ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 1910.02757
76
39
v1v2v3v4 (latest)

Stochastic Bandits with Delay-Dependent Payoffs

7 October 2019
Leonardo Cella
Nicolò Cesa-Bianchi
ArXiv (abs)PDFHTML
Abstract

Motivated by recommendation problems in music streaming platforms, we propose a nonstationary stochastic bandit model in which the expected reward of an arm depends on the number of rounds that have passed since the arm was last pulled. After proving that finding an optimal policy is NP-hard even when all model parameters are known, we introduce a class of ranking policies provably approximating, to within a constant factor, the expected reward of the optimal policy. We show an algorithm whose regret with respect to the best ranking policy is bounded by O~( ⁣kT)\widetilde{\mathcal{O}}\big(\!\sqrt{kT}\big)O(kT​), where kkk is the number of arms and TTT is time. Our algorithm uses only O(kln⁡ln⁡T)\mathcal{O}\big(k\ln\ln T\big)O(klnlnT) switches, which helps when switching between policies is costly. As constructing the class of learning policies requires ordering the arms according to their expectations, we also bound the number of pulls required to do so. Finally, we run experiments to compare our algorithm against UCB on different problem instances.

View on arXiv
Comments on this paper