Embedded Files
2025
Optimistically Optimistic Exploration for Provably Efficient Infinite-Horizon Reinforcement and Imitation Learning.
COLT 2025 paper
A. Moulin, G. Neu, L. Viano
IL-SOAR : Imitation Learning with Soft Optimistic Actor cRitic
ICML 2025 paper
Stefano Viel*, Luca Viano*, Volkan Cevher
Best of Both Worlds: Regret Minimization versus Minimax Play
ICML 2025 paper
Adrian Mueller*, Jon Schneider*, Stratis Skoulakis*, Luca Viano*, Volkan Cevher
Multi-Step Alignment as Markov Games: An Optimistic Online Gradient Descent Approach with Convergence Guarantees.
Yongtao Wu*, Luca Viano*, Yihang Chen, Zhenyu Zhu, Kimon Antonakopoulos, Quanquan Gu, Volkan Cevher
Adaptive Bilevel Optimization
ACM Journal of Data Science
K. Antonakopolous, S. Sabach, L. Viano, M. Hong, V. Cevher
2024
Polynomial Convergence of Bandit No-Regret Dynamics in Congestion Games.
WINE 2024 paper ( merged with https://arxiv.org/abs/2306.13673 )
L. Dadi*, I. Panageas*, S. Skoulakis*, L. Viano*, V. Cevher
Imitation Learning in Discounted Linear MDP without exploration assumptions.
ICML 2024 paper
L. Viano, S. Skoulakis, V. Cevher
2023
Alternation makes the adversary weaker in two players game.
NeurIPS 2023 (Spotlight) [paper]
V. Cevher, A. Cutkosky, A.Kavis, G. Piliouras, S. Skoulakis, L. Viano
Semi-Bandit Dynamics in Congestion Games: Convergence to Nash Equilibrium and No Regret guarantees.
ICML 2023 (Oral) [paper]
I. Panageas*, S. Skoulakis*, L. Viano*, X. Wang, V. Cevher
What can online reinforcement learning with function approximation benefit from general coverage conditions?
What can online reinforcement learning with function approximation benefit from general coverage conditions?
ICML 2023 [paper]
F. Liu, L. Viano, V. Cevher
2022
Proximal Point Imitation Learning
NeurIPS 2022 [paper]
L. Viano, A.Kamoutsi, G. Neu, I. Krawczuk, V. Cevher
Identifiability and Generalizability from multiple experts in Inverse Reinforcement Learning
NeurIPS 2022 [paper]
P. Rolland, L. Viano, Norman Schuerhoff, Boris Nikolov, V. Cevher
Understanding Deep Neural Function Approximation in Reinforcement Learning via epsilon-Greedy Exploration
NeurIPS 2022 [paper]
F. Liu, L. Viano, V. Cevher
A Natural Actor-Critic Framework for Zero-Sum Markov Games
ICML 2022 [paper]
A. Alacaoglu, L. Viano, N.He, V.Cevher
Robust Learning from Observation under Model Misspecification
AAMAS 2022 [paper]
L. Viano, Y.T. Huang, P. Kamalaruban, Craig Innes, S. Ramamoorthy, A. Weller
2021
Robust Inverse Reinforcement Learning under Transition Dynamics Mismatch
Advances in Neural Information Processing Systems 2021 [paper]
L. Viano, Y.T. Huang, P. Kamalaruban, A. Weller, V. Cevher
Neural NID Rules
Physical Reasoning and Inductive Biases for the Real World at NeurIPS 2021 [paper]
L. Viano, J. Brea
Page updated
Google Sites
Report abuse