Risk-sensitive and minimax control of discrete-time, finite-state Markov decision processes (Q1295095): Difference between revisions
From MaRDI portal
Added link to MaRDI item. |
Removed claim: reviewed by (P1447): Item:Q731708 |
||
| Property / reviewed by | |||
| Property / reviewed by: Makiko Nisio / rank | |||
Revision as of 14:27, 20 February 2024
scientific article
| Language | Label | Description | Also known as |
|---|---|---|---|
| English | Risk-sensitive and minimax control of discrete-time, finite-state Markov decision processes |
scientific article |
Statements
Risk-sensitive and minimax control of discrete-time, finite-state Markov decision processes (English)
0 references
5 December 1999
0 references
This paper analyzes a connection between risk-sensitive and minimax criteria for discrete-time, finite state Markovian decision processes. The authors show dynamic programming for both criteria and synthesized optimal policies. Moreover, they formulate optimal risk-sensitive and minimax decision-making, in a general setting, which leads to stationary discounted optimal policies on the infinite horizon.
0 references
risk-sensitive control
0 references
minimax control
0 references
discrete-time, finite state Markovian decision processes
0 references
dynamic programming
0 references
optimal policies
0 references
minimax decision-making
0 references
