Prioritized experience replay in path planning via multi-dimensional transition priority fusion

Prioritized experience replay in path planning via multi-dimensional transition priority fusion

IntroductionDeep deterministic policy gradient (DDPG)-based path planning algorithms for intelligent robots struggle to discern the value of experience transitions during training due to their reliance on a random experience replay. This can lead to inappropriate sampling of experience transitions a...

Full description

Bibliographic Details
Main Authors: Nuo Cheng, Peng Wang, Guangyuan Zhang, Cui Ni, Erkin Nematov
Format: Article
Language:English
Published: Frontiers Media S.A. 2023-11-01
Series:Frontiers in Neurorobotics
Subjects:
deep reinforcement learning
deep deterministic policy gradient
prioritized experience replay
multi-dimensional transition priority
priority fusion
Online Access:https://www.frontiersin.org/articles/10.3389/fnbot.2023.1281166/full

Internet

https://www.frontiersin.org/articles/10.3389/fnbot.2023.1281166/full

Similar Items