EMExplorer: an episodic memory enhanced autonomous exploration strategy with Voronoi domain conversion and invalid action masking

EMExplorer: an episodic memory enhanced autonomous exploration strategy with Voronoi domain conversion and invalid action masking

Abstract Autonomous exploration is a critical technology to realize robotic intelligence as it allows unsupervised preparation for future tasks and facilitates flexible deployment. In this paper, a novel Deep Reinforcement Learning (DRL) based autonomous exploration strategy is proposed to efficient...

Full description

Bibliographic Details
Main Authors: Bolei Chen, Ping Zhong, Yongzheng Cui, Siyi Lu, Yixiong Liang, Yu Sheng
Format: Article
Language:English
Published: Springer 2023-06-01
Series:Complex & Intelligent Systems
Subjects:
Autonomous exploration
Episodic memory
Deep reinforcement learning
Generalized Voronoi diagram
Invalid action masking
Online Access:https://doi.org/10.1007/s40747-023-01144-x

Internet

https://doi.org/10.1007/s40747-023-01144-x

Similar Items