On Convergence Rate of MRetrace
Off-policy is a key setting for reinforcement learning algorithms. In recent years, the stability of off-policy learning for value-based reinforcement learning has been guaranteed even when combined with linear function approximation and bootstrapping. Convergence rate analysis is currently a hot to...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-09-01
|
| Series: | Mathematics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-7390/12/18/2930 |