Fetching the paper…

Reading the bibliography…

2020

Asymptotic Randomised Control with applications to bandits

Cohen, Samuel N., Treetanthiploet, Tanut

Original
PDF
Post on X

Understand

We consider a general multi-armed bandit problem with correlated (and simple contextual and restless) elements, as a relaxed control problem.

By introducing an entropy regularisation, we obtain a smooth asymptotic approximation to the value function.
This yields a novel semi-index approximation of the optimal decision process.
This semi-index can be interpreted as explicitly balancing an exploration-exploitation trade-off as in the optimistic (UCB) principle where the learning premium explicitly describes asymmetry of information available in the environment and non-linearity in the reward function.

Asymptotic Randomised Control with applications to bandits · Around

Built on

W. R. Thompson
1933
Earlier work this paper cites.
R. Rockafellar
1972
Earlier work this paper cites.
J. C. Gittins and D. M. Jones
1974
Earlier work this paper cites.
J. Gittins
1989
Earlier work this paper cites.
R. Agrawal
1995
Earlier work this paper cites.
S. P. Singh, T. Jaakkola, M. L. Littman, and C. Szepesvári
2000
Earlier work this paper cites.
P. Auer, N. Cesa-Bianchi, and P. Fischer
2002
Earlier work this paper cites.
M. Brezzi and T. Lai
2002
Earlier work this paper cites.
F. Coquet, Y. Hu, J. Mémin, and S. Peng
2002
Earlier work this paper cites.
M. Frittelli and E. R. Gianin
2002
Earlier work this paper cites.
J. Vermorel and M. Mohri
2005
Earlier work this paper cites.

Similar

E. Even-Dar, S. Mannor, and Y. Mansour
2006
Cited alongside, same era.
reprint Dover 2006
F. H. Knight · 2006
Cited alongside, same era.
Reprint BN Publishing, 2008
J. M. Keynes · 2008
Cited alongside, same era.
P. Rusmevichientong, A. Mersereau, and J. N. Tsitsiklis
2009
Cited alongside, same era.
S. Filippi, O. Cappé, A. Garivier, and C. Szepesvári
2010
Cited alongside, same era.
arXiv:2006.05956
Original
D. Šiška and L. Szpruch · 2010
Cited alongside, same era.
E. Kaufmann, O. Cappé, and A. Garivier
2012

Then

H. Föllmer and A. Schied
2016
Later among the works it cites.
D. Russo and B. V. Roy
2016
Later among the works it cites.
N. Cesa-Bianchi, C. Gentile, G. Lugosi, and G. Neu
2017
Later among the works it cites.
J. Kirschner and A. Krause
2018
Later among the works it cites.
D. Russo, B. V. Roy, A. Kazerouni, I. Osband, and Z. Wen
2018
Later among the works it cites.
T. Lattimore and C. Szepesvári
2019
Later among the works it cites.
H. Wang, T. Zariphopoulou, and X. Zhou
2020
Closest in time.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…

Cited alongside, same era.

I. O. Ryzhov, W. B. Powell, and P. I. Frazier

2012

Cited alongside, same era.

V. Chernozhukov, D. Chetverikov, and K. Kato

2013

Cited alongside, same era.

G. Burtini, J. Loeppky, and R. Lawrence

2015

Cited alongside, same era.

S. N. Cohen

2016

Cited alongside, same era.

C. Reisinger and Y. Zhang

2021

Closest in time.

D. Russo

2021

Closest in time.

S. N. Cohen and T. Treetanthiploet

2022

Closest in time.