2 citations · 3 across the 3 of their papers we have counts for
3 papers
Upper-Confidence-Bound Algorithms for Active Learning in Multi-Armed Bandits
Alexandra Carpentier, Alessandro Lazaric, Mohammad Ghavamzadeh +3
In this paper, we study the problem of estimating uniformly well the mean values of several distributions given a finite budget of samples. If the variance of the distributions wer…
Non-trivial two-armed partial-monitoring games are bandits
András Antos, Gábor Bartók, Csaba Szepesvári
We consider online learning in partial-monitoring games against an oblivious adversary. We show that when the number of actions available to the learner is two and the game is nont…
Toward a Classification of Finite Partial-Monitoring Games
András Antos, Gábor Bartók, Dávid Pál +1
Partial-monitoring games constitute a mathematical framework for sequential decision making problems with imperfect feedback: The learner repeatedly chooses an action, opponent res…