A multiplicative UCB strategy for Gamma rewards

Matthieu Geist (1)

1 MALIS - MAchine Learning and Interactive Systems

We consider the stochastic multi-armed bandit problem where rewards are distributed according to Gamma probability measures (unknown up to a lower bound on the form factor). To handle this problem, we propose an UCB-like strategy where indexes are multiplicative (sampled mean times a scaling factor). An upper-bound for the associated regret is provided and the proposed strategy is illustrated on some simple experiments.

Mots clés: Stochastic multi-armed bandits; Gamma-distributed rewards

Domaines: Apprentissage [cs.LG]

Matthieu Geist. A multiplicative UCB strategy for Gamma rewards. European Workshop on Reinforcement Learning, 2015, Lille, France. ⟨hal-01258820⟩