Journal of the Royal Statistical Society Series B (Statistical Methodology) · 1980 · 530 citations · 9 references
BusinessEconomicsMathematicsMarkov Decision ProcessesOptimizationStochastic ProcessesDynamic ProgrammingOptimal StoppingReinforcement Learning FoundationsBandit AlgorithmsGittins IndexStochastic BanditsStochastic Dynamic Programming
Summary A plausible conjecture (C) has the implication that a relationship (12) holds between the maximal expected rewards for a multi-project process and for a one-project process (F and φi respectively), if the option of retirement with reward M is available. The validity of this relation and optimality of Gittins' index rule are verified simultaneously by dynamic programming methods. These results are partially extended to the case of so-called “bandit superprocesses”.
9
Discounted Dynamic Programming
David Blackwell · The Annals of Mathematical Statistics · 1965 · 947 citations · Full text