On Upper-Confidence Bound Policies for Non-Stationary Bandit Problems

Asymptotically efficient adaptive allocation rules

T. L. Lai and Herbert Robbins · 1985

Earlier work this paper cites.

Restless bandits: activity allocation in a changing world

P. Whittle · 1988

Earlier work this paper cites.

Sample mean based index policies with O ⁡ ( log ⁡ n ) O(\log n) regret for the multi-armed bandit problem

R. Agrawal · 1995

Earlier work this paper cites.

A decision-theoretic generalization of on-line learning and an application to boosting

Yoav Freund and Robert E. Schapire · 1995

Earlier work this paper cites.

A probabilistic theory of pattern recognition , volume 31 of Applications of Mathematics (New York)

L. Devroye, L. Györfi, and G. Lugosi · 1996

Earlier work this paper cites.

Tracking the best expert

M. Herbster and M.K. Warmuth · 1998

Earlier work this paper cites.

On prediction of individual sequences

Nicolò Cesa-Bianchi and Gábor Lugosi · 1999

Earlier work this paper cites.

Finite-time lower bounds for the two-armed bandit problem

S. R. Kulkarni and G. Lugosi · 2000

Cited alongside, same era.

The nonstochastic multiarmed bandit problem

P. Auer, N. Cesa-Bianchi, Y. Freund, and R.E. Schapire · 2002

Cited alongside, same era.

Using confidence bounds for exploitation-exploration trade-offs

Peter Auer · 2002

Cited alongside, same era.

Finite-time analysis of the multiarmed bandit problem

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

Cited alongside, same era.

Prediction, Learning, and Games

Nicolo Cesa-Bianchi and Gabor Lugosi · 2006

Cited alongside, same era.

Regret minimization under partial monitoring

Nicolò Cesa-Bianchi, Gábor Lugosi, and Gilles Stoltz · 2006

Cited alongside, same era.

Discounted UCB

L. Kocsis and C. Szepesvári · 2006

Later among the works it cites.

Tuning bandit algorithms in stochastic environments

J-Y. Audibert, R. Munos, and A. Szepesvári · 2007

Later among the works it cites.

Cognitive medium access: Exploration, exploitation and competition, 2007

L. Lai, H. El Gamal, H. Jiang, and H. V. Poor · 2007

Later among the works it cites.

Competing with typical compound actions, 2008

Nicolò Cesa-Bianchi, Gábor Lugosi, and Gilles Stoltz · 2008

Closest in time.

Reinforcement learning and evolutionary algorithms for non-stationary multi-armed bandit problems

D. E. Koulouriotis and A. Xanthopoulos · 2008

Closest in time.

Adapting to a changing environment: the brownian restless bandits, 2008

A. Slivkins and E. Upfal · 2008

Closest in time.