Diverse randomized value functions: a provably pessimistic approach for offline reinforcement learning (Q6595316)
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: Diverse randomized value functions: a provably pessimistic approach for offline reinforcement learning |
scientific article; zbMATH DE number 7903571
| Language | Label | Description | Also known as |
|---|---|---|---|
| English | Diverse randomized value functions: a provably pessimistic approach for offline reinforcement learning |
scientific article; zbMATH DE number 7903571 |
Statements
Diverse randomized value functions: a provably pessimistic approach for offline reinforcement learning (English)
0 references
30 August 2024
0 references
offline reinforcement learning
0 references
randomized value functions
0 references
pessimism
0 references
diversification
0 references
distributional shift
0 references
