Balanced Q-learning: combining the influence of optimistic and pessimistic targets (Q6067050): Difference between revisions
From MaRDI portal
Added link to MaRDI item. |
Set OpenAlex properties. |
||
Property / OpenAlex ID | |||
Property / OpenAlex ID: W3211287969 / rank | |||
Normal rank |
Revision as of 10:43, 30 July 2024
scientific article; zbMATH DE number 7777848
Language | Label | Description | Also known as |
---|---|---|---|
English | Balanced Q-learning: combining the influence of optimistic and pessimistic targets |
scientific article; zbMATH DE number 7777848 |
Statements
Balanced Q-learning: combining the influence of optimistic and pessimistic targets (English)
0 references
14 December 2023
0 references
reinforcement learning
0 references
maximization bias
0 references
\(Q\)-learning target
0 references
optimistic updates
0 references
pessimistic updates
0 references