On conditional versus marginal bias in multi-armed bandits

v1v2v3 (latest)

On conditional versus marginal bias in multi-armed bandits

19 February 2020

Alessandro Rinaldo

ArXiv (abs)PDF HTML

Papers citing "On conditional versus marginal bias in multi-armed bandits"

6 / 6 papers shown

Title
Confidence Intervals for Policy Evaluation in Adaptive Experiments Vitor Hadad David A. Hirshberg Ruohan Zhan Stefan Wager Susan Athey 68 146 0 07 Nov 2019
Are sample means in multi-armed bandits positively or negatively biased? Jaehyeok Shin Aaditya Ramdas Alessandro Rinaldo 69 37 0 27 May 2019
Accurate Inference for Adaptive Linear Models Y. Deshpande Lester W. Mackey Vasilis Syrgkanis Matt Taddy OffRL 99 62 0 18 Dec 2017
lil' UCB : An Optimal Exploration Algorithm for Multi-Armed Bandits Kevin Jamieson Matthew Malloy Robert D. Nowak Sébastien Bubeck 84 417 0 27 Dec 2013
Thompson Sampling: An Asymptotically Optimal Finite Time Analysis E. Kaufmann N. Korda Rémi Munos 167 588 0 18 May 2012
The KL-UCB Algorithm for Bounded Stochastic Bandits and Beyond Aurélien Garivier Olivier Cappé 182 615 0 12 Feb 2011