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...

This paper studies fitted value iteration for continuous state dynamic programming using nonexpansive function approximators. A number of nonexpansive approximation schemes are discussed. The main contribution is to provide error bounds for approximate optimal policies generated by the value...

Dutta (J. Econom. Theory, 1991, 55, 64?94) showed that long-run optimality of the limit of discounted optima when the discount rate vanishes is implied by a certain bound on the value function of the optimal program. We introduce a new method to verify this bound using coupling techniques.