The Annals of Probability · 1987 · 70 citations · 11 references
Natural SciencesMathematicsProject ManagementDecision TheoryOptimizationStochastic ProcessesDynamic ProgrammingOptimal ControlResource AllocationStochastic ControlStochastic OptimizationStochastic ProgrammingAllocationBandit AlgorithmsContinuous-time Dynamic ProgrammingContinuous-time ModelsContinuous-time OptimizationStochastic BanditsStochastic Dynamic Optimization
A general framework is proposed for continuous time dynamic allocation models of a scarce resource among competing projects. The allocation model is formulated as a multi-armed bandit model and solved as a control problem of a multiparameter process. In contrast to discrete time bandits, where only one arm can be pulled at a time, the continuous time bandit must allow simultaneous pulls. The multiparameter approach allows a strong solution of diffusion-type bandits. Here the main problem is to define precisely how to switch among arms and the solution involves local times.
11
Diffusion Processes and their Sample Paths.
G. F. Newell, Kanae Ito, H. P. McKean · American Mathematical Monthly · 1968 · 1.1K citations