Is Q-Learning Minimax Optimal? A Tight Sample Complexity Analysis (Q6198738)
From MaRDI portal
scientific article; zbMATH DE number 7821757
| Language | Label | Description | Also known as |
|---|---|---|---|
| English | Is Q-Learning Minimax Optimal? A Tight Sample Complexity Analysis |
scientific article; zbMATH DE number 7821757 |
Statements
Is Q-Learning Minimax Optimal? A Tight Sample Complexity Analysis (English)
0 references
20 March 2024
0 references
Q-learning
0 references
temporal difference learning
0 references
effective horizon
0 references
sample complexity
0 references
minimax optimality
0 references
lower bound
0 references
overestimation
0 references
