Abstract
The Onsager–Machlup Lagrangian is shown to have a direct relevance to a cost function for a stochastic control problem. It is found that any stationary diffusion process can be regarded as a solution to the stochastic control problem, that is, it is controlled optimally by the Onsager–Machlup Lagrangian. A deterministic limit of the stationary diffusion process is also obtained as a solution to an ordinary (nonrandom) control problem which is equivalent to the usual variational problem with respect to the Onsager–Machlup Lagrangian.

This publication has 15 references indexed in Scilit: