Feedback Approximation of the Stochastic Growth Model by Genetic Neural Networks

Sibel Sirakaya(a) Stephen Turnovsky(b);y M. Nedim Alemdar(c)

a. Departments of Economics and Statistics, and CSSS,
University of Washington, Seattle, WA 98195
b. Department of Economics, University of Washington, Seattle, WA 98195
c. Department of Economics, Bilkent University, 06800 Bilkent, Ankara, Turkey

A direct numerical optimization method is developed to approximate the one-sector stochastic growth model. The feedback investment policy is parameterized as a neural network and trained by a genetic algorithm to maximize the utility functional over the space of time-invariant investment policies. To eliminate the dependence of training on the initial conditions, at any generation, the same stationary investment policy (the same network) is used to repeatedly solve the problem from di®ering initial conditions. The ¯tness of a given policy rule is then computed as the sum of payo®s over all initial conditions. The algorithm performs quite well under a wide set of parameters. Given the general purpose nature of the method, the °exibility of neural network parametrization and the global nature of the genetic algorithm search, it can be easily extended to tackle problems with higher dimensional nonlinearities, state spaces and/or discontinuities.

<more | download>