Gabriele Farina

发表

Counterfactual-Free Regret Minimization for Sequential Decision Making and Extensive-Form Games

T. Sandholm, Gabriele Farina, Robin Schmucker, 2020 .

Uncoupled Learning Dynamics with O(log T) Swap Regret in Multiplayer Games

Haipeng Luo, T. Sandholm, Christian Kroer, 2022, ArXiv.

M ODELING S TRONG AND H UMAN - LIKE G AMEPLAY WITH KL-R EGULARIZED S EARCH

Hengyuan Hu, Gabriele Farina, 2022 .

Decoding Hidden Markov Models Faster than Viterbi Via Online Matrix-Vector $(protect mathop {elax kern z@ mathgroup symoperators max}mlimits@ , +)$-Multiplication

Gabriele Farina, Massimo Cairo, Romeo Rizzi, 2016 .

Near-optimal no-regret learning for correlated equilibria in multi-player general-sum games

C. Daskalakis, T. Sandholm, Noah Golowich, 2021, Symposium on the Theory of Computing.

Near-Optimal No-Regret Learning for General Convex Games

Haipeng Luo, T. Sandholm, Christian Kroer, 2022, ArXiv.

ESCHER: Eschewing Importance Sampling in Games by Computing a History Value Function to Estimate Regret

Marc Lanctot, T. Sandholm, Gabriele Farina, 2022, ArXiv.

Equilibrium Refinement for the Age of Machines: The One-Sided Quasi-Perfect Equilibrium

T. Sandholm, Gabriele Farina, 2021, NeurIPS.

Near-Optimal $\Phi$-Regret Learning in Extensive-Form Games

T. Sandholm, Gabriele Farina, Ioannis Anagnostides, 2022, 2208.09747.

Meta-Learning in Games

Zhiwei Steven Wu, M. Khodak, T. Sandholm, 2022, ArXiv.

Near-Optimal No-Regret Learning for General Convex Games

Haipeng Luo, T. Sandholm, Christian Kroer, 2022, ArXiv.

Mastering the Game of No-Press Diplomacy via Human-Regularized Reinforcement Learning and Planning

Alexander H. Miller, Athul Paul Jacob, Adam Lerer, 2022, ArXiv.

ESCHER: Eschewing Importance Sampling in Games by Computing a History Value Function to Estimate Regret

Marc Lanctot, T. Sandholm, Gabriele Farina, 2022, ICLR.

Uncoupled Learning Dynamics with O(log T) Swap Regret in Multiplayer Games

Haipeng Luo, T. Sandholm, Christian Kroer, 2022, NeurIPS.

Optimistic Mirror Descent Either Converges to Nash or to Strong Coarse Correlated Equilibria in Bimatrix Games

Ioannis Panageas, T. Sandholm, Gabriele Farina, 2022, NeurIPS.

Near-Optimal No-Regret Learning Dynamics for General Convex Games

Haipeng Luo, T. Sandholm, Christian Kroer, 2022, NeurIPS.

Human-level play in the game of Diplomacy by combining language models with strategic reasoning

Alexander H. Miller, Athul Paul Jacob, Adam Lerer, 2022, Science.

Clairvoyant Regret Minimization: Equivalence with Nemirovski's Conceptual Prox Method and Extension to General Convex Games

Haipeng Luo, Christian Kroer, Gabriele Farina, 2022, 2208.14891.

Near-optimal no-regret learning for correlated equilibria in multi-player general-sum games

C. Daskalakis, T. Sandholm, Noah Golowich, 2021, STOC.

Decentralized No-regret Learning Algorithms for Extensive-form Correlated Equilibria (Extended Abstract)

Nicola Gatti, Gabriele Farina, Alberto Marchesi, 2021, IJCAI.

Smoothing Method for Approximate Extensive-Form Perfect Equilibrium

Tuomas Sandholm, Christian Kroer, Gabriele Farina, 2017, IJCAI.

On the Convergence of No-Regret Learning Dynamics in Time-Varying Games

Ioannis Panageas, T. Sandholm, Gabriele Farina, 2023, 2301.11241.

On Last-Iterate Convergence Beyond Zero-Sum Games

Ioannis Panageas, T. Sandholm, Gabriele Farina, 2022, ICML.

T. Sandholm, A. Celli, Gabriele Farina, 2022, EC.

Simple Uncoupled No-regret Learning Dynamics for Extensive-form Correlated Equilibrium

Nicola Gatti, Gabriele Farina, Alberto Marchesi, 2020, J. ACM.

Polynomial-Time Computation of Optimal Correlated Equilibria in Two-Player Extensive-Form Games with Public Chance Moves and Beyond pdf

Tuomas Sandholm, Gabriele Farina, T. Sandholm, 2020, NeurIPS.

No-Regret Learning Dynamics for Extensive-Form Correlated Equilibrium pdf

Nicola Gatti, Gabriele Farina, Alberto Marchesi, 2020, NeurIPS.

Coarse Correlation in Extensive-Form Games

Tuomas Sandholm, Gabriele Farina, Tommaso Bianchi, 2019, AAAI.

Efficient Regret Minimization Algorithm for Extensive-Form Correlated Equilibrium

Tuomas Sandholm, Fei Fang, Gabriele Farina, 2019, NeurIPS.

Correlation in Extensive-Form Games: Saddle-Point Formulation and Benchmarks

Tuomas Sandholm, Fei Fang, Gabriele Farina, 2019, NeurIPS.

EXTENSIVE-FORM CORRELATED EQUILIBRIUM∗

Chun Kai Ling, A. Preprint, Gabriele Farina, 2019 .

Fast Payoff Matrix Sparsification Techniques for Structured Extensive-Form Games pdf

Tuomas Sandholm, Gabriele Farina, T. Sandholm, 2021, AAAI.

Combination treatment optimization using a pan-cancer pathway model

Tuomas Sandholm, Fabian Fröhlich, Gabriele Farina, 2020, bioRxiv.

Connecting Optimal Ex-Ante Collusion in Teams to Extensive-Form Correlation: Faster Algorithms and Positive Complexity Results

Tuomas Sandholm, Nicola Gatti, Gabriele Farina, 2021, ICML.

The Update Equivalence Framework for Decision-Time Planning

J. Z. Kolter, Noam Brown, Hengyuan Hu, 2023, ArXiv.

Quasi-Perfect Stackelberg Equilibrium

Tuomas Sandholm, Nicola Gatti, Christian Kroer, 2018, AAAI.

Trembling-Hand Perfection in Extensive-Form Games with Commitment

Tuomas Sandholm, Nicola Gatti, Christian Kroer, 2018, IJCAI.

Robust Stackelberg Equilibria in Extensive-Form Games and Extension to Limited Lookahead pdf

Tuomas Sandholm, Christian Kroer, Gabriele Farina, 2017, AAAI.

Team Belief DAG Form: A Concise Representation for Team-Correlated Game-Theoretic Decision Making

T. Sandholm, B. Zhang, Gabriele Farina, 2022, ArXiv.

Better Regularization for Sequential Decision Spaces: Fast Convergence Rates for Nash, Correlated, and Team Equilibria

Tuomas Sandholm, Christian Kroer, Gabriele Farina, 2021, EC.

Computing Optimal Equilibria and Mechanisms via Learning in Zero-Sum Extensive-Form Games

T. Sandholm, N. Gatti, B. Zhang, 2023, arXiv.org.

Steering No-Regret Learners to Optimal Equilibria

T. Sandholm, N. Gatti, B. Zhang, 2023, ArXiv.

Regret Circuits: Composability of Regret Minimizers

Tuomas Sandholm, Christian Kroer, Gabriele Farina, 2018, ICML.

Modeling Strong and Human-Like Gameplay with KL-Regularized Search

Athul Paul Jacob, Adam Lerer, A. Bakhtin, 2021, ICML.

Online Convex Optimization for Sequential Decision Processes and Extensive-Form Games

Tuomas Sandholm, Christian Kroer, Gabriele Farina, 2018, AAAI.

Dynamic Subtrees Queries Revisited: The Depth First Tour Tree pdf

Luigi Laura, Gabriele Farina, L. Laura, 2015, IWOCA.

Optimistic Regret Minimization for Extensive-Form Games via Dilated Distance-Generating Functions

Tuomas Sandholm, Christian Kroer, Gabriele Farina, 2019, NeurIPS.

Model-Free Online Learning in Unknown Sequential Decision Making Problems and Games

Tuomas Sandholm, Gabriele Farina, T. Sandholm, 2021, AAAI.

Inter-Club Kidney Exchange

Tuomas Sandholm, John P. Dickerson, Gabriele Farina, 2017, AAAI Workshops.

Operation Frames and Clubs in Kidney Exchange

Tuomas Sandholm, John P. Dickerson, Gabriele Farina, 2017, IJCAI.

Stochastic Regret Minimization in Extensive-Form Games

Tuomas Sandholm, Christian Kroer, Gabriele Farina, 2020, ICML.

Stable-Predictive Optimistic Counterfactual Regret Minimization pdf

Tuomas Sandholm, Christian Kroer, Gabriele Farina, 2019, ICML.

Meta-Learning in Games

Zhiwei Steven Wu, M. Khodak, T. Sandholm, 2022, ICLR.

On the Convergence of No-Regret Learning Dynamics in Time-Varying Games

Ioannis Panageas, T. Sandholm, Gabriele Farina, 2023, ArXiv.

Near-Optimal No-Regret Learning for General Convex Games

Haipeng Luo, T. Sandholm, Christian Kroer, 2022, ArXiv.

Simple Uncoupled No-regret Learning Dynamics for Extensive-form Correlated Equilibrium

N. Gatti, A. Celli, Gabriele Farina, 2021, J. ACM.

Kernelized Multiplicative Weights for 0/1-Polyhedral Games: Bridging the Gap Between Learning in Extensive-Form and Normal-Form Games

Haipeng Luo, Christian Kroer, Gabriele Farina, 2022, ICML.

Faster Game Solving via Predictive Blackwell Approachability: Connecting Regret Matching and Mirror Descent pdf

Tuomas Sandholm, Christian Kroer, Gabriele Farina, 2020, AAAI.

Solving Large Sequential Games with the Excessive Gap Technique

Tuomas Sandholm, Christian Kroer, Gabriele Farina, 2018, NeurIPS.

Bandit Linear Optimization for Sequential Decision Making and Extensive-Form Games

Tuomas Sandholm, Gabriele Farina, Robin Schmucker, 2021, AAAI.

Near-Optimal Φ-Regret Learning in Extensive-Form Games

T. Sandholm, Gabriele Farina, Ioannis Anagnostides, 2022, ICML.

Faster No-Regret Learning Dynamics for Extensive-Form Correlated and Coarse Correlated Equilibria

T. Sandholm, Christian Kroer, A. Celli, 2022, EC.

Regret Minimization in Behaviorally-Constrained Zero-Sum Games

Tuomas Sandholm, Christian Kroer, Gabriele Farina, 2017, ICML.

Decoding Hidden Markov Models Faster Than Viterbi Via Online Matrix-Vector (max, +)-Multiplication

Romeo Rizzi, Gabriele Farina, Massimo Cairo, 2015, AAAI.

Team-PSRO for Learning Approximate TMECor in Large Team Games via Cooperative Reinforcement Learning

T. Sandholm, Gabriele Farina, Stephen McAleer, 2023, NeurIPS.

Composability of Regret Minimizers

T. Sandholm, Christian Kroer, Gabriele Farina, 2018, ArXiv.