Are sample means in multi-armed bandits positively or negatively biased?

On the likelihood that one unknown probability exceeds another in view of the evidence of two samples

William R Thompson · 1933

Earlier work this paper cites.

Some aspects of the sequential design of experiments

Herbert Robbins · 1952

Earlier work this paper cites.

Remarks on a stopping time

Norman Starr and Michael B Woodroofe · 1968

Earlier work this paper cites.

Statistical methods related to the law of the iterated logarithm

Herbert Robbins · 1970

Earlier work this paper cites.

Estimation following sequential tests

David Siegmund · 1978

Earlier work this paper cites.

Introduction to reinforcement learning

Richard S Sutton and Andrew G Barto · 1998

Earlier work this paper cites.

Finite-time analysis of the multiarmed bandit problem

Peter Auer, Nicolo Cesa-Bianchi, and Paul Fischer · 2002

Earlier work this paper cites.

Minimax policies for adversarial and stochastic bandits

Jean-Yves Audibert and Sébastien Bubeck · 2009

Earlier work this paper cites.

Stopped random walks

Allan Gut · 2009

Cited alongside, same era.

The KL-UCB algorithm for bounded stochastic bandits and beyond

Aurélien Garivier and Olivier Cappé · 2011

Cited alongside, same era.

Analysis of thompson sampling for the multi-armed bandit problem

Shipra Agrawal and Navin Goyal · 2012

Cited alongside, same era.

Pac subset selection in stochastic multi-armed bandits

Shivaram Kalyanakrishnan, Ambuj Tewari, Peter Auer, and Peter Stone · 2012

Cited alongside, same era.

Thompson sampling: An asymptotically optimal finite-time analysis

Emilie Kaufmann, Nathaniel Korda, and Rémi Munos · 2012

Cited alongside, same era.

Estimation bias in multi-armed bandit algorithms for search advertising

Min Xu, Tao Qin, and Tie-Yan Liu · 2013

Cited alongside, same era.

Optimal best arm identification with fixed confidence

Aurélien Garivier and Emilie Kaufmann · 2016

Later among the works it cites.

Simple bayesian algorithms for best arm identification

Daniel Russo · 2016

Later among the works it cites.

Unbiased estimation for response adaptive clinical trials

Jack Bowden and Lorenzo Trippa · 2017

Later among the works it cites.

Uniform, nonparametric, non-asymptotic confidence sequences

Original

Steven R Howard, Aaditya Ramdas, Jon McAuliffe, and Jasjeet Sekhon · 2018

Later among the works it cites.

Why adaptively collected data have negative bias and how to correct for it

Xinkun Nie, Xiaoying Tian, Jonathan Taylor, and James Zou · 2018

Later among the works it cites.

Bandit algorithms

Tor Lattimore and Csaba Szepesvári · 2019