Finite sample analyses for TD (0) with function approximation G Dalal, B Szörényi, G Thoppe, S Mannor Proceedings of the AAAI Conference on Artificial Intelligence 32 (1), 2018 | 180 | 2018 |
Distributed clustering of linear bandits in peer to peer networks N Korda, B Szörényi, S Li Journal of Machine Learning Research Workshop and Conference Proceedings 48 …, 2016 | 174 | 2016 |
Finite sample analysis of two-timescale stochastic approximation with applications to reinforcement learning G Dalal, G Thoppe, B Szörényi, S Mannor Conference On Learning Theory, 1199-1233, 2018 | 119 | 2018 |
Gossip-based distributed stochastic bandit algorithms B Szorenyi, R Busa-Fekete, I Hegedus, R Ormándi, M Jelasity, B Kégl International conference on machine learning, 19-27, 2013 | 118 | 2013 |
Online rank elicitation for plackett-luce: A dueling bandits approach B Szörényi, R Busa-Fekete, A Paul, E Hüllermeier Advances in neural information processing systems 28, 2015 | 98 | 2015 |
Top-k selection based on adaptive sampling of noisy preferences R Busa-Fekete, B Szorenyi, W Cheng, P Weng, E Hüllermeier International Conference on Machine Learning, 1094-1102, 2013 | 91 | 2013 |
Preference-based rank elicitation using statistical models: The case of mallows R Busa-Fekete, E Hüllermeier, B Szörényi International conference on machine learning, 1071-1079, 2014 | 78 | 2014 |
Preference-based reinforcement learning: evolutionary direct policy search using a preference-based racing algorithm R Busa-Fekete, B Szörényi, P Weng, W Cheng, E Hüllermeier Machine learning 97, 327-351, 2014 | 68 | 2014 |
Qualitative multi-armed bandits: A quantile-based approach B Szorenyi, R Busa-Fekete, P Weng, E Hüllermeier International Conference on Machine Learning, 1660-1668, 2015 | 54 | 2015 |
Characterizing statistical query learning: simplified notions and proofs B Szörényi International Conference on Algorithmic Learning Theory, 186-200, 2009 | 52 | 2009 |
A tale of two-timescale reinforcement learning with the tightest finite-time bound G Dalal, B Szorenyi, G Thoppe Proceedings of the AAAI Conference on Artificial Intelligence 34 (04), 3701-3708, 2020 | 50 | 2020 |
Horn Complements: Towards Horn-to-Horn Belief Revision. M Langlois, RH Sloan, B Szörényi, G Turán AAAI, 466-471, 2008 | 46 | 2008 |
Online f-measure optimization R Busa-Fekete, B Szörényi, K Dembczynski, E Hüllermeier Advances in Neural Information Processing Systems 28, 2015 | 45 | 2015 |
Multi-objective bandits: Optimizing the generalized gini index R Busa-Fekete, B Szörényi, P Weng, S Mannor International Conference on Machine Learning, 625-634, 2017 | 42 | 2017 |
Theory revision with queries: Horn, read-once, and parity formulas J Goldsmith, RH Sloan, B Szörényi, G Turán Artificial Intelligence 156 (2), 139-176, 2004 | 31* | 2004 |
PAC rank elicitation through adaptive sampling of stochastic pairwise preferences R Busa-Fekete, B Szörényi, E Hüllermeier Proceedings of the AAAI Conference on Artificial Intelligence 28 (1), 2014 | 29 | 2014 |
Optimistic planning in Markov decision processes using a generative model B Szörényi, G Kedenburg, R Munos Advances in Neural Information Processing Systems 27, 2014 | 28 | 2014 |
Optimal learning of mallows block model R Busa-Fekete, D Fotakis, B Szörényi, M Zampetakis Conference on learning theory, 529-532, 2019 | 24 | 2019 |
On k-Term DNF with the Largest Number of Prime Implicants RH Sloan, B Szörényi, G Turán SIAM Journal on Discrete Mathematics 21 (4), 987-998, 2008 | 24 | 2008 |
PAC Bandits with Risk Constraints. Y David, B Szörényi, M Ghavamzadeh, S Mannor, N Shimkin ISAIM, 2018 | 22 | 2018 |