{"id":509,"date":"2023-06-12T14:04:37","date_gmt":"2023-06-12T14:04:37","guid":{"rendered":"https:\/\/webresources-uat.com\/acrp0361\/?post_type=glossary&#038;p=509"},"modified":"2023-06-12T14:04:37","modified_gmt":"2023-06-12T14:04:37","slug":"reinforcement-learning","status":"publish","type":"glossary","link":"https:\/\/crp.trb.org\/acrpwebresource18\/glossary\/reinforcement-learning\/","title":{"rendered":"Reinforcement Learning"},"content":{"rendered":"<p><span class=\"NormalTextRun SCXW127687911 BCX0\">Area of machine learning<\/span><span class=\"NormalTextRun SCXW127687911 BCX0\">&nbsp;concerned with how intelligent agents (artificial intelligence) <\/span><span class=\"NormalTextRun SCXW127687911 BCX0\">should<\/span> <span class=\"NormalTextRun SCXW127687911 BCX0\">take actions to maximize<\/span><span class=\"NormalTextRun SCXW127687911 BCX0\"> the notion of cumulative reward (<\/span><span class=\"NormalTextRun SCXW127687911 BCX0\">e.g., <\/span><span class=\"NormalTextRun SCXW127687911 BCX0\">Markov decision process).<\/span><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Area of machine learning&nbsp;concerned with how intelligent agents (artificial intelligence) should take actions to maximize the notion of cumulative reward (e.g., Markov decision process).<\/p>\n","protected":false},"author":111,"featured_media":0,"menu_order":0,"template":"","meta":{"_acf_changed":false,"footnotes":""},"glossary-categories":[],"glossary-tags":[],"class_list":["post-509","glossary","type-glossary","status-publish","hentry"],"acf":[],"_links":{"self":[{"href":"https:\/\/crp.trb.org\/acrpwebresource18\/wp-json\/wp\/v2\/glossary\/509","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/crp.trb.org\/acrpwebresource18\/wp-json\/wp\/v2\/glossary"}],"about":[{"href":"https:\/\/crp.trb.org\/acrpwebresource18\/wp-json\/wp\/v2\/types\/glossary"}],"author":[{"embeddable":true,"href":"https:\/\/crp.trb.org\/acrpwebresource18\/wp-json\/wp\/v2\/users\/111"}],"version-history":[{"count":0,"href":"https:\/\/crp.trb.org\/acrpwebresource18\/wp-json\/wp\/v2\/glossary\/509\/revisions"}],"wp:attachment":[{"href":"https:\/\/crp.trb.org\/acrpwebresource18\/wp-json\/wp\/v2\/media?parent=509"}],"wp:term":[{"taxonomy":"glossary-categories","embeddable":true,"href":"https:\/\/crp.trb.org\/acrpwebresource18\/wp-json\/wp\/v2\/glossary-categories?post=509"},{"taxonomy":"glossary-tags","embeddable":true,"href":"https:\/\/crp.trb.org\/acrpwebresource18\/wp-json\/wp\/v2\/glossary-tags?post=509"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}