Continuous State Dynamic Programming via Nonexpansive Approximation |
| |
| Authors: | John Stachurski |
| |
| Affiliation: | (1) Institute of Economic Research, Kyoto University, Yoshida-honmachi, Sakyo-ku, Kyoto 606-8501, Japan |
| |
| Abstract: | ![]()
This paper studies fitted value iteration for continuous state numerical dynamic programming using nonexpansive function approximators. A number of approximation schemes are discussed. The main contribution is to provide error bounds for approximate optimal policies generated by the value iteration algorithm. |
| |
| Keywords: | Numerical dynamic programming Nonexpansive approximation |
| 本文献已被 SpringerLink 等数据库收录！ |
