A unified approach to Markov decision problems and performance sensitivity analysis with discounted and average criteria: multichain cases (Q705478)
From MaRDI portal
!
This is the item page for this Wikibase entity, intended for internal use and editing purposes. Please use the normal view instead:
scientific article; zbMATH DE number 2131559
| Language | Label | Description | Also known as |
|---|---|---|---|
| default for all languages | No label defined |
||
| English | A unified approach to Markov decision problems and performance sensitivity analysis with discounted and average criteria: multichain cases |
scientific article; zbMATH DE number 2131559 |
Statements
A unified approach to Markov decision problems and performance sensitivity analysis with discounted and average criteria: multichain cases (English)
0 references
31 January 2005
0 references
Policy iteration
0 references
Potentials
0 references
Perturbation analysis
0 references
Performance sensitivity
0 references
Reinforcement learning
0 references
0.8894953727722168
0 references
0.8017292022705078
0 references
0.7849117517471313
0 references
