| Learning Value Functions in Deep Policy Gradients using Residual Variance Y Flet-Berliac, R Ouhamma, OA Maillard, P Preux ICLR 2021-International Conference on Learning Representations, 2021 | 21 | 2021 |
| Stochastic online linear regression: the forward algorithm to replace ridge R Ouhamma, OA Maillard, V Perchet Advances in Neural Information Processing Systems 34, 24430-24441, 2021 | 13 | 2021 |
| Bilinear exponential family of MDPs: frequentist regret bound with tractable exploration & planning R Ouhamma, D Basu, O Maillard Proceedings of the AAAI Conference on Artificial Intelligence 37 (8), 9336-9344, 2023 | 11 | 2023 |
| Online Sign Identification: Minimization of the Number of Errors in Thresholding Bandits R Ouhamma, R Degenne, V Perchet, P Gaillard Advances in Neural Information Processing Systems 34, 2021 | 3 | 2021 |
| Learning Nash Equilibria in Zero-Sum Markov Games: A Single Time-scale Algorithm Under Weak Reachability R Ouhamma, M Kamgarpour arXiv preprint arXiv:2312.08008, 2023 | 1 | 2023 |
| Finite-time convergence to an -efficient Nash equilibrium in potential games A Maddux, R Ouhamma, M Kamgarpour arXiv preprint arXiv:2405.15497, 2024 | | 2024 |
| Toward realistic reinforcement learning R Ouhamma Université de Lille, 2023 | | 2023 |
| Group ID U14171 M Erkul, M Kamgarpour, AM Maddux, T Ni, R Ouhamma, K Ren, ... | | |
Odalric-Ambrym MaillardInria Lille - Nord EuropeVerified email at inria.fr
