Get started
Author

Daniil Ryabko

Online Regret Bounds for Undiscounted Continuous Reinforcement Learning
2013 · Ortner, Ronald, Ryabko, Daniil · arXiv (Cornell University) · 53
PDF
Consistent Algorithms for Clustering Time Series
2016 · Khaleghi, Azadeh, Ryabko, Daniil, et al. · Lancaster EPrints (Lancaster University) · 41
PDF
Regret Bounds for Restless Markov Bandits
2012 · Ronald Ortner, Daniil Ryabko, et al. · Lecture notes in computer science · 37
Regret bounds for restless Markov bandits
2014 · Ronald Ortner, Daniil Ryabko, et al. · Theoretical Computer Science · 34
Selecting the State-Representation in Reinforcement Learning
2013 · Maillard, Odalric-Ambrym, Munos, Rémi, et al. · arXiv (Cornell University) · 29
PDF
Nonparametric Statistical Inference for Ergodic Processes
2010 · Daniil Ryabko, Boris Ryabko · IEEE Transactions on Information Theory · 29
Regret Bounds for Restless Markov Bandits
2012 · Ortner, Ronald, Ryabko, Daniil, et al. · arXiv (Cornell University) · 28
Improved Regret Bounds for Undiscounted Continuous Reinforcement Learning
2015 · Lakshmanan, Kailasam, Ortner, Ronald, et al. · HAL (Le Centre pour la Communication Scientifique Directe) · 27
Discrimination Between B-Processes is Impossible
2009 · Daniil Ryabko · Journal of Theoretical Probability · 24
Asymptotically optimal perfect steganographic systems
2009 · B. Ya. Ryabko, D. B. Ryabko · Problems of Information Transmission · 22
Reinforcement learning
1993 · Odalric-ambrym Maillard, Phuong Nguyen, et al. · Computers & Mathematics with Applications · 22
Asymptotic Nonparametric Statistical Analysis of Stationary Time Series
2019 · Daniil Ryabko · SpringerBriefs in computer science · 21
PDF
Optimal Regret Bounds for Selecting the State Representation in Reinforcement Learning
2013 · Maillard, Odalric-Ambrym, Nguyen, Phuong, et al. · arXiv (Cornell University) · 21
PDF
On the possibility of learning in reactive environments with arbitrary dependence
2008 · Daniil Ryabko, Marcus Hutter · Theoretical Computer Science · 21
PDF
Pattern Recognition for Conditionally Independent Data
2005 · Ryabko, Daniil · arXiv (Cornell University) · 21
PDF
Online Clustering of Processes
2012 · Khaleghi, Azadeh, Ryabko, Daniil, et al. · 20
Clustering processes
2010 · Ryabko, Daniil · arXiv (Cornell University) · 18
PDF
On hypotheses testing for ergodic processes
2008 · Daniil Ryabko, Boris Ryabko · IEEE Information Theory Workshop (ITW) · 18
Selecting Near-Optimal Approximate State Representations in Reinforcement Learning
2014 · Ronald Ortner, Odalric-Ambrym Maillard, et al. · Lecture notes in computer science · 17
PDF
On Sequence Prediction for Arbitrary Measures
2007 · Daniil Ryabko, Marcus Hutter · IEEE International Symposium on Information Theory (ISIT) · 16
Testing composite hypotheses about discrete ergodic processes
2011 · Daniil Ryabko · Test · 15
Predicting non-stationary processes
2007 · Daniil Ryabko, Marcus Hutter · Applied Mathematics Letters · 15
PDF
Locating Changes in Highly Dependent Data with Unknown Number of Change Points
2012 · Azadeh Khaleghi, Daniil Ryabko · 14
Information-Theoretic Approach to Steganographic Systems
2007 · Boris Ryabko, Daniil Ryabko · IEEE International Symposium on Information Theory (ISIT) · 13
Constructing perfect steganographic systems
2011 · Boris Ryabko, Daniil Ryabko · Information and Computation · 12
PDF
Works count: 140
Citation count: 791
H-index: 18
I10-index: 31
Year
Topic
Type