ML Anthology

Deterministic Calibration and Nash Equilibrium

Sham M. Kakade, Dean P. Foster
COLT 2004 pp. 33-48
doi:10.1007/978-3-540-27819-1_3 /colt/2004/kakade2004colt-deterministic/

Abstract

We provide a natural learning process in which the joint frequency of empirical play converges into the set of convex combinations of Nash equilibria. In this process, all players rationally choose their actions using a public prediction made by a deterministic, weakly calibrated algorithm. Furthermore, the public predictions used in any given round of play are frequently close to some Nash equilibrium of the game.

PDF COLT Semantic Scholar

Cite

Text

Kakade and Foster. "Deterministic Calibration and Nash Equilibrium." Annual Conference on Computational Learning Theory, 2004. doi:10.1007/978-3-540-27819-1_3

Markdown

[Kakade and Foster. "Deterministic Calibration and Nash Equilibrium." Annual Conference on Computational Learning Theory, 2004.](https://mlanthology.org/colt/2004/kakade2004colt-deterministic/) doi:10.1007/978-3-540-27819-1_3

BibTeX

@inproceedings{kakade2004colt-deterministic,
  title     = {{Deterministic Calibration and Nash Equilibrium}},
  author    = {Kakade, Sham M. and Foster, Dean P.},
  booktitle = {Annual Conference on Computational Learning Theory},
  year      = {2004},
  pages     = {33-48},
  doi       = {10.1007/978-3-540-27819-1_3},
  url       = {https://mlanthology.org/colt/2004/kakade2004colt-deterministic/}
}