Instance-Dependent ℓ<sub>∞</sub>-Bounds for Policy Evaluation in Tabular Reinforcement Learning (Q5151732)
From MaRDI portal
scientific article; zbMATH DE number 7314046
| Language | Label | Description | Also known as |
|---|---|---|---|
| English | Instance-Dependent ℓ<sub>∞</sub>-Bounds for Policy Evaluation in Tabular Reinforcement Learning |
scientific article; zbMATH DE number 7314046 |
Statements
Instance-Dependent ℓ<sub>∞</sub>-Bounds for Policy Evaluation in Tabular Reinforcement Learning (English)
0 references
22 February 2021
0 references
Markov reward processes (MRPs)
0 references
stochastic phenomena
0 references
non-asymptotic bounds
0 references
