{"id":"https://openalex.org/W7128444771","doi":"https://doi.org/10.1137/24m1631250","title":"Policy Gradient Algorithms for Robust MDP\\(\\text{s}\\) with Nonrectangular Uncertainty Sets","display_name":"Policy Gradient Algorithms for Robust MDP\\(\\text{s}\\) with Nonrectangular Uncertainty Sets","publication_year":2026,"publication_date":"2026-02-09","ids":{"openalex":"https://openalex.org/W7128444771","doi":"https://doi.org/10.1137/24m1631250"},"language":"en","primary_location":{"id":"doi:10.1137/24m1631250","is_oa":false,"landing_page_url":"https://doi.org/10.1137/24m1631250","pdf_url":null,"source":{"id":"https://openalex.org/S928796702","display_name":"SIAM Journal on Optimization","issn_l":"1052-6234","issn":["1052-6234","1095-7189"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320508","host_organization_name":"Society for Industrial and Applied Mathematics","host_organization_lineage":["https://openalex.org/P4310320508"],"host_organization_lineage_names":["Society for Industrial and Applied Mathematics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SIAM Journal on Optimization","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Mengmeng Li","orcid":"https://orcid.org/0000-0002-2978-7949"},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Mengmeng Li","raw_affiliation_strings":["Risk Analytics and Optimization Chair, EPFL, 1015 Lausanne, Switzerland"],"raw_orcid":"https://orcid.org/0000-0002-2978-7949","affiliations":[{"raw_affiliation_string":"Risk Analytics and Optimization Chair, EPFL, 1015 Lausanne, Switzerland","institution_ids":["https://openalex.org/I5124864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065780980","display_name":"Daniel K\u00fchn","orcid":"https://orcid.org/0000-0003-2697-8886"},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Daniel Kuhn","raw_affiliation_strings":["Risk Analytics and Optimization Chair, EPFL, 1015 Lausanne, Switzerland"],"raw_orcid":"https://orcid.org/0000-0003-2697-8886","affiliations":[{"raw_affiliation_string":"Risk Analytics and Optimization Chair, EPFL, 1015 Lausanne, Switzerland","institution_ids":["https://openalex.org/I5124864"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033819821","display_name":"Tobias Sutter","orcid":"https://orcid.org/0000-0003-1226-6845"},"institutions":[{"id":"https://openalex.org/I202963720","display_name":"University of St.Gallen","ror":"https://ror.org/0561a3s31","country_code":"CH","type":"education","lineage":["https://openalex.org/I202963720"]},{"id":"https://openalex.org/I4210145378","display_name":"University of Applied Sciences St. Gallen","ror":"https://ror.org/049bwzr51","country_code":"CH","type":"education","lineage":["https://openalex.org/I4210145378"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Tobias Sutter","raw_affiliation_strings":["Department of Economics, University of St. Gallen, 9000 St. Gallen, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Economics, University of St. Gallen, 9000 St. Gallen, Switzerland","institution_ids":["https://openalex.org/I202963720","https://openalex.org/I4210145378"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.12239395,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"36","issue":"1","first_page":"120","last_page":"151"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11413","display_name":"Risk and Portfolio Optimization","score":0.3562000095844269,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11413","display_name":"Risk and Portfolio Optimization","score":0.3562000095844269,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.20800000429153442,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.11299999803304672,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.3163999915122986},{"id":"https://openalex.org/keywords/gradient-method","display_name":"Gradient method","score":0.3075000047683716},{"id":"https://openalex.org/keywords/minification","display_name":"Minification","score":0.3009999990463257},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.2953000068664551},{"id":"https://openalex.org/keywords/frank\u2013wolfe-algorithm","display_name":"Frank\u2013Wolfe algorithm","score":0.29339998960494995}],"concepts":[{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.6951000094413757},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.555400013923645},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.42179998755455017},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.32679998874664307},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.3163999915122986},{"id":"https://openalex.org/C115680565","wikidata":"https://www.wikidata.org/wiki/Q5977448","display_name":"Gradient method","level":2,"score":0.3075000047683716},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.3009999990463257},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.2953000068664551},{"id":"https://openalex.org/C122268817","wikidata":"https://www.wikidata.org/wiki/Q2020318","display_name":"Frank\u2013Wolfe algorithm","level":5,"score":0.29339998960494995},{"id":"https://openalex.org/C193254401","wikidata":"https://www.wikidata.org/wiki/Q2160088","display_name":"Robust optimization","level":2,"score":0.2702000141143799},{"id":"https://openalex.org/C32230216","wikidata":"https://www.wikidata.org/wiki/Q7882499","display_name":"Uncertainty quantification","level":2,"score":0.26759999990463257},{"id":"https://openalex.org/C2987595161","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Optimization algorithm","level":2,"score":0.26440000534057617}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1137/24m1631250","is_oa":false,"landing_page_url":"https://doi.org/10.1137/24m1631250","pdf_url":null,"source":{"id":"https://openalex.org/S928796702","display_name":"SIAM Journal on Optimization","issn_l":"1052-6234","issn":["1052-6234","1095-7189"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320508","host_organization_name":"Society for Industrial and Applied Mathematics","host_organization_lineage":["https://openalex.org/P4310320508"],"host_organization_lineage_names":["Society for Industrial and Applied Mathematics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SIAM Journal on Optimization","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1294180184","display_name":null,"funder_award_id":"51 NF40_1 80545","funder_id":"https://openalex.org/F4320320924","funder_display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung"}],"funders":[{"id":"https://openalex.org/F4320320924","display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung","ror":"https://ror.org/00yjd3n13"},{"id":"https://openalex.org/F8269005443","display_name":"NCCR Catalysis","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W11809405","https://openalex.org/W1965878388","https://openalex.org/W1978259121","https://openalex.org/W1983452151","https://openalex.org/W1994123361","https://openalex.org/W2003747360","https://openalex.org/W2010654234","https://openalex.org/W2036931518","https://openalex.org/W2057041949","https://openalex.org/W2075090252","https://openalex.org/W2092277809","https://openalex.org/W2094387729","https://openalex.org/W2115807064","https://openalex.org/W2136885855","https://openalex.org/W2155153696","https://openalex.org/W2165622730","https://openalex.org/W2168565265","https://openalex.org/W2276122543","https://openalex.org/W2553297237","https://openalex.org/W2963190258","https://openalex.org/W3203375555","https://openalex.org/W3210638057","https://openalex.org/W4224230876","https://openalex.org/W4249667877","https://openalex.org/W4323833050","https://openalex.org/W4391045260","https://openalex.org/W4400685310","https://openalex.org/W7124284875"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2026-02-10T00:00:00"}
