Logo Logo
Help
Contact
Switch Language to German
Bengs, Viktor; Saha, Aadirupa; Hüllermeier, Eyke ORCID: 0000-0002-9944-4108 (July 2022): Stochastic Contextual Dueling Bandits under Linear Stochastic Transitivity Models. 39th International Conference on Machine Learning, July 17-23 2022, Baltimore, MD, USA.
Full text not available from 'Open Access LMU'.

Abstract

We consider the regret minimization task in a dueling bandits problem with context information. In every round of the sequential decision problem, the learner makes a context-dependent selection of two choice alternatives (arms) to be compared with each other and receives feedback in the form of noisy preference information. We assume that the feedback process is determined by a linear stochastic transitivity model with contextualized utilities (CoLST), and the learner’s task is to include the best arm (with highest latent context-dependent utility) in the duel. We propose a computationally efficient algorithm, CoLSTIM, which makes its choice based on imitating the feedback process using perturbed context-dependent utility estimates of the underlying CoLST model. If each arm is associated with a d-dimensional feature vector, we show that CoLSTIM achieves a regret of order O(sqrt(T)) after T learning rounds. Additionally, we also establish the optimality of CoLSTIM by showing a lower bound for the weak regret that refines the existing average regret analysis. Our experiments demonstrate its superiority over state-of-art algorithms for special cases of CoLST models.