| An algorithm for stochastic and adversarial bandits with switching costs C Rouyer, Y Seldin, N Cesa-Bianchi International Conference on Machine Learning, 9127-9135, 2021 | 34 | 2021 |
| A near-optimal best-of-both-worlds algorithm for online learning with feedback graphs C Rouyer, D van der Hoeven, N Cesa-Bianchi, Y Seldin Advances in Neural Information Processing Systems 35, 35035-35048, 2022 | 30 | 2022 |
| Tsallis-inf for decoupled exploration and exploitation in multi-armed bandits C Rouyer, Y Seldin Conference on Learning Theory, 3227-3249, 2020 | 24 | 2020 |
| No-regret online reinforcement learning with adversarial losses and transitions T Jin, J Liu, C Rouyer, W Chang, CY Wei, H Luo Advances in Neural Information Processing Systems 36, 38520-38585, 2023 | 20 | 2023 |
| Understanding the Gaps in Satisficing Bandits C Rouyer, R Ortner, P Auer Seventeenth European Workshop on Reinforcement Learning, 2024 | | 2024 |
| Theoretical Foundations of Learning with Worst-Case and Easy Data C Rouyer DEPARTMENT OF COMPUTER SCIENCE Ph. D. Thesis Chloé Rouyer Theoretical …, 2022 | | 2022 |
Yevgeny SeldinProfessor, Department of Computer Science, University of CopenhagenVerified email at di.ku.dk
