Variance-penalized Markov decision processes: dynamic programming and reinforcement learning techniques (Q5166474)
From MaRDI portal
 | This is the item page for this Wikibase entity, intended for internal use and editing purposes. Please use this page instead for the normal view: Variance-penalized Markov decision processes: dynamic programming and reinforcement learning techniques |
scientific article; zbMATH DE number 6309105
| Language | Label | Description | Also known as |
|---|---|---|---|
| default for all languages | No label defined |
||
| English | Variance-penalized Markov decision processes: dynamic programming and reinforcement learning techniques |
scientific article; zbMATH DE number 6309105 |
Statements
Variance-penalized Markov decision processes: dynamic programming and reinforcement learning techniques (English)
0 references
27 June 2014
0 references
variance-penalized MDPs
0 references
dynamic programming
0 references
risk penalties
0 references
reinforcement learning
0 references
Bellman equation
0 references
0.9613733
0 references
0.9531313
0 references
0.94589746
0 references
0.93408614
0 references
0 references
0.9138828
0 references
0.91324425
0 references
