64
89

Lipschitz Bandits without the Lipschitz Constant

Abstract

We consider the setting of stochastic bandit problems with a continuum of arms. We first point out that the strategies considered so far in the literature only provided theoretical guarantees of the form: given some tuning parameters, the regret is small with respect to a class of environments that depends on these parameters. This is however not the right perspective, as it is the strategy that should adapt to the specific bandit environment at hand, and not the other way round. Put differently, an adaptation issue is raised. We solve it for the special case of environments whose mean-payoff functions are globally Lipschitz. More precisely, we show that the minimax optimal orders of magnitude Ld/(d+2)T(d+1)/(d+2)L^{d/(d+2)} \, T^{(d+1)/(d+2)} of the regret bound against an environment ff with Lipschitz constant LL over TT time instances can be achieved without knowing LL or TT in advance. This is in contrast to all previously known strategies, which require to some extent the knowledge of LL to achieve this performance guarantee.

View on arXiv
Comments on this paper