Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
7377246 | Physica A: Statistical Mechanics and its Applications | 2016 | 5 Pages |
Abstract
Bellman's equation is widely used in solving stochastic optimal control problems in a variety of applications including investment planning, scheduling problems and routing problems. Building on Markov decision processes for stationary policies, we present a new proof for Bellman's equation of optimality. Our proof rests its case on the availability of an explicit model of the environment that embodies transition probabilities and associated costs.
Related Topics
Physical Sciences and Engineering
Mathematics
Mathematical Physics
Authors
Eitan Gross,