| Incentivizing users for balancing bike sharing systems A Singla, M Santoni, G Bartók, P Mukerji, M Meenen, A Krause Proceedings of the AAAI Conference on Artificial Intelligence 29 (1), 2015 | 180 | 2015 |
| Partial monitoring—classification, regret bounds, and algorithms G Bartók, DP Foster, D Pál, A Rakhlin, C Szepesvári Mathematics of Operations Research 39 (4), 967-997, 2014 | 98 | 2014 |
| Near-optimally teaching the crowd to classify A Singla, I Bogunovic, G Bartók, A Karbasi, A Krause International Conference on Machine Learning, 154-162, 2014 | 98 | 2014 |
| An efficient algorithm for learning with semi-bandit feedback G Neu, G Bartók International Conference on Algorithmic Learning Theory, 234-248, 2013 | 65 | 2013 |
| TF-Agents: A library for reinforcement learning in tensorflow S Guadarrama, A Korattikara, O Ramirez, P Castro, E Holly, S Fishman, ... GitHub repository, 2018 | 48 | 2018 |
| Minimax regret of finite partial-monitoring games in stochastic environments G Bartók, D Pál, C Szepesvári Proceedings of the 24th Annual Conference on Learning Theory, 133-154, 2011 | 48 | 2011 |
| An adaptive algorithm for finite stochastic partial monitoring G Bartók, N Zolghadr, C Szepesvári arXiv preprint arXiv:1206.6487, 2012 | 42 | 2012 |
| Partial monitoring with side information G Bartók, C Szepesvári International Conference on Algorithmic Learning Theory, 305-319, 2012 | 28 | 2012 |
| Toward a classification of finite partial-monitoring games A Antos, G Bartók, D Pál, C Szepesvári Theoretical Computer Science 473, 77-99, 2013 | 25 | 2013 |
| Importance weighting without importance weights: An efficient algorithm for combinatorial semi-bandits G Neu, B Gábor Microtome Publishing, 2016 | 23 | 2016 |
| On actively teaching the crowd to classify A Singla, I Bogunovic, G Bartók, A Karbasi, A Krause NIPS Workshop on Data Driven Education, 2013 | 22 | 2013 |
| A near-optimal algorithm for finite partial-monitoring games against adversarial opponents G Bartók Conference on Learning Theory, 696-710, 2013 | 20 | 2013 |
| Toward a classification of finite partial-monitoring games G Bartók, D Pál, C Szepesvári International Conference on Algorithmic Learning Theory, 224-238, 2010 | 20 | 2010 |
| Efficient Partial Monitoring with Prior Information. HP Vanchinathan, G Bartók, A Krause NIPS, 1691-1699, 2014 | 13 | 2014 |
| The role of information in online learning G Bartók | 8 | 2012 |
| Fast task-aware architecture inference E Kokiopoulou, A Hauth, L Sbaiz, A Gesmundo, G Bartok, J Berent arXiv preprint arXiv:1902.05781, 2019 | 6 | 2019 |
| Gumbel-matrix routing for flexible multi-task learning K Maziarz, E Kokiopoulou, A Gesmundo, L Sbaiz, G Bartok, J Berent | 3 | 2019 |
| Models of active learning in group-structured state spaces G Bartók, C Szepesvári, S Zilles Information and Computation 208 (4), 364-384, 2010 | 3 | 2010 |
| Ranking architectures using meta-learning A Dubatovka, E Kokiopoulou, L Sbaiz, A Gesmundo, G Bartok, J Berent arXiv preprint arXiv:1911.11481, 2019 | 1 | 2019 |
| Non-trivial two-armed partial-monitoring games are bandits A Antos, G Bartók, C Szepesvári arXiv preprint arXiv:1108.4961, 2011 | 1 | 2011 |
Csaba SzepesvariDeepMind & Department of Computing Science, University of AlbertaVerified email at cs.ualberta.ca
