{"id":1217,"date":"2026-01-25T19:31:26","date_gmt":"2026-01-25T19:31:26","guid":{"rendered":"https:\/\/www.cs.ubbcluj.ro\/~meco\/evaluating-cooperative-competitive-dynamics-with-deep-q-learning-2023\/"},"modified":"2026-02-01T12:07:57","modified_gmt":"2026-02-01T12:07:57","slug":"evaluating-cooperative-competitive-dynamics-with-deep-q-learning-2023","status":"publish","type":"post","link":"https:\/\/www.cs.ubbcluj.ro\/~meco\/evaluating-cooperative-competitive-dynamics-with-deep-q-learning-2023\/","title":{"rendered":"Evaluating cooperative-competitive dynamics with deep Q-learning (2023)"},"content":{"rendered":"<div class=\"entry-content\">\n<p>Neurocomputing<\/p>\n<h2>Authors<\/h2>\n<p>Anik\u00f3 Kopacz, Lehel Csat\u00f3, Camelia Chira<\/p>\n<h2>Abstract<\/h2>\n<p>We model cooperative-competitive social group dynamics with multi-agent environments, specialized in cases with a large number of agents from only a few distinct types. The multi-agent optimization problems are addressed in turn with multi-agent reinforcement learning algorithms to obtain flexible and robust solutions. We analyze the effectiveness of centralized and decentralized algorithms using three variants of deep Q-networks on these cooperative-competitive environments: first, we use the decentralized training independent learning with deep Q-networks, secondly the centralized monotonic value factorizations for\u00a0deep learning, and lastly the multi-agent variational exploration. We test the algorithms in simulated predator\u2013prey multi-agent environments in two distinct environments: the\u00a0adversary pursuit\u00a0and\u00a0simple tag. The experiments highlight the performance of the different deep Q-learning methods, and we conclude that decentralized training of deep Q-networks accumulates higher episode rewards during training and evaluation in comparison with the selected centralized learning approaches.<\/p>\n<h2>Citation<\/h2>\n<pre class=\"wp-block-preformatted\">@Inproceedings{Kopacz2023EvaluatingCD,\n author = {Anik\u00f3 Kopacz and Lehel Csat\u00f3 and Camelia Chira},\n booktitle = {Neurocomputing},\n title = {Evaluating cooperative-competitive dynamics with deep Q-learning},\n year = {2023}\n}<\/pre>\n<\/div>\n","protected":false},"excerpt":{"rendered":"<p>We model cooperative-competitive social group dynamics with multi-agent environments, specialized in cases with a large number of agents from only a few distinct types. The multi-agent optimization problems are addressed in turn with multi-agent reinforcement learning algorithms to obtain flexible and robust solutions. We analyze the effectiveness of centralized and decentralized algorithms using three variants of deep Q-networks on these cooperative-competitive environments: first, we use the decentralized training independent learning with deep Q-networks, secondly the centralized monotonic value factorizations for deep learning, and lastly the multi-agent variational exploration. We test the algorithms in simulated predator\u2013prey multi-agent environments in two distinct environments: the adversary pursuit and simple tag. The experiments highlight the performance of the different deep Q-learning methods, and we conclude that decentralized training of deep Q-networks accumulates higher episode rewards during training and evaluation in comparison with the selected centralized learning approaches.<\/p>\n","protected":false},"author":6,"featured_media":0,"comment_status":"closed","ping_status":"","sticky":false,"template":"","format":"standard","meta":[],"categories":[4],"tags":[48,11,47],"_links":{"self":[{"href":"https:\/\/www.cs.ubbcluj.ro\/~meco\/wp-json\/wp\/v2\/posts\/1217"}],"collection":[{"href":"https:\/\/www.cs.ubbcluj.ro\/~meco\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.cs.ubbcluj.ro\/~meco\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.cs.ubbcluj.ro\/~meco\/wp-json\/wp\/v2\/users\/6"}],"replies":[{"embeddable":true,"href":"https:\/\/www.cs.ubbcluj.ro\/~meco\/wp-json\/wp\/v2\/comments?post=1217"}],"version-history":[{"count":1,"href":"https:\/\/www.cs.ubbcluj.ro\/~meco\/wp-json\/wp\/v2\/posts\/1217\/revisions"}],"predecessor-version":[{"id":1462,"href":"https:\/\/www.cs.ubbcluj.ro\/~meco\/wp-json\/wp\/v2\/posts\/1217\/revisions\/1462"}],"wp:attachment":[{"href":"https:\/\/www.cs.ubbcluj.ro\/~meco\/wp-json\/wp\/v2\/media?parent=1217"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.cs.ubbcluj.ro\/~meco\/wp-json\/wp\/v2\/categories?post=1217"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.cs.ubbcluj.ro\/~meco\/wp-json\/wp\/v2\/tags?post=1217"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}