| Robust Inverse Reinforcement Learning under Transition Dynamics Mismatch L Viano, YT Huang, P Kamalaruban, A Weller, V Cevher Neural Information and Processing Systems 35, 2021 | 45 | 2021 |
| A natural actor-critic framework for zero-sum Markov games A Alacaoglu, L Viano, N He, V Cevher International Conference on Machine Learning, 307-366, 2022 | 38 | 2022 |
| Understanding Deep Neural Function Approximation in Reinforcement Learning via -Greedy Exploration F Liu, L Viano, V Cevher Neural Information and Processing Systems 36, 2022 | 28 | 2022 |
| Proximal Point Imitation Learning L Viano, A Kamoutsi, G Neu, I Krawczuk, V Cevher Neural Information and Processing Systems 36, 2022 | 25 | 2022 |
| Identifiability and generalizability from multiple experts in Inverse Reinforcement Learning P Rolland, L Viano, N Schürhoff, B Nikolov, V Cevher Neural Information and Processing Systems 36, 2022 | 24 | 2022 |
| Semi Bandit dynamics in Congestion Games: Convergence to Nash Equilibrium and No-Regret Guarantees. I Panageas, S Skoulakis, L Viano, X Wang, V Cevher ICML, 2023, 2023 | 12 | 2023 |
| Robust Learning from Observation with Model Misspecification L Viano, YT Huang, P Kamalaruban, C Innes, S Ramamoorthy, A Weller AAMAS 2022, 2022 | 12 | 2022 |
| Imitation learning in discounted linear mdps without exploration assumptions L Viano, S Skoulakis, V Cevher arXiv preprint arXiv:2405.02181, 2024 | 9 | 2024 |
| Alternation makes the adversary weaker in two-player games V Cevher, A Cutkosky, A Kavis, G Piliouras, S Skoulakis, L Viano Advances in Neural Information Processing Systems 36, 18263-18290, 2023 | 8 | 2023 |
| Optimistically optimistic exploration for provably efficient infinite-horizon reinforcement and imitation learning A Moulin, G Neu, L Viano arXiv preprint arXiv:2502.13900, 2025 | 7 | 2025 |
| Multi-step alignment as markov games: An optimistic online gradient descent approach with convergence guarantees Y Wu, L Viano, Y Chen, Z Zhu, K Antonakopoulos, Q Gu, V Cevher arXiv preprint arXiv:2502.12678, 2025 | 6 | 2025 |
| Polynomial convergence of bandit no-regret dynamics in congestion games L Dadi, I Panageas, S Skoulakis, L Viano, V Cevher arXiv preprint arXiv:2401.09628, 2024 | 5 | 2024 |
| Provable benefits of general coverage conditions in efficient online RL with function approximation F Liu, L Viano, V Cevher ICML, 2023, 2023 | 3 | 2023 |
| Adaptive bilevel optimization K Antonakopoulos, S Sabach, L Viano, M Hong, V Cevher ACM/IMS Journal of Data Science 2 (2), 1-29, 2025 | 1 | 2025 |
| Aligning Large Language Models with Human Feedback: Mathematical Foundations and Algorithm Design S Zeng, L Viano, C Li, J Li, V Cevher, M Wulfmeier, S Ermon, A Garcia, ... Authorea Preprints, 2025 | 1 | 2025 |
| Il-soar: Imitation learning with soft optimistic actor critic S Viel, L Viano, V Cevher arXiv preprint arXiv:2502.19859, 2025 | 1 | 2025 |
| Best of Both Worlds: Regret Minimization versus Minimax Play S Skoulakis, A Muller, L Viano, V Cevher, J Scheider | | 2026 |
| Rate optimal learning of equilibria from data T Freihaut, L Viano, E Nevali, V Cevher, M Geist, G Ramponi arXiv preprint arXiv:2510.09325, 2025 | | 2025 |
| Inverse Q-Learning Done Right: Offline Imitation Learning in -Realizable MDPs A Moulin, G Neu, L Viano arXiv preprint arXiv:2505.19946, 2025 | | 2025 |
| Learning Equilibria from Data: Provably Efficient Multi-Agent Imitation Learning T Freihaut, L Viano, V Cevher, M Geist, G Ramponi arXiv preprint arXiv:2505.17610, 2025 | | 2025 |
Volkan CevherAssociate Professor, LIONS, EPFL. Amazon Scholar (AGI Foundations).Verified email at epfl.ch
