128v1  Direction d'ouvrage, Proceedings
Sertan Girgin, Manuel Loth, Rémi Munos, Philippe Preux, Daniil Ryabko. Recent Advances in Reinforcement Learning
Springer, Lectures Notes in Artificial Intelligence (LNAI), vol. 5323, pp.281, 2009
hal-00639482v1  Communication dans un congrès
Boris Ryabko, Daniil Ryabko. Confidence Sets in Time-Series Filtering
IEEE International Symposium on Information Theory, Jul 2011, St. Petersburg, Russia. IEEE, pp.2436-2438, 2011, Proceedings of IEEE International Symposium on Information Theory
hal-00639537v1  Article dans une revue
Daniil Ryabko. Discrimination between B-processes is impossible
Journal of Theoretical Probability, Sprnger, 2010, 23 (2), pp.565-575
hal-00639483v1  Communication dans un congrès
Odalric-Ambrym Maillard, Rémi Munos, Daniil Ryabko. Selecting the State-Representation in Reinforcement Learning
Neural Information Processing Systems, Dec 2011, Granada, Spain. 2011
hal-00639562v1  Communication dans un congrès
Boris Ryabko, Daniil Ryabko. Using Kolmogorov Complexity for Understanding Some Limitations on Steganography
IEEE International Symposium on Information Theory, 2009, seoul, South Korea. IEEE, pp.2733-2736, 2009
hal-00639546v1  Communication dans un congrès
Daniil Ryabko. Testing composite hypotheses about discrete-valued stationary processes
IEEE Information Theory Workshop, 2010, Cairo, Egypt. IEEE, pp.291-295, 2010
hal-00913250v1  Communication dans un congrès
Azadeh Khaleghi, Daniil Ryabko. Nonparametric multiple change point estimation in highly dependent time series
Proc. 24th International Conf. on Algorithmic Learning Theory (ALT'13), 2013, Singapore, Singapore. Springer, pp.382-396, 2013, LNCS 8139
hal-00913244v1  Communication dans un congrès
Daniil Ryabko. Unsupervised model-free representation learning
Proc. 24th International Conf. on Algorithmic Learning Theory (ALT'13), 2013, Singapore, Singapore. Springer, pp.354-366, 2013, LNCS 8139
hal-00639569v1  Article dans une revue
Daniil Ryabko, M. Hutter. On the Possibility of Learning in Reactive Environments with Arbitrary Dependence
Theoretical Computer Science, Elsevier, 2008, 405, pp.274-284
...
inria-00610009v2  Article dans une revue
Daniil Ryabko. Uniform hypothesis testing for finite-valued stationary processes
Statistics, Taylor & Francis: STM, Behavioural Science and Public Health Titles, 2014, 48 (1), pp.121-128. <10.1080/02331888.2012.719511>
hal-01074077v1  Article dans une revue
Ronald Ortner, Daniil Ryabko, Peter Auer, Rémi Munos. Regret bounds for restless Markov bandits
Journal of Theoretical Computer Science (TCS), Elsevier, 2014, 558, pp.62-76. <10.1016/j.tcs.2014.09.026>
hal-01026583v1  Communication dans un congrès
Azadeh Khaleghi, Daniil Ryabko. Asymptotically consistent estimation of the number of change points in highly dependent time series
International Conference on Machine Learning (ICML), Jun 2014, Beijing, China. pp.539-547, 2014
...
inria-00347706v1  Communication dans un congrès
Daniil Ryabko. Some sufficient conditions on an arbitrary class of stochastic processes for the existence of a predictor.
Freund, Y.; Györfi, L.; Turán, G.; Zeugmann, Th. 19th International Conference on Algorithmic Learning Theory, ALT 2008, Oct 2008, Budapest, Hungary. Springer, 5254, pp.169-182, 2008, Lecture Notes in Artificial Intelligence; Lecture Notes in Artificial Intelligence (LNAI). <http://link.springer.com/chapter/10.1007/978-3-540-87987-9_17>. <10.1007/978-3-540-87987-9_17>
...
hal-00675637v5  Communication dans un congrès
Daniil Ryabko, Jérémie Mary. Reducing statistical time-series problems to binary classification
NIPS, Dec 2012, Lake Tahoe, United States. pp.2069--2077, 2012
hal-00913253v1  Article dans une revue
Boris Ryabko, Daniil Ryabko. A confidence-set approach to signal denoising
Statistical Methodology, Elsevier, 2013, 15, pp.115--120
hal-00765436v1  Communication dans un congrès
Azadeh Khaleghi, Daniil Ryabko. Locating Changes in Highly Dependent Data with Unknown Number of Change Points
P. Bartlett and F.C.N. Pereira and C.J.C. Burges and L. Bottou and K.Q. Weinberger. NIPS 2012, 2012, Lake Tahoe, United States. pp.3095--3103, 2012, Advances in Neural Information Processing Systems 25
hal-00765441v1  Communication dans un congrès
Ronald Ortner, Daniil Ryabko. Online Regret Bounds for Undiscounted Continuous Reinforcement Learning
P. Bartlett and F.C.N. Pereira and C.J.C. Burges and L. Bottou and K.Q. Weinberger. NIPS 2012, 2012, Lake Tahoe, United States. pp.1772--1780, 2012, Advances in Neural Information Processing Systems 25
hal-00765450v1  Communication dans un congrès
Ronald Ortner, Daniil Ryabko, Peter Auer, Rémi Munos. Regret Bounds for Restless Markov Bandits
ALT 2012, 2012, Lyon, France. 7568, pp.214--228, 2012, LNCS
hal-00765462v1  Communication dans un congrès
Azadeh Khaleghi, Daniil Ryabko, Jérémie Mary, Philippe Preux. Online Clustering of Processes
AISTATS 2012, 2012, La Palma, Spain. 22, pp.601-609, 2012, JMLR W\&CP
...
hal-00778586v1  Communication dans un congrès
Odalric-Ambrym Maillard, Phuong Nguyen, Ronald Ortner, Daniil Ryabko. Optimal Regret Bounds for Selecting the State Representation in Reinforcement Learning
ICML - 30th International Conference on Machine Learning, 2013, Atlanta, USA, United States. 28(1), pp.543-551, 2013, JMLR W&CP
...
inria-00388523v1  Communication dans un congrès
Daniil Ryabko. Characterizing predictable classes of processes
UAI, 2009, Montreal, Canada. pp.471-478, 2009, Proceedings of the 25th Conference on Uncertainty in Artificial Intelligence (UAI'09)
  • 1
  • 2

Contact


archive-ouverte@inria.fr