Identifying Copeland Winners in Dueling Bandits with Indifferences

no code implementations • 1 Oct 2023 • Viktor Bengs, Björn Haddenhorst, Eyke Hüllermeier

We consider the task of identifying the Copeland winner(s) in a dueling bandits problem with ternary feedback.

AC-Band: A Combinatorial Bandit-Based Approach to Algorithm Configuration

1 code implementation • 1 Dec 2022 • Jasmin Brandt, Elias Schede, Viktor Bengs, Björn Haddenhorst, Eyke Hüllermeier, Kevin Tierney

We study the algorithm configuration (AC) problem, in which one seeks to find an optimal parameter configuration of a given target algorithm in an automated way.

Multi-Armed Bandits

Finding Optimal Arms in Non-stochastic Combinatorial Bandits with Semi-bandit Feedback and Finite Budget

no code implementations • 9 Feb 2022 • Jasmin Brandt, Viktor Bengs, Björn Haddenhorst, Eyke Hüllermeier

We consider the combinatorial bandits problem with semi-bandit feedback under finite sampling budget constraints, in which the learner can carry out its action only for a limited number of times specified by an overall budget.

Identification of the Generalized Condorcet Winner in Multi-dueling Bandits

1 code implementation • NeurIPS 2021 • Björn Haddenhorst, Viktor Bengs, Eyke Hüllermeier

The reliable identification of the “best” arm while keeping the sample complexity as low as possible is a common task in the field of multi-armed bandits.

Multi-Armed Bandits

Learning Context-Dependent Choice Functions

1 code implementation • 29 Jan 2019 • Karlson Pfannschmidt, Pritha Gupta, Björn Haddenhorst, Eyke Hüllermeier

Choice functions accept a set of alternatives as input and produce a preferred subset of these alternatives as output.