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. 1505.00369
203
204
v1v2v3 (latest)

Batched Bandit Problems

2 May 2015
Vianney Perchet
Philippe Rigollet
Sylvain Chassang
E. Snowberg
    OffRL
ArXiv (abs)PDFHTML
Abstract

Motivated by practical applications, chiefly clinical trials, we study the regret achievable for stochastic bandits under the constraint that the employed policy must split trials into a small number of batches. Our results show that a very small number of batches gives close to minimax optimal regret bounds. As a byproduct, we derive optimal policies with low switching cost for stochastic bandits.

View on arXiv
Comments on this paper