Abstract
| Original language | English |
|---|---|
| Place of Publication | Eindhoven |
| Publisher | Technische Hogeschool Eindhoven |
| Number of pages | 28 |
| Publication status | Published - 1979 |
Publication series
| Name | Memorandum COSOR |
|---|---|
| Volume | 7907 |
| ISSN (Print) | 0926-4493 |
Fingerprint
Cite this
}
The method of value oriented successive approximations for the average reward Markov decision process. / Wal, van der, J.
Eindhoven : Technische Hogeschool Eindhoven, 1979. 28 p. (Memorandum COSOR; Vol. 7907).Research output: Book/Report › Report › Academic
TY - BOOK
T1 - The method of value oriented successive approximations for the average reward Markov decision process
AU - Wal, van der, J.
PY - 1979
Y1 - 1979
N2 - In this paper we consider the Markov decision process with finite state and action spaces at the criterion of average reward per unit time. We will consider the method of value oriented successive approximations which has been extensively studied by Van Nunen for the total reward case. Under various conditions which guarantee the gain of the process to be independent of the starting state and a strong aperiodicity assumption we show that the method converges and produces e-optimal policies.
AB - In this paper we consider the Markov decision process with finite state and action spaces at the criterion of average reward per unit time. We will consider the method of value oriented successive approximations which has been extensively studied by Van Nunen for the total reward case. Under various conditions which guarantee the gain of the process to be independent of the starting state and a strong aperiodicity assumption we show that the method converges and produces e-optimal policies.
M3 - Report
T3 - Memorandum COSOR
BT - The method of value oriented successive approximations for the average reward Markov decision process
PB - Technische Hogeschool Eindhoven
CY - Eindhoven
ER -