{"id":6910,"date":"2025-10-06T15:55:26","date_gmt":"2025-10-06T13:55:26","guid":{"rendered":"https:\/\/samovar.telecom-sudparis.eu\/?p=6910"},"modified":"2025-10-10T10:13:55","modified_gmt":"2025-10-10T08:13:55","slug":"seminaire-ness-robust-deterministic-policies-for-mdps-under-budgeted-uncertainty-presente-par-dr-fei-wu-univeriste-de-louvain-en-belgique-le-10-10-a-11h-salle-4a205-palaiseau","status":"publish","type":"post","link":"https:\/\/samovar.telecom-sudparis.eu\/index.php\/2025\/10\/06\/seminaire-ness-robust-deterministic-policies-for-mdps-under-budgeted-uncertainty-presente-par-dr-fei-wu-univeriste-de-louvain-en-belgique-le-10-10-a-11h-salle-4a205-palaiseau\/","title":{"rendered":"S\u00e9minaire Ness: Robust Deterministic Policies for MDPs under Budgeted Uncertainty, pr\u00e9sent\u00e9 par Dr. Fei WU, Universite de Louvain en Belgique, le 10\/10 \u00e0 11h, salle 4A205 \u00e0 Palaiseau"},"content":{"rendered":"\t\t<div data-elementor-type=\"wp-post\" data-elementor-id=\"6910\" class=\"elementor elementor-6910\">\n\t\t\t\t\t\t<section class=\"elementor-section elementor-top-section elementor-element elementor-element-6d823b8f elementor-section-boxed elementor-section-height-default elementor-section-height-default\" data-id=\"6d823b8f\" data-element_type=\"section\">\n\t\t\t\t\t\t<div class=\"elementor-container elementor-column-gap-default\">\n\t\t\t\t\t<div class=\"elementor-column elementor-col-100 elementor-top-column elementor-element elementor-element-65e5fa8c\" data-id=\"65e5fa8c\" data-element_type=\"column\">\n\t\t\t<div class=\"elementor-widget-wrap elementor-element-populated\">\n\t\t\t\t\t\t<div class=\"elementor-element elementor-element-3b4626b3 elementor-widget elementor-widget-text-editor\" data-id=\"3b4626b3\" data-element_type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t\t\t\n<p><strong>When:<\/strong> Vendredi 10 octobre 2025, 11h00<\/p>\n\n<p><strong>Where<\/strong>: Salle 4A205, \u00e0 Telecom SudParis, Palaiseau, et lien Teams: <span id=\"OBJ_PREFIX_DWT1898_com_zimbra_url\" class=\"Object\"><span id=\"OBJ_PREFIX_DWT1937_com_zimbra_url\" class=\"Object\"><span id=\"OBJ_PREFIX_DWT2862_com_zimbra_url\" class=\"Object\" role=\"link\"><span id=\"OBJ_PREFIX_DWT2877_com_zimbra_url\" class=\"Object\" role=\"link\"><a href=\"https:\/\/teams.microsoft.com\/l\/meetup-join\/19%3ameeting_ZTRlZTJjNTMtMDA4OC00ZTJiLTk0ZjgtNGI1MmQ0MmZmN2Ew%40thread.v2\/0?context=%7b%22Tid%22%3a%222b1be215-5cf1-43de-8bc7-946bdf57f9cd%22%2c%22Oid%22%3a%227e01b3e9-d62e-4d6c-b520-7439f5a11929%22%7d\" target=\"_blank\" rel=\"noopener noreferrer\">Fei Wu Seminar | R\u00e9union-Joindre | Microsoft Teams<\/a><\/span><\/span><\/span><\/span><\/p>\n\n<p><strong>Title:<\/strong> Robust Deterministic Policies for MDPs under Budgeted Uncertainty<\/p>\n\n<p><br \/><strong>Abstract<\/strong><br \/>We study the computation of robust deterministic policies for Markov Decision Processes (MDPs)<br \/>in the Lightning Does Not Strike Twice (LDST) model of Mannor, Mebel, and Xu. In this model,<br \/>designed to provide robustness in the face of uncertain input data while not being overly conservative,<br \/>transition probabilities and rewards are uncertain and the uncertainty set is constrained by a budget<br \/>that limits the number of states whose parameters can deviate from their nominal values. Mannor<br \/>et al. showed that optimal randomized policies for MDPs in the LDST regime can be efficiently<br \/>computed when only the rewards are affected by uncertainty. In contrast to these findings, we<br \/>observe that the computation of optimal deterministic policies is NP-hard even when only a single<br \/>terminal reward may deviate from its nominal value and the MDP consists of 2 time periods. For<br \/>this hard special case, we then derive a constant-factor approximation algorithm by combining two<br \/>relaxations based on the Knapsack Cover and Generalized Assignment problem, respectively. For<br \/>the general problem with possibly large number of deviations and a longer time horizon, we derive<br \/>strong inapproximability results for computing robust deterministic policies as well as \u03a3p<br \/>2-hardness, indicating that the general problem does not even admit a compact mixed integer programming<br \/>formulation.<br \/>Joint work with Jannik Matuschke and Erik Demeulemeester.<\/p>\n\n<p><strong>Biography:<\/strong><br \/>I received my Ph.D. in Operations Management from KU Leuven, where my work focused on<br \/>optimization under adversarial robustness. My research interests include combinatorial optimization,<br \/>algorithm design and analysis, and robust optimization, with applications to logistics and production.<br \/>I was invited to the Hausdorff Institute for Mathematics (University of Bonn) for a discrete<br \/>optimization program, where I presented preliminary results on robust MDPs.<\/p>\n\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t<\/div>\n\t\t","protected":false},"excerpt":{"rendered":"<p>When: Vendredi 10 octobre 2025, 11h00 Where: Salle 4A205, \u00e0 Telecom SudParis, Palaiseau, et lien Teams: Fei Wu Seminar | R\u00e9union-Joindre | Microsoft Teams Title: Robust Deterministic Policies for MDPs under Budgeted Uncertainty AbstractWe study the computation of robust deterministic policies for Markov Decision Processes (MDPs)in the Lightning Does Not Strike Twice (LDST) model of [&hellip;]<\/p>\n","protected":false},"author":4,"featured_media":0,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"ocean_post_layout":"","ocean_both_sidebars_style":"","ocean_both_sidebars_content_width":0,"ocean_both_sidebars_sidebars_width":0,"ocean_sidebar":"","ocean_second_sidebar":"","ocean_disable_margins":"enable","ocean_add_body_class":"","ocean_shortcode_before_top_bar":"","ocean_shortcode_after_top_bar":"","ocean_shortcode_before_header":"","ocean_shortcode_after_header":"","ocean_has_shortcode":"","ocean_shortcode_after_title":"","ocean_shortcode_before_footer_widgets":"","ocean_shortcode_after_footer_widgets":"","ocean_shortcode_before_footer_bottom":"","ocean_shortcode_after_footer_bottom":"","ocean_display_top_bar":"default","ocean_display_header":"default","ocean_header_style":"","ocean_center_header_left_menu":"","ocean_custom_header_template":"","ocean_custom_logo":0,"ocean_custom_retina_logo":0,"ocean_custom_logo_max_width":0,"ocean_custom_logo_tablet_max_width":0,"ocean_custom_logo_mobile_max_width":0,"ocean_custom_logo_max_height":0,"ocean_custom_logo_tablet_max_height":0,"ocean_custom_logo_mobile_max_height":0,"ocean_header_custom_menu":"","ocean_menu_typo_font_family":"","ocean_menu_typo_font_subset":"","ocean_menu_typo_font_size":0,"ocean_menu_typo_font_size_tablet":0,"ocean_menu_typo_font_size_mobile":0,"ocean_menu_typo_font_size_unit":"px","ocean_menu_typo_font_weight":"","ocean_menu_typo_font_weight_tablet":"","ocean_menu_typo_font_weight_mobile":"","ocean_menu_typo_transform":"","ocean_menu_typo_transform_tablet":"","ocean_menu_typo_transform_mobile":"","ocean_menu_typo_line_height":0,"ocean_menu_typo_line_height_tablet":0,"ocean_menu_typo_line_height_mobile":0,"ocean_menu_typo_line_height_unit":"","ocean_menu_typo_spacing":0,"ocean_menu_typo_spacing_tablet":0,"ocean_menu_typo_spacing_mobile":0,"ocean_menu_typo_spacing_unit":"","ocean_menu_link_color":"","ocean_menu_link_color_hover":"","ocean_menu_link_color_active":"","ocean_menu_link_background":"","ocean_menu_link_hover_background":"","ocean_menu_link_active_background":"","ocean_menu_social_links_bg":"","ocean_menu_social_hover_links_bg":"","ocean_menu_social_links_color":"","ocean_menu_social_hover_links_color":"","ocean_disable_title":"default","ocean_disable_heading":"default","ocean_post_title":"","ocean_post_subheading":"","ocean_post_title_style":"","ocean_post_title_background_color":"","ocean_post_title_background":0,"ocean_post_title_bg_image_position":"","ocean_post_title_bg_image_attachment":"","ocean_post_title_bg_image_repeat":"","ocean_post_title_bg_image_size":"","ocean_post_title_height":0,"ocean_post_title_bg_overlay":0.5,"ocean_post_title_bg_overlay_color":"","ocean_disable_breadcrumbs":"default","ocean_breadcrumbs_color":"","ocean_breadcrumbs_separator_color":"","ocean_breadcrumbs_links_color":"","ocean_breadcrumbs_links_hover_color":"","ocean_display_footer_widgets":"default","ocean_display_footer_bottom":"default","ocean_custom_footer_template":"","ocean_post_oembed":"","ocean_post_self_hosted_media":"","ocean_post_video_embed":"","ocean_link_format":"","ocean_link_format_target":"self","ocean_quote_format":"","ocean_quote_format_link":"post","ocean_gallery_link_images":"on","ocean_gallery_id":[],"footnotes":""},"categories":[286,402,7],"tags":[],"class_list":["post-6910","post","type-post","status-publish","format-standard","hentry","category-fractualites-ennews-fr","category-seminaires-ness-2013-fr","category-uncategorized-fr","entry"],"_links":{"self":[{"href":"https:\/\/samovar.telecom-sudparis.eu\/index.php\/wp-json\/wp\/v2\/posts\/6910","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/samovar.telecom-sudparis.eu\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/samovar.telecom-sudparis.eu\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/samovar.telecom-sudparis.eu\/index.php\/wp-json\/wp\/v2\/users\/4"}],"replies":[{"embeddable":true,"href":"https:\/\/samovar.telecom-sudparis.eu\/index.php\/wp-json\/wp\/v2\/comments?post=6910"}],"version-history":[{"count":12,"href":"https:\/\/samovar.telecom-sudparis.eu\/index.php\/wp-json\/wp\/v2\/posts\/6910\/revisions"}],"predecessor-version":[{"id":6922,"href":"https:\/\/samovar.telecom-sudparis.eu\/index.php\/wp-json\/wp\/v2\/posts\/6910\/revisions\/6922"}],"wp:attachment":[{"href":"https:\/\/samovar.telecom-sudparis.eu\/index.php\/wp-json\/wp\/v2\/media?parent=6910"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/samovar.telecom-sudparis.eu\/index.php\/wp-json\/wp\/v2\/categories?post=6910"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/samovar.telecom-sudparis.eu\/index.php\/wp-json\/wp\/v2\/tags?post=6910"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}