{"id":34439,"date":"2025-05-04T21:39:07","date_gmt":"2025-05-04T18:39:07","guid":{"rendered":"https:\/\/w3.bilkent.edu.tr\/tr\/?p=34439"},"modified":"2025-05-05T22:52:24","modified_gmt":"2025-05-05T19:52:24","slug":"math-seminer-entropy-regularized-stochastic-control-and-mean-field-games-gunes-akbas-1530-5-mayis-2025-en","status":"publish","type":"post","link":"https:\/\/w3.bilkent.edu.tr\/tr\/math-seminer-entropy-regularized-stochastic-control-and-mean-field-games-gunes-akbas-1530-5-mayis-2025-en\/","title":{"rendered":"MATH Semineri: \u201cEntropy-Regularized Stochastic Control and Mean Field Games\u201d, G\u00fcne\u015f Akba\u015f, 15:30 5 May\u0131s 2025 (EN)"},"content":{"rendered":"<p>You are cordially invited to the Analysis Seminar organized by the Department of Mathematics.<\/p>\n<p>Speaker: : G\u00fcne\u015f Akba\u015f (Bilkent)<\/p>\n<p>&#8220;Entropy-Regularized Stochastic Control and Mean Field Games&#8221;<\/p>\n<p>Abstract: Starting from controlled Markov processes with an infinite-horizon average-cost objective, we add an entropy penalty that turns the hard minimum in the Bellman equation into a soft minimum, converting deterministic actions into well-behaved stochastic policies.<br \/>\nThe same regularization is then lifted to mean field games, where the transition kernel and payoff depend on the evolving population distribution. Under Lipschitz continuity, the soft-min map becomes contractive, so alternating policy optimization with population updates converges to a stationary mean-field equilibrium. Entropy regularization thus offers a concise, scalable bridge from single-agent control to large-population game theory.<\/p>\n<p>Date: Monday, May 5, 2025<br \/>\nTime: 15:30-16:30<br \/>\nPlace: Mathematics Seminar Room, SA \u2013 141<\/p>\n","protected":false},"excerpt":{"rendered":"<p>You are cordially invited to the Analysis Seminar organized by the Department of Mathematics. Speaker: : G\u00fcne\u015f Akba\u015f (Bilkent) &#8220;Entropy-Regularized Stochastic Control and Mean Field Games&#8221; Abstract: Starting from controlled Markov processes with an infinite-horizon average-cost objective, we add an entropy penalty that turns the hard minimum in the Bellman [\u2026] <\/p>\n<div class=\"clear\"><\/div>\n<p><a class=\"more_link clearfix\" href=\"https:\/\/w3.bilkent.edu.tr\/tr\/math-seminer-entropy-regularized-stochastic-control-and-mean-field-games-gunes-akbas-1530-5-mayis-2025-en\/\" rel=\"nofollow\">Read More<\/a><\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[22],"tags":[],"class_list":["post-34439","post","type-post","status-publish","format-standard","hentry","category-eskipostlar"],"_links":{"self":[{"href":"https:\/\/w3.bilkent.edu.tr\/tr\/wp-json\/wp\/v2\/posts\/34439","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/w3.bilkent.edu.tr\/tr\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/w3.bilkent.edu.tr\/tr\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/w3.bilkent.edu.tr\/tr\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/w3.bilkent.edu.tr\/tr\/wp-json\/wp\/v2\/comments?post=34439"}],"version-history":[{"count":2,"href":"https:\/\/w3.bilkent.edu.tr\/tr\/wp-json\/wp\/v2\/posts\/34439\/revisions"}],"predecessor-version":[{"id":34476,"href":"https:\/\/w3.bilkent.edu.tr\/tr\/wp-json\/wp\/v2\/posts\/34439\/revisions\/34476"}],"wp:attachment":[{"href":"https:\/\/w3.bilkent.edu.tr\/tr\/wp-json\/wp\/v2\/media?parent=34439"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/w3.bilkent.edu.tr\/tr\/wp-json\/wp\/v2\/categories?post=34439"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/w3.bilkent.edu.tr\/tr\/wp-json\/wp\/v2\/tags?post=34439"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}