Journal of the Royal Statistical Society Series B (Statistical Methodology) · 1980 · 36 citations · 4 references
BusinessDecision SciencesDecision TheoryMarkov Decision ProcessesOptimizationDynamic ProgrammingOptimal ControlReinforcement LearningReinforcement Learning FoundationsResource AllocationBandit AlgorithmsMulti-armed Bandit OptimizationStochastic BanditsStochastic Dynamic Optimization
Summary A multi-armed bandit problem is investigated in which rewards obtained from pulls of any arm depend on the states of the other arms, as well as on the state of the arm pulled. A Dynamic Allocation Index is defined for this class of problems, and it is shown that this leads to optimal policies.
4
Discounted Dynamic Programming
David Blackwell · The Annals of Mathematical Statistics · 1965 · 947 citations · Full text
Introduction to stochastic control
David D. Sworder · IEEE Transactions on Automatic Control · 1972 · 399 citations