A novel policy based on action confidence limit to improve exploration efficiency in reinforcement learning (Q6121659)
From MaRDI portal
scientific article; zbMATH DE number 7824802
| Language | Label | Description | Also known as |
|---|---|---|---|
| English | A novel policy based on action confidence limit to improve exploration efficiency in reinforcement learning |
scientific article; zbMATH DE number 7824802 |
Statements
A novel policy based on action confidence limit to improve exploration efficiency in reinforcement learning (English)
0 references
26 March 2024
0 references
reinforcement learning
0 references
exploration policy
0 references
action confidence limit
0 references
uncertainty of action
0 references
deep auto-encoder network
0 references
0 references
0 references
0 references
