Breaking the sample complexity barrier to regret-optimal model-free reinforcement learning (Q6039766)
From MaRDI portal
!
WARNING
This is the item page for this Wikibase entity, intended for internal use and editing purposes.
Please use the normal view instead:
scientific article; zbMATH DE number 7688060
| Language | Label | Description | Also known as |
|---|---|---|---|
| default for all languages | No label defined |
||
| English | Breaking the sample complexity barrier to regret-optimal model-free reinforcement learning |
scientific article; zbMATH DE number 7688060 |
Statements
Breaking the sample complexity barrier to regret-optimal model-free reinforcement learning (English)
0 references
23 May 2023
0 references
model-free RL
0 references
memory efficiency
0 references
variance reduction
0 references
Q-learning
0 references
upper confidence bounds
0 references
lower confidence bounds
0 references
0.7383135557174683
0 references
0.7338125109672546
0 references
0.7133070230484009
0 references
0.7075896859169006
0 references
