{"id":3923,"date":"2021-08-17T07:29:14","date_gmt":"2021-08-17T07:29:14","guid":{"rendered":"http:\/\/network.ee.tsinghua.edu.cn\/niulab\/?p=3923"},"modified":"2022-08-17T07:40:17","modified_gmt":"2022-08-17T07:40:17","slug":"smart-situationally-aware-multi-agent-reinforcement-learning-based-transmissions","status":"publish","type":"post","link":"https:\/\/network.ee.tsinghua.edu.cn\/niulab\/?p=3923","title":{"rendered":"SMART: Situationally-Aware Multi-Agent Reinforcement Learning-Based Transmissions"},"content":{"rendered":"<p><span class=\"paper_subtitle\">LANGUAGE English<\/span><\/p>\n<p><span class=\"paper_subtitle\">SOURCE\u00a0<strong> \u00a0IEEE Trans. Cognitive Commun. Networking, 2021, 7(4):1430-1443<\/strong><\/span><\/p>\n<p><span class=\"paper_subtitle\">Published Date: July 2021<\/span><\/p>\n<p><span class=\"paper_subtitle\">ABSTRACT\u00a0\u00a0<\/span><\/p>\n<p><span class=\"fontstyle0\">In future wireless systems, latency of information needs to be minimized to satisfy the requirements of many mission-critical applications. Meanwhile, not all terminals carry equally-urgent packets given their distinct situations, e.g., status freshness. Leveraging this feature, we propose an on-demand Medium Access Control (MAC) scheme, whereby each terminal transmits with dynamically adjusted aggressiveness based on its situations which are modeled as Markov states. A Multi-Agent Reinforcement Learning (MARL) framework is utilized and each agent is trained with a Deep Deterministic Policy Gradient (DDPG) network. A notorious issue for MARL is slow and nonscalable convergence \u2013 to address this, a new Situationally-aware MARL-based Transmissions (SMART) scheme is proposed. It is shown that SMART can significantly shorten the convergence time and the converged performance is also dramatically improved compared with state-of-the-art DDPG-based MARL schemes, at the expense of an additional offline training stage.<br \/>\nSMART also outperforms conventional MAC schemes significantly, e.g., Carrier Sensing and Multiple Access (CSMA), in terms of average and peak Age of Information (AoI). In addition, SMART also has the advantage of versatility \u2013 different Quality-of-Service (QoS) metrics and hence various state space definitions are tested in extensive simulations, where SMART shows robustness and scalability in all considered scenarios.<\/span><\/p>\n","protected":false},"excerpt":{"rendered":"<p><a href=\"https:\/\/network.ee.tsinghua.edu.cn\/niulab\/wp-content\/uploads\/2022\/08\/SMART_Situationally-Aware_Multi-Agent_Reinforcement_Learning-Based_Transmissions.pdf\" target=\"_blank\" rel=\"noopener\"><img loading=\"lazy\" decoding=\"async\" class=\"alignleft size-full wp-image-117\" title=\"pdf\" src=\"https:\/\/network.ee.tsinghua.edu.cn\/niulab\/wp-content\/uploads\/2010\/08\/pdf.gif\"alt=\"\" width=\"95\" height=\"50\" \/><\/a>Z. Jiang, Y. Liu, J. Hribar, L. A. DaSilva, S. Zhou, and Z. Niu, SMART: Situationally-Aware Multi-Agent Reinforcement Learning-Based Transmissions, <span class=\"papersource\">IEEE Trans. Cognitive Commun. Networking, 2021, 7(4):1430-1443.<\/span><\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_jetpack_memberships_contains_paid_content":false,"footnotes":""},"categories":[7],"tags":[100],"jetpack_sharing_enabled":true,"jetpack_featured_media_url":"","_links":{"self":[{"href":"https:\/\/network.ee.tsinghua.edu.cn\/niulab\/index.php?rest_route=\/wp\/v2\/posts\/3923"}],"collection":[{"href":"https:\/\/network.ee.tsinghua.edu.cn\/niulab\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/network.ee.tsinghua.edu.cn\/niulab\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/network.ee.tsinghua.edu.cn\/niulab\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/network.ee.tsinghua.edu.cn\/niulab\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=3923"}],"version-history":[{"count":0,"href":"https:\/\/network.ee.tsinghua.edu.cn\/niulab\/index.php?rest_route=\/wp\/v2\/posts\/3923\/revisions"}],"wp:attachment":[{"href":"https:\/\/network.ee.tsinghua.edu.cn\/niulab\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=3923"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/network.ee.tsinghua.edu.cn\/niulab\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=3923"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/network.ee.tsinghua.edu.cn\/niulab\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=3923"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}