Showing 1 - 20 results of 5,919 for search '"sampling-based algorithms"', query time: 1.23s Refine Results
  1. 1
  2. 2
  3. 3
    Conference

    Source: 2014 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL) Adaptive Dynamic Programming and Reinforcement Learning (ADPRL), 2014 IEEE Symposium on. :1-8 Dec, 2014

    Relation: 2014 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL)

  4. 4
  5. 5
    Conference

    Source: 2026 IEEE International Conference on Mechatronics and Automation (ICMA) Mechatronics and Automation (ICMA), 2026 IEEE International Conference on. :635-641 Aug, 2026

    Relation: 2026 IEEE International Conference on Mechatronics and Automation (ICMA)

  6. 6
  7. 7
    Conference

    Source: 2017 IEEE International Conference on Robotics and Automation (ICRA) Robotics and Automation (ICRA), 2017 IEEE International Conference on. :4991-4996 May, 2017

    Relation: 2017 IEEE International Conference on Robotics and Automation (ICRA)

  8. 8
  9. 9
    Mixed Materials

    Additional Titles: We consider a kernelized bandit problem with a compact arm set ${X} \subset \mathbb{R}^d $ and a fixed but unknown reward function $f^*$ with a finite norm in some Reproducing Kernel Hilbert Space (RKHS). We propose a class of computationally efficient kernelized bandit algorithms, which we call GP-Generic, based on a novel concept: exploration distributions. This class of algorithms includes Upper Confidence Bound-based approaches as a special case, but also allows for a variety of randomized algorithms. With careful choice of exploration distribution, our proposed generic algorithm realizes a wide range of concrete algorithms that achieve $\tilde{O}(γ_T\sqrt{T})$ regret bounds, where $γ_T$ characterizes the RKHS complexity. This matches known results for UCB- and Thompson Sampling-based algorithms; we also show that in practice, randomization can yield better practical results.

    Index Terms: Machine Learning, text

  10. 10
    Mixed Materials

    Additional Titles: We address differentially private stochastic bandit problems from the angles of exploring the deep connections among Thompson Sampling with Gaussian priors, Gaussian mechanisms, and Gaussian differential privacy (GDP). We propose DP-TS-UCB, a novel parametrized private bandit algorithm that enables to trade off privacy and regret. DP-TS-UCB satisfies $ \tilde{O} \left(T^{0.25(1-α)}\right)$-GDP and enjoys an $O \left(K\ln^{α+1}(T)/Δ\right)$ regret bound, where $α\in [0,1]$ controls the trade-off between privacy and regret. Theoretically, our DP-TS-UCB relies on anti-concentration bounds of Gaussian distributions and links exploration mechanisms in Thompson Sampling-based algorithms and Upper Confidence Bound-based algorithms, which may be of independent interest.

    Index Terms: Machine Learning, text

  11. 11
    Conference

    Source: 2026 IEEE Guwahati Subsection Conference (GCON) Guwahati Subsection Conference (GCON), 2026 IEEE. :1-6 Jun, 2026

    Relation: 2026 IEEE Guwahati Subsection Conference (GCON)

  12. 12
    Conference

    Source: 2013 IEEE International Conference on Robotics and Automation Robotics and Automation (ICRA), 2013 IEEE International Conference on. :2421-2428 May, 2013

    Relation: 2013 IEEE International Conference on Robotics and Automation (ICRA)

  13. 13
    Conference

    Source: 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) Intelligent Robots and Systems (IROS), 2015 IEEE/RSJ International Conference on. :1422-1427 Sep, 2015

    Relation: 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

  14. 14
    Conference

    Source: 53rd IEEE Conference on Decision and Control Decision and Control (CDC), 2014 IEEE 53rd Annual Conference on. :1858-1865 Dec, 2014

    Relation: 2014 IEEE 53rd Annual Conference on Decision and Control (CDC)

  15. 15
  16. 16
    Academic Journal

    Source: IEEE Transactions on Automation Science and Engineering IEEE Trans. Automat. Sci. Eng. Automation Science and Engineering, IEEE Transactions on. 13(2):415-424 Apr, 2016

    Linked Full Text
  17. 17
    Conference

    Source: 2014 IEEE International Conference on Robotics and Automation (ICRA) Robotics and Automation (ICRA), 2014 IEEE International Conference on. :5326-5332 May, 2014

    Relation: 2014 IEEE International Conference on Robotics and Automation (ICRA)

  18. 18
    Conference

    Source: 2013 American Control Conference American Control Conference (ACC), 2013. :4604-4610 Jun, 2013

    Relation: 2013 American Control Conference (ACC)

  19. 19
    Conference

    Source: 2012 American Control Conference (ACC) American Control Conference (ACC), 2012. :735-742 Jun, 2012

    Relation: 2012 American Control Conference - ACC 2012

  20. 20
    Conference

    Source: 20th Iranian Conference on Electrical Engineering (ICEE2012) Electrical Engineering (ICEE), 2012 20th Iranian Conference on. :963-968 May, 2012

    Relation: 2012 20th Iranian Conference on Electrical Engineering (ICEE)