Paper

Revisiting CFR+ and Alternating Updates

Burch, Neil, Moravcik, Matej, Schmid, Martin

Understand

The CFR+ algorithm for solving imperfect information games is a variant of the popular CFR algorithm, with faster empirical performance on a range of problems.

  • It was introduced with a theoretical upper bound on solution error, but subsequent work showed an error in one step of the proof.
  • We provide updated proofs to recover the original bound.

Built on

  • Theory of Games and Economic Behavior

    Von Neumann, J., & Morgenstern, O. (1947) · 1947

    Earlier work this paper cites.

  • Equilibrium points in n-person games

    Nash, J. F. (1950) · 1950

    Earlier work this paper cites.

  • A simple adaptive procedure leading to correlated equilibrium

    Hart, S., & Mas-Colell, A. (2000) · 2000

    Earlier work this paper cites.

Similar

  • Regret minimization in games with incomplete information

    Zinkevich, M., Johanson, M., Bowling, M., & Piccione, C. (2007) · 2007

    Cited alongside, same era.

  • Solving large imperfect information games using CFR+

    Original

    Tammelin, O. (2014) · 2014

    Cited alongside, same era.

  • Heads-up limit hold’em poker is solved

    Bowling, M., Burch, N., Johanson, M., & Tammelin, O. (2015) · 2015

    Cited alongside, same era.

Then

  • Solving heads-up limit texas hold’em

    Tammelin, O., Burch, N., Johanson, M., & Bowling, M. (2015) · 2015

    Later among the works it cites.

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

    Farina, G., Kroer, C., & Sandholm, T. (2019) · 2019

    Later among the works it cites.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…