Gabriele Farina

I am interested in solid theoretical and algorithmic foundations for learning and computational decision-making under imperfect information. To achieve that, I combine and advance techniques and notions of strategicness from game theory together with modern tools from machine learning, optimization, and statistics.

I am an Assistant Professor at MIT in EECS and LIDS, additionally affiliated with the Operations Research Center (ORC). I hold the X-Window Consortium Career Development Chair. Before that, I spent a year as a Research Scientist at FAIR (Meta AI), where I worked on Cicero, a human-level AI agent combining strategic reasoning and natural language. Before that, I was a Ph.D. student in the Computer Science Department at Carnegie Mellon University, where I worked with Tuomas Sandholm. I was supported by a 2019-2020 Facebook Fellowship in the area of Economics and Computation.

Curriculum Vitae Publications Teaching

Some current research interests

➊ No-Regret Learning Dynamics

No-regret learning dynamics for games are a fascinating theoretical problem ("can local learning result in global game-theoretic equilibrium?"), as well as currently the most practically scalable technique we know for training strong agents in large games.

Publications on this topic: [ = most representative]

ICLR 2024 (to appear)	The Update Equivalence Framework for Decision-Time Planning Samuel Sokota, Gabriele Farina, David J. Wu, Hengyuan Hu, Kevin A. Wang, J. Zico Kolter, Noam Brown
AAAI 2024 pdf	Efficient Online Learning on Polytopes with Linear Minimization Oracles Darshan Chakrabarti, Gabriele Farina, Christian Kroer
AAAI 2024 pdf	Optimistic Policy Gradient in Multi-Player Markov Games with a Single Controller: Convergence Beyond the Minty Property Ioannis Anagnostides, Ioannis Panageas, Gabriele Farina, Tuomas Sandholm
NeurIPS 2023 pdf	Polynomial-Time Linear-Swap Regret Minimization in Imperfect-Information Sequential Games [] Gabriele Farina, Charilaos Pipis
NeurIPS 2023 pdf	Regret Matching$^+$: (In)Stability and Fast Convergence in Games Gabriele Farina, Julien Grand-Clément, Christian Kroer, Chung-Wei Lee, Haipeng Luo Spotlight paper
NeurIPS 2023 pdf	On the Convergence of No-Regret Learning Dynamics in Time-Varying Games Ioannis Anagnostides, Ioannis Panageas, Gabriele Farina, Tuomas Sandholm
ICML 2023 pdf	Near-Optimal $\Phi$-Regret Learning in Extensive-Form Games Ioannis Anagnostides, Gabriele Farina, Tuomas Sandholm
ICLR 2023 pdf	Meta-Learning in Games Keegan Harris, Ioannis Anagnostides, Gabriele Farina, Mikhail Khodak, Steven Wu, Tuomas Sandholm
ICLR 2023 pdf	ESCHER: Eschewing Importance Sampling in Games by Computing a History Value Function to Estimate Regret Stephen McAleer, Gabriele Farina, Marc Lanctot, Tuomas Sandholm
J. ACM 2022 pdf	Simple Uncoupled No-regret Learning Dynamics for Extensive-form Correlated Equilibrium [] Gabriele Farina, Andrea Celli, Alberto Marchesi, Nicola Gatti
Science 2022 link	Human-level play in the game of Diplomacy by combining language models with strategic reasoning [] Meta Fundamental AI Research Diplomacy Team (FAIR)
NeurIPS 2022 pdf	Near-Optimal No-Regret Learning Dynamics for General Convex Games [] Gabriele Farina, Ioannis Anagnostides, Haipeng Luo, Chung-Wei Lee, Christian Kroer, Tuomas Sandholm
NeurIPS 2022 pdf	Uncoupled Learning Dynamics with $O(\log T)$ Swap Regret in Multiplayer Games Ioannis Anagnostides, Gabriele Farina, Christian Kroer, Chung-Wei Lee, Haipeng Luo, Tuomas Sandholm Oral presentation
ICML 2022 pdf	Kernelized Multiplicative Weights for 0/1-Polyhedral Games: Bridging the Gap Between Learning in Extensive-Form and Normal-Form Games [] Gabriele Farina, Chung-Wei Lee, Haipeng Luo, Christian Kroer
ICML 2022 pdf	On Last-Iterate Convergence Beyond Zero-Sum Games Ioannis Anagnostides, Ioannis Panageas, Gabriele Farina, Tuomas Sandholm
STOC 2022 pdf	Near-Optimal No-Regret Learning for Correlated Equilibria in Multi-Player General-Sum Games Ioannis Anagnostides, Constantinos Daskalakis, Gabriele Farina, Maxwell Fishelson, Noah Golowich, Tuomas Sandholm
AAAI 2022 pdf	Fast Payoff Matrix Sparsification Techniques for Structured Extensive-Form Games Gabriele Farina, Tuomas Sandholm
EC 2021 pdf	Better Regularization for Sequential Decision Spaces: Fast Convergence Rates for Nash, Correlated, and Team Equilibria Gabriele Farina, Christian Kroer, Tuomas Sandholm
AAAI 2021 pdf	Faster Game Solving via Predictive Blackwell Approachability: Connecting Regret Matching and Mirror Descent [] Gabriele Farina, Christian Kroer, Tuomas Sandholm
AAAI 2021 pdf	Model-Free Online Learning in Unknown Sequential Decision Making Problems and Games Gabriele Farina, Tuomas Sandholm
AAAI 2021 pdf	Bandit Linear Optimization for Sequential Decision Making and Extensive-Form Games Gabriele Farina, Robin Schmucker, Tuomas Sandholm
ICML 2020 pdf	Stochastic Regret Minimization in Extensive-Form Games Gabriele Farina, Christian Kroer, Tuomas Sandholm
NeurIPS 2019 pdf	Optimistic Regret Minimization for Extensive-Form Games via Dilated Distance-Generating Functions Gabriele Farina, Christian Kroer, Tuomas Sandholm
ICML 2019 pdf	Regret Circuits: Composability of Regret Minimizers [] Gabriele Farina, Christian Kroer, Tuomas Sandholm Long presentation
ICML 2019 pdf	Stable-Predictive Optimistic Counterfactual Regret Minimization Gabriele Farina, Christian Kroer, Noam Brown, Tuomas Sandholm
AAAI 2019 pdf	Online Convex Optimization for Sequential Decision Processes and Extensive-Form Games Gabriele Farina, Christian Kroer, Tuomas Sandholm
NeurIPS 2018 pdf	Solving Large Sequential Games with the Excessive Gap Technique Christian Kroer, Gabriele Farina, Tuomas Sandholm Spotlight paper

➋ Correlation and Mediated Equilibria

Most of the literature on strategic decision-making so far has focused on the task of computing optimal strategies for individual agents that seek to maximize their own utility. On the other hand, many realistic interactions require studying correlated strategies. The study of the geometric and analytical properties of correlated strategies in extensive-form strategic interactions is a fundamental question with applications to diverse settings, and is yet to be fully explored.

Publications on this topic: [ = most representative]

ICLR 2024 (to appear)	Mediator Interpretation and Faster Learning Algorithms for Linear Correlated Equilibria in General Sequential Games Brian H. Zhang, Gabriele Farina, Tuomas Sandholm
NeurIPS 2023 pdf	Computing Optimal Equilibria and Mechanisms via Learning in Zero-Sum Extensive-Form Games Brian H. Zhang, Gabriele Farina, Ioannis Anagnostides, Federico Cacciamani, Stephen McAleer, Andreas Alexander Haupt, Andrea Celli, Nicola Gatti, Vincent Conitzer, Tuomas Sandholm
J. ACM 2022 pdf	Simple Uncoupled No-regret Learning Dynamics for Extensive-form Correlated Equilibrium [] Gabriele Farina, Andrea Celli, Alberto Marchesi, Nicola Gatti
NeurIPS 2022 pdf	Optimistic Mirror Descent Either Converges to Nash or to Strong Coarse Correlated Equilibria in Bimatrix Games [] Ioannis Anagnostides, Gabriele Farina, Ioannis Panageas, Tuomas Sandholm
EC 2022 pdf	Optimal Correlated Equilibria in General-Sum Extensive-Form Games: Fixed-Parameter Algorithms, Hardness, and Two-Sided Column-Generation [] Brian H. Zhang, Gabriele Farina, Andrea Celli, Tuomas Sandholm
EC 2022 pdf	Faster No-Regret Learning Dynamics for Extensive-Form Correlated and Coarse Correlated Equilibrium Ioannis Anagnostides, Gabriele Farina, Christian Kroer, Andrea Celli, Tuomas Sandholm
STOC 2022 pdf	Near-Optimal No-Regret Learning for Correlated Equilibria in Multi-Player General-Sum Games Ioannis Anagnostides, Constantinos Daskalakis, Gabriele Farina, Maxwell Fishelson, Noah Golowich, Tuomas Sandholm
NeurIPS 2020 pdf	No-Regret Learning Dynamics for Extensive-Form Correlated Equilibrium [] Andrea Celli, Alberto Marchesi, Gabriele Farina, Nicola Gatti Best paper award*
NeurIPS 2020 pdf	Polynomial-Time Computation of Optimal Correlated Equilibria in Two-Player Extensive-Form Games with Public Chance Moves and Beyond [] Gabriele Farina, Tuomas Sandholm
AAAI 2020 pdf	Coarse Correlation in Extensive-Form Games Gabriele Farina, Tommaso Bianchi, Tuomas Sandholm
NeurIPS 2019 pdf	Correlation in Extensive-Form Games: Saddle-Point Formulation and Benchmarks Gabriele Farina, Chun Kai Ling, Fei Fang, Tuomas Sandholm

➌ Team Games and Team Equilibria

Publications on this topic: [ = most representative]

NeurIPS 2023 pdf	Team-PSRO for Learning Approximate TMECor in Large Team Games via Cooperative Reinforcement Learning Stephen McAleer, Gabriele Farina, Gaoyue Zhou, Mingzhi Wang, Yaodong Yang, Tuomas Sandholm
ICML 2023 pdf	Team Belief DAG: Generalizing the Sequence Form to Team Games for Fast Computation of Correlated Team Max-Min Equilibria via Regret Minimization [] Brian H. Zhang, Gabriele Farina, Tuomas Sandholm
NeurIPS 2022 pdf	Subgame Solving in Adversarial Team Games Brian H. Zhang, Luca Carminati, Federico Cacciamani, Gabriele Farina, Pierriccardo Olivieri, Nicola Gatti, Tuomas Sandholm
ICML 2021 pdf	Connecting Optimal Ex-Ante Collusion in Teams to Extensive-Form Correlation: Faster Algorithms and Positive Complexity Results [] Gabriele Farina, Andrea Celli, Nicola Gatti, Tuomas Sandholm
NeurIPS 2018 pdf	Ex Ante Coordination and Collusion in Zero-Sum Multi-Player Extensive-Form Games [] Gabriele Farina, Andrea Celli, Nicola Gatti, Tuomas Sandholm

➍ Human Modeling, Robustness to Mistakes, and Equilibrium Perfection

Nash equilibrium is the most seminal solution concept in game theory. However, in some strategic interaction it is too restrictive, assuming that the agents have unlimited computational power to come up with the optimal solution to the interactions. On the other hand, in other strategic interactions it is too permissive, prescribing unsatisfactory strategies. For example, in the case of multi-step interactions, one limitation is that some Nash equilibria do not prescribe optimal play after the player or the opponent has made a mistake (sequential irrationality). Resolving these issues is important to develop algorithms that are ready to operate in the real world.

Publications on this topic: [ = most representative]

ICLR 2024 (to appear)	The Consensus Game: Language Model Generation via Equilibrium Search Athul Paul Jacob, Yikang Shen, Gabriele Farina, Jacob Andreas Spotlight paper
ICLR 2023 pdf	Mastering the Game of No-Press Diplomacy via Human-Regularized Reinforcement Learning and Planning [] Anton Bakhtin, David J. Wu, Adam Lerer, Jonathan Gray, Athul Paul Jacob, Gabriele Farina, Alexander H. Miller, Noam Brown Outstanding Paper Honorable Mention Selected as “Notable-top-5%”
Science 2022 link	Human-level play in the game of Diplomacy by combining language models with strategic reasoning [] Meta Fundamental AI Research Diplomacy Team (FAIR)
ICML 2022 pdf	Modeling Strong and Human-Like Gameplay with KL-Regularized Search [] Athul Paul Jacob, David J. Wu, Gabriele Farina*, Adam Lerer, Hengyuan Hu, Anton Bakhtin, Jacob Andreas, Noam Brown
NeurIPS 2021 pdf	Equilibrium Refinement for the Age of Machines: The One-Sided Quasi-Perfect Equilibrium [] Gabriele Farina, Tuomas Sandholm
AAAI 2019 pdf	Quasi-Perfect Stackelberg Equilibrium Alberto Marchesi, Gabriele Farina, Christian Kroer, Nicola Gatti, Tuomas Sandholm
NeurIPS 2018 pdf	Practical Exact Algorithm for Trembling-Hand Equilibrium Refinements in Games [] Gabriele Farina, Nicola Gatti, Tuomas Sandholm
IJCAI 2018 pdf	Trembling-Hand Perfection in Extensive-Form Games with Commitment Gabriele Farina, Alberto Marchesi, Christian Kroer, Nicola Gatti, Tuomas Sandholm
AAAI 2018 pdf	Robust Stackelberg Equilibria in Extensive-Form Games and Extension to Limited Lookahead Christian Kroer, Gabriele Farina, Tuomas Sandholm
ICML 2017 pdf	Regret Minimization in Behaviorally-Constrained Zero-Sum Games Gabriele Farina, Christian Kroer, Tuomas Sandholm
IJCAI 2017 pdf	Smoothing Method for Approximate Extensive-Form Perfect Equilibrium Christian Kroer, Gabriele Farina, Tuomas Sandholm
AAAI 2017 pdf	Extensive-Form Perfect Equilibrium Computation in Two-Player Games [] Gabriele Farina, Nicola Gatti