Corpus ID: 49690121

Factored Bandits

@article{Zimmert2018FactoredB,
  title={Factored Bandits},
  author={Julian Zimmert and Yevgeny Seldin},
  journal={ArXiv},
  year={2018},
  volume={abs/1807.01488}
}
  • Julian Zimmert, Yevgeny Seldin
  • Published 2018
  • Computer Science, Mathematics
  • ArXiv
  • We introduce the factored bandits model, which is a framework for learning with limited (bandit) feedback, where actions can be decomposed into a Cartesian product of atomic actions. [...] Key Method Furthermore, we show that with a slight modification the proposed algorithm can be applied to utility based dueling bandits. We obtain an improvement in the additive terms of the regret bound compared to state of the art algorithms (the additive terms are dominating up to time horizons which are exponential in the…Expand Abstract
    4 Citations
    Influence Diagram Bandits: Variational Thompson Sampling for Structured Bandit Problems
    Solving Bernoulli Rank-One Bandits with Unimodal Thompson Sampling
    • 3
    • PDF
    Bandits with adversarial scaling
    • 1
    • PDF
    Bilinear Bandits with Low-rank Structure
    • 10
    • PDF

    References

    SHOWING 1-10 OF 18 REFERENCES
    Beat the Mean Bandit
    • 72
    • PDF
    Reducing Dueling Bandits to Cardinal Bandits
    • 59
    • PDF
    Minimal Exploration in Structured Stochastic Bandits
    • 40
    • PDF
    Parametric Bandits: The Generalized Linear Case
    • 221
    • PDF
    The K-armed Dueling Bandits Problem
    • 194
    • PDF
    Regret Lower Bound and Optimal Algorithm in Dueling Bandit Problem
    • 34
    • PDF
    Relative Upper Confidence Bound for the K-Armed Dueling Bandit Problem
    • 69
    • PDF
    Improved Algorithms for Linear Stochastic Bandits
    • 630
    • PDF
    The End of Optimism? An Asymptotic Analysis of Finite-Armed Linear Bandits
    • 52
    • Highly Influential
    • PDF
    Stochastic Rank-1 Bandits
    • 30
    • PDF