首页|期刊导航|High Technology Letters|SPaRM: an efficient exploration and planning framework for sparse reward reinforcement learning

SPaRM: an efficient exploration and planning framework for sparse reward reinforcement learning

BAN Jian LI Gongyan XU Shaoyun

High Technology Letters2024，Vol.30Issue(4)：P.344-355,12.

High Technology Letters2024，Vol.30Issue(4)：P.344-355,12.DOI:10.3772/j.issn.1006-6748.2024.04.002

SPaRM: an efficient exploration and planning framework for sparse reward reinforcement learning

BAN Jian ¹LI Gongyan ²XU Shaoyun²

作者信息

1. Institute of Microelectronics,Chinese Academy of Sciences,Beijing 100029,P.R.China University of Chinese Academy of Sciences,Beijing 100049,P.R.China
2. Institute of Microelectronics,Chinese Academy of Sciences,Beijing 100029,P.R.China
折叠

摘要

关键词

reinforcement learning(RL)/sparse reward,reward-free exploration(RFE)/space partitioning(SP)/reverse merging(RM)

分类

信息技术与安全科学

引用本文复制引用

BAN Jian,LI Gongyan,XU Shaoyun..SPaRM: an efficient exploration and planning framework for sparse reward reinforcement learning[J].High Technology Letters,2024,30(4):P.344-355,12.

基金项目

Supported by the International Partnership Program of Chinese Academy of Sciences(No.184131KYSB20200033). （No.184131KYSB20200033）

High Technology Letters

ISSN：1006-6748

访问量0

下载量0

段落导航