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

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

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


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


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

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


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

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


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

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


Apr 25, 2022
Ioannis Anagnostides, Gabriele Farina, Christian Kroer, Chung-Wei Lee, Haipeng Luo, Tuomas Sandholm


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

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


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

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


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

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


Dec 14, 2021
Athul Paul Jacob, David J. Wu, Gabriele Farina, Adam Lerer, Anton Bakhtin, Jacob Andreas, Noam Brown


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

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


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

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


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

* Accepted for publication at EC21 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

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


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

* 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

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email
1
2
3
>>