Exploration and Exploitation Balanced Experience Replay

Experience replay can reuse past experience to update target policy and improve the utilization of samples,which has become an important component of deep reinforcement learning.Prioritized experience replay performs selective sampling based on experience replay to use samples more efficiently.Never...

Full description

Bibliographic Details

Published in:	Jisuanji kexue
Main Author:	ZHANG Jia-neng, LI Hui, WU Hao-lin, WANG Zhuang
Format:	Article
Language:	Chinese
Published:	Editorial office of Computer Science 2022-05-01
Subjects:	reinforcement learning|experience replay|priority sampling|exploitation|exploration|soft actor-critic algorithm
Online Access:	https://www.jsjkx.com/fileup/1002-137X/PDF/1002-137X-2022-49-5-179.pdf