Get started
Author

Luca Viano

Optimistically Optimistic Exploration for Provably Efficient Infinite-Horizon Reinforcement and Imitation Learning
2025 · Moulin, Antoine, Neu, Gergely, et al. · arXiv (Cornell University) · 10
PDF
Robust Learning from Observation with Model Misspecification
2022 · Luca Viano, Yu-Ting Huang, et al. · Adaptive Agents and Multi-Agents Systems · 9
PDF
Robust Inverse Reinforcement Learning under Transition Dynamics Mismatch
2020 · Viano, Luca, Huang, Yu-Ting, et al. · arXiv (Cornell University) · 8
PDF
Multi-Step Alignment as Markov Games: An Optimistic Online Gradient Descent Approach with Convergence Guarantees
2025 · Wu, Yongtao, Viano, Luca, et al. · arXiv (Cornell University) · 7
PDF
Polynomial Convergence of Bandit No-Regret Dynamics in Congestion Games
2024 · Dadi, Leello, Panageas, Ioannis, et al. · arXiv (Cornell University) · 6
PDF
Identifiability and generalizability from multiple experts in Inverse Reinforcement Learning
2022 · Rolland, Paul, Viano, Luca, et al. · arXiv (Cornell University) · 5
PDF
Inverse Q-Learning Done Right: Offline Imitation Learning in $Q^\pi$-Realizable MDPs
2025 · Antoine Moulin, Gergely Neu, et al. · neural information processing systems · 4
PDF
Proximal Point Imitation Learning
2022 · Luca Viano, Angeliki Kamoutsi, et al. · neural information processing systems · 4
PDF
Understanding Deep Neural Function Approximation in Reinforcement Learning Via e-Greedy Exploration
2022 · Fanghui Liu, Luca Viano, et al. · neural information processing systems · 4
Aligning Large Language Models With Human Feedback: Mathematical foundations and algorithm design [Special Issue on the Mathematics of Deep Learning]
2026 · Siliang Zeng, Luca Viano, et al. · IEEE Signal Processing Magazine · 3
PDF
Best of Both Worlds: Regret Minimization versus Minimax Play
2025 · Müller, Adrian, Schneider, Jon, et al. · arXiv (Cornell University) · 3
PDF
Understanding Deep Neural Function Approximation in Reinforcement Learning via $ε$-Greedy Exploration
2022 · Liu, Fanghui, Viano, Luca, et al. · arXiv (Cornell University) · 3
PDF
When Does On-Policy Interaction Help? Representational Tradeoffs in Value-Based Imitation Learning
2026 · Viano, Luca, Moulin, Antoine, et al. · arXiv (Cornell University) · 2
PDF
Rate optimal learning of equilibria from data
2025 · Freihaut, Till, Viano, Luca, et al. · arXiv (Cornell University) · 2
PDF
IL-SOAR : Imitation Learning with Soft Optimistic Actor cRitic
2025 · Viel, Stefano, Viano, Luca, et al. · arXiv (Cornell University) · 2
PDF
Multi-agent imitation learning with function approximation: Linear Markov games and beyond
2026 · Viano, Luca, Freihaut, Till, et al. · arXiv (Cornell University) · 1
PDF
Beyond Binary Preferences: A Principled Framework for Reward Modeling with Ordinal Feedback
2026 · Afsharrad, Amirhossein, Zhou, Ruida, et al. · arXiv (Cornell University) · 1
PDF
Direct Preference Optimization with Rating Information: Practical Algorithms and Provable Gains
2026 · Viano, Luca, Zhou, Ruida, et al. · arXiv (Cornell University) · 1
PDF
What can online reinforcement learning with function approximation benefit from general coverage conditions?
2023 · Liu, Fanghui, Viano, Luca, et al. · arXiv (Cornell University) · 1
PDF
Alternation makes the adversary weaker in two-player games
2023 · Volkan Cevher, Ashok Cutkosky, et al. · neural information processing systems · 1
PDF
Identifiability and Generalizability from Multiple Experts in Inverse Reinforcement Learning
2022 · Paul Rolland, Luca Viano, et al. · SSRN Electronic Journal · 1
Best of Both Worlds:Regret Minimization versus Minimax Play
2026 · Skoulakis, Stratis, Muller, Adrian, et al.
Split the Differences, Pool the Rest: Provably Efficient Multi-Objective Imitation
2026 · Sheebaelhamd, Ziyad, Viano, Luca, et al. · arXiv (Cornell University)
PDF
Provably avoiding over-optimization in Direct Preference Optimization without knowing the data distribution
2026 · Barla, Adam, Nevali, Emanuele, et al. · arXiv (Cornell University)
PDF
Convergence to Equilibrium of No-Regret Dynamics in Congestion Games
2026 · Volkan Cevher, Wei Chen, et al. · Lecture notes in computer science
Works count: 38
Citation count: 92
H-index: 6
I10-index: 1
Year
Topic
Type