Accelerating actor-critic-based algorithms via pseudo-labels derived from prior knowledge (Q6126872): Difference between revisions
From MaRDI portal
ReferenceBot (talk | contribs) Changed an Item |
Created claim: Wikidata QID (P12): Q129390077, #quickstatements; #temporary_batch_1726256605485 |
||
| Property / Wikidata QID | |||
| Property / Wikidata QID: Q129390077 / rank | |||
Normal rank | |||
Revision as of 20:47, 13 September 2024
scientific article; zbMATH DE number 7829860
| Language | Label | Description | Also known as |
|---|---|---|---|
| English | Accelerating actor-critic-based algorithms via pseudo-labels derived from prior knowledge |
scientific article; zbMATH DE number 7829860 |
Statements
Accelerating actor-critic-based algorithms via pseudo-labels derived from prior knowledge (English)
0 references
10 April 2024
0 references
reinforcement learning
0 references
deep RL
0 references
actor-critic methods
0 references
policy optimization
0 references
sample efficiency
0 references
exploration
0 references
0 references
