Calibration and Internal No-Regret with Random Signals
Abstract
A calibrated strategy can be obtained by performing a strategy that has no internal regret in some auxiliary game. Such a strategy 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 B -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.
Cite
Text
Perchet. "Calibration and Internal No-Regret with Random Signals." International Conference on Algorithmic Learning Theory, 2009. doi:10.1007/978-3-642-04414-4_10Markdown
[Perchet. "Calibration and Internal No-Regret with Random Signals." International Conference on Algorithmic Learning Theory, 2009.](https://mlanthology.org/alt/2009/perchet2009alt-calibration/) doi:10.1007/978-3-642-04414-4_10BibTeX
@inproceedings{perchet2009alt-calibration,
title = {{Calibration and Internal No-Regret with Random Signals}},
author = {Perchet, Vianney},
booktitle = {International Conference on Algorithmic Learning Theory},
year = {2009},
pages = {68-82},
doi = {10.1007/978-3-642-04414-4_10},
url = {https://mlanthology.org/alt/2009/perchet2009alt-calibration/}
}