Get our free extension to see links to code for papers anywhere online!

Add to Chrome

Add to Firefox

Picture for Gabriele Farina

Gabriele Farina

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

Aug 20, 2022
Ioannis Anagnostides, Gabriele Farina, Tuomas Sandholm

Figure 1 for Near-Optimal $Φ$-Regret Learning in Extensive-Form Games

Figure 2 for Near-Optimal $Φ$-Regret Learning in Extensive-Form Games

Access Paper or Ask Questions

Near-Optimal No-Regret Learning for General Convex Games

Jun 20, 2022
Gabriele Farina, Ioannis Anagnostides, Haipeng Luo, Chung-Wei Lee, Christian Kroer, Tuomas Sandholm

Figure 1 for Near-Optimal No-Regret Learning for General Convex Games

Access Paper or Ask Questions

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

Jun 08, 2022
Stephen McAleer, Gabriele Farina, Marc Lanctot, Tuomas Sandholm

Figure 1 for ESCHER: Eschewing Importance Sampling in Games by Computing a History Value Function to Estimate Regret

Figure 2 for ESCHER: Eschewing Importance Sampling in Games by Computing a History Value Function to Estimate Regret

Figure 3 for ESCHER: Eschewing Importance Sampling in Games by Computing a History Value Function to Estimate Regret

Figure 4 for ESCHER: Eschewing Importance Sampling in Games by Computing a History Value Function to Estimate Regret

Access Paper or Ask Questions

Optimal Correlated Equilibria in General-Sum Extensive-Form Games: Fixed-Parameter Algorithms, Hardness, and Two-Sided Column-Generation

Mar 14, 2022
Brian Zhang, Gabriele Farina, Andrea Celli, Tuomas Sandholm

Figure 1 for Optimal Correlated Equilibria in General-Sum Extensive-Form Games: Fixed-Parameter Algorithms, Hardness, and Two-Sided Column-Generation

Figure 2 for Optimal Correlated Equilibria in General-Sum Extensive-Form Games: Fixed-Parameter Algorithms, Hardness, and Two-Sided Column-Generation

Figure 3 for Optimal Correlated Equilibria in General-Sum Extensive-Form Games: Fixed-Parameter Algorithms, Hardness, and Two-Sided Column-Generation

Figure 4 for Optimal Correlated Equilibria in General-Sum Extensive-Form Games: Fixed-Parameter Algorithms, Hardness, and Two-Sided Column-Generation

Access Paper or Ask Questions

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

Feb 01, 2022
Gabriele Farina, Chung-Wei Lee, Haipeng Luo, Christian Kroer

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

Figure 2 for Kernelized Multiplicative Weights for 0/1-Polyhedral Games: Bridging the Gap Between Learning in Extensive-Form and Normal-Form Games

Figure 3 for Kernelized Multiplicative Weights for 0/1-Polyhedral Games: Bridging the Gap Between Learning in Extensive-Form and Normal-Form Games

Figure 4 for Kernelized Multiplicative Weights for 0/1-Polyhedral Games: Bridging the Gap Between Learning in Extensive-Form and Normal-Form Games

Access Paper or Ask Questions

Near-Optimal No-Regret Learning for Correlated Equilibria in Multi-Player General-Sum Games

Nov 11, 2021
Ioannis Anagnostides, Constantinos Daskalakis, Gabriele Farina, Maxwell Fishelson, Noah Golowich, Tuomas Sandholm

Figure 1 for Near-Optimal No-Regret Learning for Correlated Equilibria in Multi-Player General-Sum Games

Figure 2 for Near-Optimal No-Regret Learning for Correlated Equilibria in Multi-Player General-Sum Games

Access Paper or Ask Questions

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

May 27, 2021
Gabriele Farina, Christian Kroer, Tuomas Sandholm

Figure 1 for Better Regularization for Sequential Decision Spaces: Fast Convergence Rates for Nash, Correlated, and Team Equilibria

Figure 2 for Better Regularization for Sequential Decision Spaces: Fast Convergence Rates for Nash, Correlated, and Team Equilibria

Figure 3 for Better Regularization for Sequential Decision Spaces: Fast Convergence Rates for Nash, Correlated, and Team Equilibria

Figure 4 for Better Regularization for Sequential Decision Spaces: Fast Convergence Rates for Nash, Correlated, and Team Equilibria

* Accepted for publication at EC21

Access Paper or Ask Questions

Simple Uncoupled No-Regret Learning Dynamics for Extensive-Form Correlated Equilibrium

Apr 04, 2021
Gabriele Farina, Andrea Celli, Alberto Marchesi, Nicola Gatti

Figure 1 for Simple Uncoupled No-Regret Learning Dynamics for Extensive-Form Correlated Equilibrium

Figure 2 for Simple Uncoupled No-Regret Learning Dynamics for Extensive-Form Correlated Equilibrium

* Extended version of our NeurIPS 2020 paper. Compared to the conference version, this preprint gives finer, in-high-probability regret bounds. We also better connected our work to the phi-regret framework

Access Paper or Ask Questions