{"id":5,"date":"2016-09-12T11:03:10","date_gmt":"2016-09-12T15:03:10","guid":{"rendered":"https:\/\/sites.bu.edu\/aolshevsky\/alex-olshevsky\/"},"modified":"2026-06-21T16:21:27","modified_gmt":"2026-06-21T20:21:27","slug":"alex-olshevsky","status":"publish","type":"page","link":"https:\/\/sites.bu.edu\/aolshevsky\/","title":{"rendered":""},"content":{"rendered":"<h1>Alex Olshevsky<\/h1>\n<p><img loading=\"lazy\" src=\"\/aolshevsky\/files\/2026\/06\/20260621_161311-1-1-636x477.jpg\" alt=\"\" width=\"167\" height=\"223\" class=\"alignleft wp-image-1302\" \/><br \/>\nProfessor<br \/>\n<a href=\"http:\/\/www.bu.edu\/eng\/departments\/ece\/\">Department of Electrical and Computer Engineering<\/a><br \/>\n<a href=\"http:\/\/www.bu.edu\/eng\/departments\/se\/\">Division of Systems Engineering<\/a><br \/>\n<a href=\"https:\/\/www.bu.edu\/cs\/\">Department of Computer Science<\/a> (affiliate)<a href=\"http:\/\/www.bu.edu\/systems\/\"><br \/>\n<\/a>Boston University<\/p>\n<p><strong><\/strong><\/p>\n<p><strong><\/strong><\/p>\n<p><strong><\/strong><\/p>\n<p>&nbsp;<\/p>\n<p><strong><br \/>\n<\/strong><strong><\/strong><strong>Research Interests<\/strong><\/p>\n<ul>\n<li>Learning and Control<\/li>\n<li>Reinforcement Learning<\/li>\n<\/ul>\n<p><strong>Selected Recent Publications<\/strong><\/p>\n<ul>\n<li><a href=\"\/aolshevsky\/files\/2026\/04\/Average_Reward__Copy_-1-1.pdf\">Bridging the Gap Between Average and Discounted TD Learning<\/a><br \/>\n<em>Proceedings of ICML 2026<\/em>.<\/li>\n<li><a href=\"https:\/\/arxiv.org\/abs\/2404.10851\" class=\"gsc_a_at\">Sample Complexity of the Linear Quadratic Regulator: A Reinforcement Learning Lens<\/a><br \/>\n<em>Journal of Machine Learning Research<\/em>, 2025<\/li>\n<li><a href=\"https:\/\/arxiv.org\/abs\/2407.06712\" class=\"gsc_a_at\">MDP Geometry, Normalization and Value Free Solvers<\/a><br \/>\n<em>Proceedings AISTATS 2025<\/em><\/li>\n<li><a href=\"https:\/\/openreview.net\/forum?id=QlfGOVD5PO\">Convergence of Actor-Critic with Multi-Layer Neural Networks<\/a><br \/>\n<em>\u00a0Proceedings of NeurIPS 2023.<\/em><\/li>\n<li><a href=\"https:\/\/openreview.net\/pdf?id=6JMXLWX68Kj\">On the Performance of Temporal Difference Learning with Neural Networks<\/a><br \/>\n<em>Proceedings of ICLR 2023<\/em><\/li>\n<li><a href=\"https:\/\/arxiv.org\/abs\/2203.02591\">A Small Gain Analysis of Single Timescale Actor-Critic<\/a><br \/>\n<em>SIAM Journal on Control and Optimization, 2023<\/em>.<\/p>\n<ul><\/ul>\n<\/li>\n<\/ul>\n<p><strong>Professional\u00a0information<\/strong><\/p>\n<p>[<a href=\"https:\/\/sites.bu.edu\/aolshevsky\/publications\/\">Publications<\/a>][<a href=\"http:\/\/scholar.google.com\/citations?user=YKwHoFMAAAAJ\">Google Scholar<\/a>][<a href=\"\/aolshevsky\/files\/2025\/07\/Abbreviated_CV.pdf\">CV<\/a> (outdated)]<\/p>\n<p><strong>Contact Information<\/strong><\/p>\n<p>Email:\u00a0alexols [at] bu [dot] edu<br \/>\nOffice: 419 Photonics Center; 8 St. Mary St, Boston, MA, 02215.<\/p>\n<p>&nbsp;<\/p>\n<p>&nbsp;<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Alex Olshevsky Professor Department of Electrical and Computer Engineering Division of Systems Engineering Department of Computer Science (affiliate) Boston University &nbsp; Research Interests Learning and Control Reinforcement Learning Selected Recent Publications Bridging the Gap Between Average and Discounted TD Learning Proceedings of ICML 2026. Sample Complexity of the Linear Quadratic Regulator: A Reinforcement Learning Lens [&hellip;]<\/p>\n","protected":false},"author":12455,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"page-templates\/profiles.php","meta":[],"_links":{"self":[{"href":"https:\/\/sites.bu.edu\/aolshevsky\/wp-json\/wp\/v2\/pages\/5"}],"collection":[{"href":"https:\/\/sites.bu.edu\/aolshevsky\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/sites.bu.edu\/aolshevsky\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/sites.bu.edu\/aolshevsky\/wp-json\/wp\/v2\/users\/12455"}],"replies":[{"embeddable":true,"href":"https:\/\/sites.bu.edu\/aolshevsky\/wp-json\/wp\/v2\/comments?post=5"}],"version-history":[{"count":50,"href":"https:\/\/sites.bu.edu\/aolshevsky\/wp-json\/wp\/v2\/pages\/5\/revisions"}],"predecessor-version":[{"id":1305,"href":"https:\/\/sites.bu.edu\/aolshevsky\/wp-json\/wp\/v2\/pages\/5\/revisions\/1305"}],"wp:attachment":[{"href":"https:\/\/sites.bu.edu\/aolshevsky\/wp-json\/wp\/v2\/media?parent=5"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}