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...

Full description

Bibliographic Details

Main Authors:	Mohd Aris, Teh Noranis, Chen, Ningning, Mustapha, Norwati, Zolkepli, Maslina
Format:	Article
Language:	en
Published:	Public Library of Science 2025
Subjects:	Multidisciplinary
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!