Sample-Efficient Reinforcement Learning with Temporal Logic Objectives: Leveraging the Task Specification to Guide Exploration

IF 6.2 1区计算机科学 Q1 AUTOMATION & CONTROL SYSTEMS

IEEE Transactions on Automatic Control Pub Date : 2024-10-21 DOI:10.1109/tac.2024.3484290

Yiannis Kantaros, Jun Wang

引用次数: 0

查看原文本刊更多论文

具有时态逻辑目标的样本高效强化学习：利用任务规范指导探索

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

IEEE Transactions on Automatic Control 工程技术-工程：电子与电气

CiteScore

11.30

自引率

5.90%

发文量

824

审稿时长

9 months

期刊介绍： In the IEEE Transactions on Automatic Control, the IEEE Control Systems Society publishes high-quality papers on the theory, design, and applications of control engineering. Two types of contributions are regularly considered: 1) Papers: Presentation of significant research, development, or application of control concepts. 2) Technical Notes and Correspondence: Brief technical notes, comments on published areas or established control topics, corrections to papers and notes published in the Transactions. In addition, special papers (tutorials, surveys, and perspectives on the theory and applications of control systems topics) are solicited.