Prioritized experience replay based on dynamics priority

Abstract Experience replay has been instrumental in achieving significant advancements in reinforcement learning by increasing the utilization of data. To further improve the sampling efficiency, prioritized experience replay (PER) was proposed. This algorithm prioritizes experiences based on the te...

Full description

Bibliographic Details
Published in:Scientific Reports
Main Authors: Hu Li, Xuezhong Qian, Wei Song
Format: Article
Language:English
Published: Nature Portfolio 2024-03-01
Subjects:
Online Access:https://doi.org/10.1038/s41598-024-56673-3