Suivre
András Antos
Titre
Citée par
Citée par
Année
Learning near-optimal policies with Bellman-residual minimization based fitted policy iteration and a single sample path
A Antos, C Szepesvári, R Munos
Machine Learning 71, 89-129, 2008
4872008
Convergence properties of functional estimates for discrete distributions
A Antos, I Kontoyiannis
Random Structures & Algorithms 19 (3‐4), 163-193, 2001
3042001
Fitted Q-iteration in continuous action-space MDPs
A Antos, R Munos, C Szepesvári
Advances in Neural Information Processing Systems 20, 9-16, 2008
2902008
Online Markov decision processes under bandit feedback
G Neu, A György, C Szepesvári, A Antos
Advances in Neural Information Processing Systems 23, 1804-1812, 2010
2052010
Lower bounds for Bayes error estimation
A Antos, L Devroye, L Györfi
Pattern Analysis and Machine Intelligence, IEEE Transactions on 21 (7), 643-645, 1999
1001999
Active learning in multi-armed bandits
A Antos, V Grover, C Szepesvári
Algorithmic Learning Theory: 19th International Conference, ALT 2008 …, 2008
712008
Active learning in heteroscedastic noise
A Antos, V Grover, C Szepesvári
Theoretical Computer Science 411 (29-30), 2712-2728, 2010
702010
Individual convergence rates in empirical vector quantizer design
A Antos, L Györfi, A György
Information Theory, IEEE Transactions on 51 (11), 4013-4022, 2005
532005
Improved convergence rates in empirical vector quantizer design
A Antos, L Györfi, A György
Proceedings 2004 IEEE International Symposium on Information Theory, 301, 2004
53*2004
Value-iteration based fitted policy iteration: learning with a single trajectory
A Antos, C Szepesvári, R Munos
Approximate Dynamic Programming and Reinforcement Learning, 2007. ADPRL 2007 …, 2007
522007
Data-dependent margin-based generalization bounds for classification
A Antos, B Kégl, T Linder, G Lugosi
Journal of Machine Learning Research 3, 73-98, 2003
522003
Toward a classification of finite partial-monitoring games
A Antos, G Bartók, D Pál, C Szepesvári
Theoretical Computer Science, Arxiv preprint arXiv:1102.2041, 2012
502012
Strong minimax lower bounds for learning
A Antos, G Lugosi
Proceedings of the Ninth Annual Conference on Computational Learning Theory …, 1996
411996
Learning near-optimal policies with Bellman-residual minimization based fitted policy iteration and a single sample path
A Antos, C Szepesvari, R Munos
The Nineteenth Annual Conference on Learning Theory, COLT 2006, Proceedings …, 2006
402006
Improved minimax bounds on the test and training distortion of empirical designed vector quantizers
A Antos
LNCS/LNAI: The Eighteenth Annual Conference on Learning Theory, COLT 2005 …, 2005
342005
Forced-exploration based algorithms for playing in stochastic linear bandits
Y Abbasi-Yadkori, A Antos, C Szepesvári
COLT Workshop on On-line Learning with Limited Feedback 92, 236, 2009
252009
Adaptive strategy for stratified Monte Carlo sampling.
A Carpentier, R Munos, A Antos
J. Mach. Learn. Res. 16, 2231-2271, 2015
192015
Lower bounds on the rate of convergence of nonparametric regression estimates
A Antos, L Györfi, M Kohler
Journal of statistical planning and inference 83 (1), 91-100, 2000
182000
Estimating the entropy of discrete distributions
A Antos, I Kontoyiannis
IEEE International Symposium on Information Theory, 45-45, 2001
172001
Performance limits of nonparametric estimators
A Antos
Technical University of Budapest, 1999
81999
Le système ne peut pas réaliser cette opération maintenant. Veuillez réessayer plus tard.
Articles 1–20