Bounds for the quality and the number of steps in Bellman's value iteration algorithm (Q1317533): Difference between revisions
From MaRDI portal
Set profile property. |
ReferenceBot (talk | contribs) Changed an Item |
||
| Property / cites work | |||
| Property / cites work: Q5599448 / rank | |||
Normal rank | |||
| Property / cites work | |||
| Property / cites work: A polynomial time bound for Howard's policy improvement algorithm / rank | |||
Normal rank | |||
| Property / cites work | |||
| Property / cites work: Q3730373 / rank | |||
Normal rank | |||
| Property / cites work | |||
| Property / cites work: On the Fixed Points of the Optimal Reward Operator in Stochastic Dynamic Programming with Discount Factor Greater than One / rank | |||
Normal rank | |||
| Property / cites work | |||
| Property / cites work: Bounds and good policies in stationary finite–stage Markovian decision problems / rank | |||
Normal rank | |||
| Property / cites work | |||
| Property / cites work: Abschätzungen für Spektralwerte / rank | |||
Normal rank | |||
Revision as of 12:41, 22 May 2024
scientific article
| Language | Label | Description | Also known as |
|---|---|---|---|
| English | Bounds for the quality and the number of steps in Bellman's value iteration algorithm |
scientific article |
Statements
Bounds for the quality and the number of steps in Bellman's value iteration algorithm (English)
0 references
27 March 1995
0 references
discounted Markovian decision process
0 references
finite state space
0 references
infinite horizon
0 references
sub-optimal decisions
0 references
\(\varepsilon\)-optimal policy
0 references
