{"id":788,"date":"2018-03-10T09:40:54","date_gmt":"2018-03-10T08:40:54","guid":{"rendered":"http:\/\/babel.isa.uma.es\/kipr\/?p=788"},"modified":"2018-07-13T09:43:39","modified_gmt":"2018-07-13T08:43:39","slug":"multi-agent-reinfocerment-learning-for-working-with-high-dimensional-spaces","status":"publish","type":"post","link":"https:\/\/babel.isa.uma.es\/kipr\/?p=788","title":{"rendered":"Multi-agent reinfocerment learning for working with high-dimensional spaces"},"content":{"rendered":"<h4>David L. Leottau, Javier Ruiz-del-Solar, Robert Babu\u0161ka, <strong>Decentralized Reinforcement Learning of Robot Behaviors<\/strong>, Artificial Intelligence, Volume 256, 2018, Pages 130-159, <a href=\"http:\/\/doi.org\/10.1016\/j.artint.2017.12.001\" target=\"_blank\">DOI: 10.1016\/j.artint.2017.12.001<\/a>.<\/h4>\n<blockquote><p>A multi-agent methodology is proposed for Decentralized Reinforcement Learning (DRL) of individual behaviors in problems where multi-dimensional action spaces are involved. When using this methodology, sub-tasks are learned in parallel by individual agents working toward a common goal. In addition to proposing this methodology, three specific multi agent DRL approaches are considered: DRL-Independent, DRL Cooperative-Adaptive (CA), and DRL-Lenient. These approaches are validated and analyzed with an extensive empirical study using four different problems: 3D Mountain Car, SCARA Real-Time Trajectory Generation, Ball-Dribbling in humanoid soccer robotics, and Ball-Pushing using differential drive robots. The experimental validation provides evidence that DRL implementations show better performances and faster learning times than their centralized counterparts, while using less computational resources. DRL-Lenient and DRL-CA algorithms achieve the best final performances for the four tested problems, outperforming their DRL-Independent counterparts. Furthermore, the benefits of the DRL-Lenient and DRL-CA are more noticeable when the problem complexity increases and the centralized scheme becomes intractable given the available computational resources and training time.<\/p><\/blockquote>\n","protected":false},"excerpt":{"rendered":"<p>David L. Leottau, Javier Ruiz-del-Solar, Robert Babu\u0161ka, Decentralized Reinforcement Learning of Robot Behaviors, Artificial Intelligence, Volume 256, 2018, Pages 130-159, <span class=\"ellipsis\">&hellip;<\/span> <span class=\"more-link-wrap\"><a href=\"https:\/\/babel.isa.uma.es\/kipr\/?p=788\" class=\"more-link\"><span>Read More &rarr;<\/span><\/a><\/span><\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[14,84],"tags":[323],"class_list":["post-788","post","type-post","status-publish","format-standard","hentry","category-applications-of-reinforcement-learning-to-robots","category-reinforcement-learning-in-ai","tag-multiagent-systems"],"_links":{"self":[{"href":"https:\/\/babel.isa.uma.es\/kipr\/index.php?rest_route=\/wp\/v2\/posts\/788"}],"collection":[{"href":"https:\/\/babel.isa.uma.es\/kipr\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/babel.isa.uma.es\/kipr\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/babel.isa.uma.es\/kipr\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/babel.isa.uma.es\/kipr\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=788"}],"version-history":[{"count":1,"href":"https:\/\/babel.isa.uma.es\/kipr\/index.php?rest_route=\/wp\/v2\/posts\/788\/revisions"}],"predecessor-version":[{"id":789,"href":"https:\/\/babel.isa.uma.es\/kipr\/index.php?rest_route=\/wp\/v2\/posts\/788\/revisions\/789"}],"wp:attachment":[{"href":"https:\/\/babel.isa.uma.es\/kipr\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=788"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/babel.isa.uma.es\/kipr\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=788"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/babel.isa.uma.es\/kipr\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=788"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}