On an unified framework for approachability in games with or without signals

TL;DR

This paper introduces a unified abstract framework for approachability in games with full or partial monitoring, providing new theoretical results, characterizations, and convergence rates for approachable sets.

Contribution

It develops a new abstract game model called the 'purely informative game' that unifies approachability theory across different monitoring scenarios, extending and generalizing prior results.

Findings

New necessary and sufficient conditions for approachability of arbitrary sets.

Complete characterization of approachable convex sets with simple reformulation.

Rates of convergence for specific classes of games.

Abstract

We unify standard frameworks for approachability both in full or partial monitoring by defining a new abstract game, called the "purely informative game", where the outcome at each stage is the maximal information players can obtain, represented as some probability measure. Objectives of players can be rewritten as the convergence (to some given set) of sequences of averages of these probability measures. We obtain new results extending the approachability theory developed by Blackwell moreover this new abstract framework enables us to characterize approachable sets with, as usual, a remarkably simple and clear reformulation for convex sets. Translated into the original games, those results become the first necessary and sufficient condition under which an arbitrary set is approachable and they cover and extend previous known results for convex sets. We also investigate a specific class of games where, thanks to some unusual definition of averages and convexity, we again obtain a complete characterization of approachable sets along with rates of convergence.