The K-armed Dueling Bandits Problem

@article{Yue2009TheKD,
  title={The K-armed Dueling Bandits Problem},
  author={Yisong Yue and Josef Broder and Robert D. Kleinberg and Thorsten Joachims},
  journal={J. Comput. Syst. Sci.},
  year={2009},
  volume={78},
  pages={1538-1556}
}
  • Yisong Yue, Josef Broder, +1 author Thorsten Joachims
  • Published 2009
  • Computer Science, Mathematics
  • J. Comput. Syst. Sci.
  • We study a partial-information online-learning problem where actions are restricted to noisy comparisons between pairs of strategies (also known as bandits). In contrast to conventional approaches that require the absolute reward of the chosen strategy to be quantifiable and observable, our setting assumes only that (noisy) binary feedback about the relative reward of two chosen strategies is available. This type of relative feedback is particularly appropriate in applications where absolute… CONTINUE READING

    Figures and Topics from this paper.

    Explore key concepts

    Links to highly relevant papers for key concepts in this paper:

    Citations

    Publications citing this paper.
    SHOWING 1-10 OF 183 CITATIONS

    Preference-based Online Learning with Dueling Bandits: A Survey

    VIEW 5 EXCERPTS
    CITES BACKGROUND & METHODS
    HIGHLY INFLUENCED

    Beat the Mean Bandit

    VIEW 9 EXCERPTS
    CITES BACKGROUND & METHODS

    A Survey of Preference-Based Online Learning with Bandit Algorithms

    VIEW 5 EXCERPTS
    CITES BACKGROUND
    HIGHLY INFLUENCED

    Instance-dependent Regret Bounds for Dueling Bandits

    VIEW 6 EXCERPTS
    CITES BACKGROUND & METHODS
    HIGHLY INFLUENCED

    Contextual Dueling Bandits

    VIEW 8 EXCERPTS
    CITES BACKGROUND & METHODS
    HIGHLY INFLUENCED

    Duelling Bandits with Weak Regret in Adversarial Environments

    VIEW 8 EXCERPTS
    CITES BACKGROUND, METHODS & RESULTS
    HIGHLY INFLUENCED

    Sparse Dueling Bandits

    VIEW 7 EXCERPTS
    CITES BACKGROUND
    HIGHLY INFLUENCED

    Combinatorial Bandits with Relative Feedback

    VIEW 1 EXCERPT
    CITES BACKGROUND

    FILTER CITATIONS BY YEAR

    2009
    2020

    CITATION STATISTICS

    • 35 Highly Influenced Citations

    • Averaged 24 Citations per year from 2018 through 2020

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 35 REFERENCES