Conservative and Risk-Aware Offline Multi-Agent Reinforcement Learning

IF 7.4 1区计算机科学 Q1 TELECOMMUNICATIONS

IEEE Transactions on Cognitive Communications and Networking Pub Date : 2024-11-14 DOI:10.1109/tccn.2024.3499357

Eslam Eldeeb, Houssem Sifaou, Osvaldo Simeone, Mohammad Shehab, Hirley Alves

引用次数: 0

查看原文本刊更多论文

保守和风险意识离线多代理强化学习

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 Cognitive Communications and Networking Computer Science-Artificial Intelligence

CiteScore

15.50

自引率

7.00%

发文量

108

期刊介绍： The IEEE Transactions on Cognitive Communications and Networking (TCCN) aims to publish high-quality manuscripts that push the boundaries of cognitive communications and networking research. Cognitive, in this context, refers to the application of perception, learning, reasoning, memory, and adaptive approaches in communication system design. The transactions welcome submissions that explore various aspects of cognitive communications and networks, focusing on innovative and holistic approaches to complex system design. Key topics covered include architecture, protocols, cross-layer design, and cognition cycle design for cognitive networks. Additionally, research on machine learning, artificial intelligence, end-to-end and distributed intelligence, software-defined networking, cognitive radios, spectrum sharing, and security and privacy issues in cognitive networks are of interest. The publication also encourages papers addressing novel services and applications enabled by these cognitive concepts.