mistat (version 2.0.3)

dynOAB: Dynamic programming of the optimal One-Armed Bandits

Description

Dynamic programming of the optimal One-Armed Bernoulli Bandits process

Usage

dynOAB(N, al)

Arguments

N

number of trials.

al

the known probability of reward on arm A.

Value

For dynOAB the matrix of maximal predicted rewards. For dynOAB2 the optimal predicted reward.

See Also

simOAB

Examples

# NOT RUN {
dynOAB(10, 0.5)
dynOAB2(10, 0.5)
# }