English

Calibration and Internal no-Regret with Partial Monitoring

Computer Science and Game Theory 2010-07-28 v1 Machine Learning Machine Learning

Abstract

Calibrated strategies can be obtained by performing strategies that have no internal regret in some auxiliary game. Such strategies can be constructed explicitly with the use of Blackwell's approachability theorem, in an other auxiliary game. We establish the converse: a strategy that approaches a convex BB-set can be derived from the construction of a calibrated strategy. We develop these tools in the framework of a game with partial monitoring, where players do not observe the actions of their opponents but receive random signals, to define a notion of internal regret and construct strategies that have no such regret.

Keywords

Cite

@article{arxiv.1006.1746,
  title  = {Calibration and Internal no-Regret with Partial Monitoring},
  author = {Vianney Perchet},
  journal= {arXiv preprint arXiv:1006.1746},
  year   = {2010}
}