Blackwell approachability, regret minimization and calibration are three criteria evaluating a strategy (or an algorithm) in different sequential decision problems, or repeated games between a player and Nature. Although they have at first sight nothing in common, links between have been discovered: both consistent and calibrated strategies can be constructed by following, in some auxiliary game, an approachability strategy. We gathered famous or recent results and provide new ones in order to develop and generalize Blackwell's elegant theory. The final goal is to show how it can be used as a basic powerful tool to exhibit a new class of intuitive algorithms, based on simple geometric properties. In order to be complete, we also prove that ...
In the standard setting of approachability there are two players and a target set. The players play ...
Online learning or sequential decision making is formally defined as a repeated game between an adve...
Blackwell approachability is an online learning setup generalizing the classical problem of regret m...
This paper reframes approachability theory within the context of population games. Thus, whilst a pl...
We examine Blackwell approachability in so-called generalized quitting games. These are repeated gam...
We unify standard frameworks for approachability both in full or partial monitoring by defining a ne...
In repeated games with differential information on one side, the labelling "general case" refers to ...
Over the past few years many proofs of the existence of calibration have been discovered. Each of th...
International audienceWe provide yet another proof of the existence of calibrated forecasters; it ha...
Abstract. The approachability theorem of Blackwell (1956b) is extended to infinite dimensional space...
We exhibit and characterize an entire class of simple adaptive strategies, in the repeated play of a...
Abstract. This manuscript investigates the relationship between Blackwell Approachability, a stochas...
Regret minimizing strategies for repeated games have been receiving increasing attention in the lite...
International audienceIn game-theoretic learning, several agents are simultaneously following their ...
In the standard setting of approachability there are two players and a target set. The players play ...
Online learning or sequential decision making is formally defined as a repeated game between an adve...
Blackwell approachability is an online learning setup generalizing the classical problem of regret m...
This paper reframes approachability theory within the context of population games. Thus, whilst a pl...
We examine Blackwell approachability in so-called generalized quitting games. These are repeated gam...
We unify standard frameworks for approachability both in full or partial monitoring by defining a ne...
In repeated games with differential information on one side, the labelling "general case" refers to ...
Over the past few years many proofs of the existence of calibration have been discovered. Each of th...
International audienceWe provide yet another proof of the existence of calibrated forecasters; it ha...
Abstract. The approachability theorem of Blackwell (1956b) is extended to infinite dimensional space...
We exhibit and characterize an entire class of simple adaptive strategies, in the repeated play of a...
Abstract. This manuscript investigates the relationship between Blackwell Approachability, a stochas...
Regret minimizing strategies for repeated games have been receiving increasing attention in the lite...
International audienceIn game-theoretic learning, several agents are simultaneously following their ...
In the standard setting of approachability there are two players and a target set. The players play ...
Online learning or sequential decision making is formally defined as a repeated game between an adve...
Blackwell approachability is an online learning setup generalizing the classical problem of regret m...