Results 181 to 190 of about 18,568,643 (214)

Numerical Investigation of the Two Armed Bandit

1983
This paper is concerned with Bernoulli two armed bandits with independent beta priors for the unknown success probabilities where there are a finite number of trials, N, and the objective is to maximise the overall expected return. The two armed bandit with one probability known is also considered.
P. W. Jones, H. A. Kandeel
openaire   +1 more source

Time horizons of pigeons on a two-armed bandit

Animal Behaviour, 1989
Abstract Time available for foraging (time horizon) should influence optimal behaviour according to some foraging models. When animals encounter two patches of unknown density (a two-armed bandit) there should be more sampling before sustained exploitation of the better patch when the time horizon is long than when it is short.
Sara J. Shettleworth, Catherine M.S. Plowright   +1 more
openaire   +1 more source

Good news and bad news in two-armed bandits

Journal of Economic Theory, 2007
zbMATH Open Web Interface contents unavailable due to conflicting licenses.
openaire   +1 more source

Finite-Time Performance of Some Two-Armed Bandit Controllers

IEEE Transactions on Systems, Man, and Cybernetics, 1973
A class of asymptotically ?-optimal two-armed bandit controllers is given, and two criteria for comparing the long-term finite-time performance of controllers in this class are proposed. The performances of three particular controllers are compared using the criteria, and the analysis is confirmed by computer iteration if the appropriate probability ...
openaire   +3 more sources

Monotone Decision Rules for the Two-Armed Bandit

1984
Consider the following problem in sequential design: Two Bernoulli experiments called arm 1 and arm 2 are given with unknown success probabilities. We consider them as random variables with a joint prior distribution μ not concentrated on the boundary of [0, 1]2. The aim is to maximize the expected number of successes in N trials by choosing one of the
Harald Benzing, Michael Kolonko
openaire   +1 more source

Some results for the two armed bandit problem

Optimization, 1976
The paper is concerned with the optimal dynamic programming approach to the solution of the two armed bandit problem for beta priors for the two unknown probabilities. Some properties of the objctive function are obtained and a conjecture concerning the design is made.
openaire   +2 more sources

The Two-Armed Bandit

Biometrika, 1975
openaire   +1 more source

A One-Armed Bandit Problem with a Concomitant Variable

Journal of the American Statistical Association, 1979
Michael Woodroofe
exaly   +2 more sources

Bayesian rules for the two-armed bandit problem

Biometrika, 1977
Wahrenberger, David L., Antle, Charles E., Klimko, Lawrence A.   +2 more
openaire   +2 more sources

The Minimax Risk for the Two-Armed Bandit Problem

1983
Let r be the number of successes scored in t independent trials, each of which must be allocated to one of two experiments, where the probabilities p1, p2 of success in these experiments are both unknown. For any allocation rule Δ, the expected number of successes lost as a result of ignorance is $${L_\Delta}({p_1},{p_2},t) = t{\kern 1pt} \max ...
openaire   +1 more source