Profiles2023-2026
Gabriele Farina
Massachusetts Institute of Technology
21Papers
5Last author
26Unique co-authors
2First author
1Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers21
- Reevaluating Policy Gradient Methods for Imperfect-Information GamesAuthor 7 of 9ICLR 2026 · 17 citations
- Computing Equilibrium beyond Unilateral DeviationAuthor 2 of 3ICLR 2026 · 1 citation
- Differentially Private Equilibrium Finding in Polymatrix GamesAuthor 2 of 3ICLR 2026 · 1 citation
- UFT: Unifying Supervised and Reinforcement Fine-TuningAuthor 2 of 3NeurIPS 2025 · 61 citations
- Efficient Learning and Computation of Linear Correlated Equilibrium in General Convex GamesAuthor 2 of 4STOC 2025 · 14 citations
- On the Universal Near Optimality of Hedge in Combinatorial SettingsAuthor 6 of 6NeurIPS 2025 · 2 citations
- Policy Gradient Methods Converge Globally in Imperfect-Information Extensive-Form GamesAuthor 2 of 2NeurIPS 2025 · 2 citations
- The Complexity of Correlated Equilibria in Generalized GamesAuthor 4 of 4NeurIPS 2025 · 2 citations
- Faster Rates for No-Regret Learning in General Games via Cautious OptimismAuthor 3 of 3STOC 2025 · 1 citation
- A Policy-Gradient Approach to Solving Imperfect-Information Games with Best-Iterate ConvergenceAuthor 2 of 3ICLR 2025
- Last-Iterate Convergence Properties of Regret-Matching Algorithms in GamesAuthor 2 of 6ICLR 2025
- Fast Last-Iterate Convergence of Learning in Games Requires Forgetful AlgorithmsAuthor 2 of 6NeurIPS 2024 · 24 citations
- Polynomial-Time Computation of Exact -Equilibria in Polyhedral GamesAuthor 1 of 1NeurIPS 2024 · 9 citations
- Efficient -Regret Minimization with Low-Degree Swap Deviations in Extensive-Form GamesAuthor 3 of 5NeurIPS 2024 · 7 citations
- The Update-Equivalence Framework for Decision-Time PlanningAuthor 2 of 7ICLR 2024 · 5 citations
- Efficient Learning in Polyhedral Games via Best-Response OraclesAuthor 2 of 3AAAI 2024 · 4 citations
- On the Optimality of Dilated Entropy and Lower Bounds for Online Learning in Extensive-Form GamesAuthor 3 of 3NeurIPS 2024 · 3 citations
- Optimistic Policy Gradient in Multi-Player Markov Games with a Single Controller: Convergence beyond the Minty PropertyAuthor 3 of 4AAAI 2024 · 3 citations
- Mediator Interpretation and Faster Learning Algorithms for Linear Correlated Equilibria in General Sequential GamesAuthor 2 of 3ICLR 2024 · 2 citations
- Computing Optimal Equilibria and Mechanisms via Learning in Zero-Sum Extensive-Form GamesAuthor 2 of 13NeurIPS 2023 · 17 citations
- Polynomial-Time Linear-Swap Regret Minimization in Imperfect-Information Sequential GamesAuthor 1 of 2NeurIPS 2023 · 13 citations
