A PAC algorithm in relative precision for bandit problem with costly sampling
From MaRDI portal
Publication:2084297
DOI10.1007/s00186-022-00769-xzbMath1503.90085arXiv2007.15331MaRDI QIDQ2084297
Arthur Macherey, Marie Billaud Friess, Anthony Nouy, Clémentine Prieur
Publication date: 18 October 2022
Published in: Mathematical Methods of Operations Research (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/2007.15331
concentration inequalities; relative precision; Monte Carlo estimates; bandit algorithm; probably approximately correct algorithm
90C15: Stochastic programming
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Exploration-exploitation tradeoff using variance estimates in multi-armed bandits
- Robust optimization - a comprehensive survey
- Good arm identification via bandit feedback
- Pure exploration in finitely-armed and continuous-armed bandits
- Robust Stochastic Approximation Approach to Stochastic Programming
- Stochastic approximation on a discrete set and the multi— armed
- Stochastic Discrete Optimization
- Stochastic Comparison Algorithm for Discrete Optimization with Estimation
- Bandit Algorithms