| Explore first, exploit next: The true shape of regret in bandit problems A Garivier, P Ménard, G Stoltz Mathematics of Operations Research 44 (2), 377-399, 2019 | 151 | 2019 |
| Episodic Reinforcement Learning in Finite MDPs: Minimax Lower Bounds Revisited O Darwiche Domingues, P Ménard, E Kaufmann, M Valko arXiv e-prints, arXiv: 2010.03531, 2020 | 60* | 2020 |
| Non-asymptotic pure exploration by solving games R Degenne, WM Koolen, P Ménard Advances in Neural Information Processing Systems 32, 2019 | 55 | 2019 |
| Adaptive reward-free exploration E Kaufmann, P Ménard, OD Domingues, A Jonsson, E Leurent, M Valko Algorithmic Learning Theory, 865-891, 2021 | 45 | 2021 |
| Gamification of pure exploration for linear bandits R Degenne, P Ménard, X Shang, M Valko International Conference on Machine Learning, 2432-2442, 2020 | 45 | 2020 |
| A minimax and asymptotically optimal algorithm for stochastic bandits P Ménard, A Garivier International Conference on Algorithmic Learning Theory, 223-237, 2017 | 44 | 2017 |
| Fixed-confidence guarantees for Bayesian best-arm identification X Shang, R Heide, P Menard, E Kaufmann, M Valko International Conference on Artificial Intelligence and Statistics, 1823-1832, 2020 | 35 | 2020 |
| KL-UCB-switch: optimal regret bounds for stochastic bandits from both a distribution-dependent and a distribution-free viewpoints A Garivier, H Hadiji, P Menard, G Stoltz | 35 | 2018 |
| Kernel-based reinforcement learning: A finite-time analysis OD Domingues, P Ménard, M Pirotta, E Kaufmann, M Valko International Conference on Machine Learning, 2783-2792, 2021 | 25* | 2021 |
| A Kernel-Based Approach to Non-Stationary Reinforcement Learning in Metric Spaces O Darwiche Domingues, P Ménard, M Pirotta, E Kaufmann, M Valko arXiv e-prints, arXiv: 2007.05078, 2020 | 23* | 2020 |
| Fano’s inequality for random variables S Gerchinovitz, P Ménard, G Stoltz | 23 | 2020 |
| UCB Momentum Q-learning: Correcting the bias without forgetting P Ménard, OD Domingues, X Shang, M Valko International Conference on Machine Learning, 7609-7618, 2021 | 22 | 2021 |
| Fast active learning for pure exploration in reinforcement learning P Ménard, OD Domingues, A Jonsson, E Kaufmann, E Leurent, M Valko International Conference on Machine Learning, 7599-7608, 2021 | 22 | 2021 |
| Thresholding bandit for dose-ranging: The impact of monotonicity A Garivier, P Ménard, L Rossi, P Menard arXiv preprint arXiv:1711.04454, 2017 | 22 | 2017 |
| Fast active learning for pure exploration in reinforcement learning P Ménard, OD Domingues, A Jonsson, E Kaufmann, E Leurent, M Valko arXiv preprint arXiv:2007.13442, 2020 | 19 | 2020 |
| Planning in markov decision processes with gap-dependent sample complexity A Jonsson, E Kaufmann, P Ménard, O Darwiche Domingues, E Leurent, ... Advances in Neural Information Processing Systems 33, 1253-1263, 2020 | 19 | 2020 |
| Planning in entropy-regularized Markov decision processes and games JB Grill, O Darwiche Domingues, P Ménard, R Munos, M Valko Advances in Neural Information Processing Systems 32, 2019 | 15 | 2019 |
| Model-free learning for two-player zero-sum partially observable markov games with perfect recall T Kozuno, P Ménard, R Munos, M Valko arXiv preprint arXiv:2106.06279, 2021 | 14* | 2021 |
| A single algorithm for both restless and rested rotting bandits J Seznec, P Menard, A Lazaric, M Valko International Conference on Artificial Intelligence and Statistics, 3784-3794, 2020 | 14 | 2020 |
| Gradient ascent for active exploration in bandit problems P Ménard arXiv preprint arXiv:1905.08165, 2019 | 12 | 2019 |
Michal ValkoDeepMind Paris & Inria France & ENS MVAVerified email at deepmind.com
