Name
Abstract | ||
|---|---|---|
In this paper, we analyze the asymptotic behaviour of the value function vt of an undiscounted continuous-time Markov decision chain. Both the state space and the action space are assumed to be finite. A new proof of the convergence of vt-tg is presented where g denotes the maximal expected average reward over an infinite time horizon. Moreover, it is shown that this convergence is exponential. |
Year | DOI | Venue |
|---|---|---|
1987 | 10.1287/moor.12.4.700 | Math. Oper. Res. |
Keywords | DocType | Volume |
average reward criterion,continuous time,undiscounted continuous-time markov decision,markov decision chain,value function,exponential convergence | Journal | 12 |
Issue | ISSN | Citations |
4 | 0364-765X | 0 |
PageRank | References | Authors |
0.34 | 0 | 1 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| W. H. M. Zijm | 1 | 162 | 23.24 |