Balanced Q-learning: combining the influence of optimistic and pessimistic targets (Q6067050)
From MaRDI portal
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
