MetaCart Sign in to MyCiteSeerX

Include Citations | Advanced Search | Help

Disambiguated Search | Include Citations | Advanced Search | Help

Gambling in a Rigged Casino: The adversarial multi-armed bandit problem (1998) [108 citations — 6 self]

Abstract:

In the multi-armed bandit problem, a gambler must decide which arm of K non-identical slot machines to play in a sequence of trials so as to maximize his reward. This classical problem has received much attention because of the simple model it provides of the trade-off between exploration (trying out each arm to find the best one) and exploitation (playing the arm believed to give the best payoff). Past solutions for the bandit problem have almost always relied on assumptions about the statistics of the slot machines.

Citations

4923 Elements of Information Theory – Cover, Thomas - 1991
1205 Schapire, “Decision-theoretic generalization of on-line learning and application to boosting – Freund, E - 1997
438 The weighted majority algorithm – Littlestone, Warmuth - 1994
228 How to use expert advice – Cesa-Bianchi, Freund, et al. - 1997
98 Approximation to Bayes risk in repeated play – Hannan - 1957
87 Multi-Armed Bandit Allocation Indices – Gittins - 1989
86 Some aspects of the sequential design of experiments – Robbins - 1952
62 Asymptotically efficient adaptive allocation rules – Lai, Robbins - 1985
54 Consistency and cautious fictitious play – Fudenberg, Levine - 1995
28 Discrete-Parameter Martingales – Neveu - 1975
26 A randomization rule for selecting forecasts – Foster, Vohra - 1993
19 to use expert advice – How - 1997
15 On repeated games with incomplete information played by non-Bayesian players – Megiddo - 1980
13 On pseudo-games – Baños - 1968
9 Multi-armed bandit problem revisited – Ishikida, Varaiya - 1994
6 Controlled random walks. invited address – Blackwell - 1956
1 On pseudo-games. The Annals of Mathematical Statistics – Banos - 1968
1 Controlled random walks. invited address, Institute of Mathematical Statistics Meeting – Blackwell - 1956