Robust Risk-Averse Stochastic Multi-armed Bandits

@inproceedings{Maillard2013RobustRS,
  title={Robust Risk-Averse Stochastic Multi-armed Bandits},
  author={O. Maillard},
  booktitle={ALT},
  year={2013}
}
  • O. Maillard
  • Published in ALT 2013
  • Computer Science
  • We study a variant of the standard stochastic multi-armed bandit problem when one is not interested in the arm with the best mean, but instead in the arm maximizing some coherent risk measure criterion. Further, we are studying the deviations of the regret instead of the less informative expected regret. We provide an algorithm, called RA-UCB to solve this problem, together with a high probability bound on its regret. 
    30 Citations

    Figures and Topics from this paper

    Generalized Risk-Aversion in Stochastic Multi-Armed Bandits
    • 17
    • Highly Influenced
    • PDF
    Risk-Averse Multi-Armed Bandit Problems Under Mean-Variance Measure
    • S. Vakili, Qing Zhao
    • Mathematics, Computer Science
    • IEEE Journal of Selected Topics in Signal Processing
    • 2016
    • 39
    • PDF
    Risk-Averse Stochastic Convex Bandit
    • 11
    • PDF
    Constrained regret minimization for multi-criterion multi-armed bandits
    • 2
    • Highly Influenced
    • PDF
    Thompson Sampling Algorithms for Mean-Variance Bandits
    • 3
    • PDF
    A General Approach to Multi-Armed Bandits Under Risk Criteria
    • 21
    • PDF
    Near-Optimal MNL Bandits Under Risk Criteria
    • 1
    • PDF
    Statistically Robust, Risk-Averse Best Arm Identification in Multi-Armed Bandits
    • 1
    • PDF
    A General Framework for Bandit Problems Beyond Cumulative Objectives.
    • PDF

    References

    SHOWING 1-10 OF 35 REFERENCES
    Risk-Aversion in Multi-armed Bandits
    • 78
    • PDF
    Thompson Sampling: An Asymptotically Optimal Finite-Time Analysis
    • 389
    • PDF
    Robustness of Anytime Bandit Policies
    • 2
    • PDF
    Exploration-exploitation tradeoff using variance estimates in multi-armed bandits
    • 412
    • PDF
    Robustness of stochastic bandit policies
    • 4
    Finite-time Analysis of the Multiarmed Bandit Problem
    • 4,414
    • PDF
    The Nonstochastic Multiarmed Bandit Problem
    • 1,673
    • PDF