Dual experience replay enhanced deep deterministic policy gradient for efficient continuous data sampling
To address the inefficiencies in sample utilization and policy instability in asynchronous distributed reinforcement learning, we propose TPDEB—a dual experience replay framework that integrates prioritized sampling and temporal diversity. While recent distributed RL systems have scaled well, they o...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | en |
| Published: |
Public Library of Science
2025
|
| Subjects: | |
| Online Access: | http://psasir.upm.edu.my/id/eprint/124660/1/124660.pdf http://psasir.upm.edu.my/id/eprint/124660/ https://dx.plos.org/10.1371/journal.pone.0334411 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|