Fitted Value Function Iteration with Probability One Contractions
This paper studies a value function iteration algorithm based on nonexpansive function approximation and Monte Carlo integration that can be applied to almost all stationary dynamic programming problems. The method can be represented using a randomized fitted Bellman operator and a corresponding algorithm that is shown to be globally convergent with probability one. When additional restrictions are imposed, an OP(n-1/2) rate of convergence for Monte Carlo error is obtained.
|Collections||ANU Research Publications|
|Source:||Journal of Economic Dynamics and Control|
|01_Pal_Fitted_Value_Function_2013.pdf||309.49 kB||Adobe PDF||Request a copy|
|02_Pal_Fitted_Value_Function_2013.pdf||357.11 kB||Adobe PDF||Request a copy|
|03_Pal_Fitted_Value_Function_2013.pdf||673.52 kB||Adobe PDF||Request a copy|
Items in Open Research are protected by copyright, with all rights reserved, unless otherwise indicated.