{"id":"https://openalex.org/W4415178454","doi":"https://doi.org/10.1109/tac.2025.3621539","title":"Nonconvex Regularization for Markov Decision Processes: Modeling and Algorithms","display_name":"Nonconvex Regularization for Markov Decision Processes: Modeling and Algorithms","publication_year":2025,"publication_date":"2025-10-14","ids":{"openalex":"https://openalex.org/W4415178454","doi":"https://doi.org/10.1109/tac.2025.3621539"},"language":"en","primary_location":{"id":"doi:10.1109/tac.2025.3621539","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tac.2025.3621539","pdf_url":null,"source":{"id":"https://openalex.org/S184954342","display_name":"IEEE Transactions on Automatic Control","issn_l":"0018-9286","issn":["0018-9286","1558-2523","2334-3303"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Automatic Control","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":"https://openalex.org/A5101888873","display_name":"Yuwei Wu","orcid":"https://orcid.org/0000-0001-8717-4107"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuwei Wu","raw_affiliation_strings":["School of Management and Engineering, Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0001-8717-4107","affiliations":[{"raw_affiliation_string":"School of Management and Engineering, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103045020","display_name":"Caihua Chen","orcid":"https://orcid.org/0000-0001-8057-3690"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Caihua Chen","raw_affiliation_strings":["School of Management and Engineering, Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0001-8057-3690","affiliations":[{"raw_affiliation_string":"School of Management and Engineering, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Chunlin Chen","orcid":"https://orcid.org/0000-0003-3929-4707"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunlin Chen","raw_affiliation_strings":["School of Management and Engineering, Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0003-3929-4707","affiliations":[{"raw_affiliation_string":"School of Management and Engineering, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017213485","display_name":"Suhong Jiang","orcid":null},"institutions":[{"id":"https://openalex.org/I137056471","display_name":"Nanjing University of Finance and Economics","ror":"https://ror.org/031y8am81","country_code":"CN","type":"education","lineage":["https://openalex.org/I137056471"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Suhong Jiang","raw_affiliation_strings":["School of Accounting, Nanjing University of Finance and Economics, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0004-7109-3379","affiliations":[{"raw_affiliation_string":"School of Accounting, Nanjing University of Finance and Economics, Nanjing, China","institution_ids":["https://openalex.org/I137056471"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102741528","display_name":"Andrew Lim","orcid":"https://orcid.org/0000-0003-0510-8080"},"institutions":[{"id":"https://openalex.org/I4800084","display_name":"Southwest Jiaotong University","ror":"https://ror.org/00hn7w693","country_code":"CN","type":"education","lineage":["https://openalex.org/I4800084"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Andrew Lim","raw_affiliation_strings":["School of Computing and Artificial Intelligence, Southwest Jiaotong University, Chengdu, China","Red Jasper Holdings, Singapore"],"raw_orcid":"https://orcid.org/0000-0003-0510-8080","affiliations":[{"raw_affiliation_string":"School of Computing and Artificial Intelligence, Southwest Jiaotong University, Chengdu, China","institution_ids":["https://openalex.org/I4800084"]},{"raw_affiliation_string":"Red Jasper Holdings, Singapore","institution_ids":[]}]}],"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":0.14432067,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"71","issue":"3","first_page":"2015","last_page":"2022"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.30300000309944153,"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"}},"topics":[{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.30300000309944153,"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/T10876","display_name":"Fault Detection and Control Systems","score":0.26170000433921814,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.6876000165939331},{"id":"https://openalex.org/keywords/linear-programming","display_name":"Linear programming","score":0.6078000068664551},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5763999819755554},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.5663999915122986},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.5160999894142151},{"id":"https://openalex.org/keywords/rate-of-convergence","display_name":"Rate of convergence","score":0.49399998784065247},{"id":"https://openalex.org/keywords/linear-system","display_name":"Linear system","score":0.4507000148296356},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.42500001192092896}],"concepts":[{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6876000165939331},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.6333000063896179},{"id":"https://openalex.org/C41045048","wikidata":"https://www.wikidata.org/wiki/Q202843","display_name":"Linear programming","level":2,"score":0.6078000068664551},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5763999819755554},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.5663999915122986},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5598000288009644},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.541100025177002},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.5160999894142151},{"id":"https://openalex.org/C57869625","wikidata":"https://www.wikidata.org/wiki/Q1783502","display_name":"Rate of convergence","level":3,"score":0.49399998784065247},{"id":"https://openalex.org/C6802819","wikidata":"https://www.wikidata.org/wiki/Q1072174","display_name":"Linear system","level":2,"score":0.4507000148296356},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.42500001192092896},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.40709999203681946},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3885999917984009},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.32429999113082886},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.3221000134944916},{"id":"https://openalex.org/C148764684","wikidata":"https://www.wikidata.org/wiki/Q621751","display_name":"Approximation algorithm","level":2,"score":0.2759999930858612},{"id":"https://openalex.org/C2988995629","wikidata":"https://www.wikidata.org/wiki/Q2915729","display_name":"Matrix algebra","level":3,"score":0.274399995803833},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.2727999985218048},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.27129998803138733},{"id":"https://openalex.org/C159694833","wikidata":"https://www.wikidata.org/wiki/Q2321565","display_name":"Iterative method","level":2,"score":0.2535000145435333}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tac.2025.3621539","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tac.2025.3621539","pdf_url":null,"source":{"id":"https://openalex.org/S184954342","display_name":"IEEE Transactions on Automatic Control","issn_l":"0018-9286","issn":["0018-9286","1558-2523","2334-3303"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Automatic Control","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1251036310","display_name":"\u5e93\u5b58\u4e0e\u914d\u9001\u4e00\u4f53\u5316\u51b3\u7b56\u95ee\u9898\u7684\u7814\u7a76","funder_award_id":"72071139","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1302871764","display_name":null,"funder_award_id":"12501430","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1746495320","display_name":null,"funder_award_id":"2025300110","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G1775507442","display_name":null,"funder_award_id":"2024300418","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G2026071716","display_name":null,"funder_award_id":"72394363/72394360","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2362776713","display_name":null,"funder_award_id":"72394364","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5521227422","display_name":null,"funder_award_id":"12431011","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1],"investigates":[2],"efficient":[3],"algorithm":[4],"for":[5,39],"Markov":[6],"Decision":[7],"Processes":[8],"(MDPs)":[9],"through":[10],"Linear":[11],"programming":[12],"(LP).":[13],"Generally,":[14],"solving":[15],"large-scale":[16],"MDPs":[17,41],"via":[18],"standard":[19],"LP":[20],"solvers":[21],"faces":[22],"significant":[23],"computational":[24],"bottlenecks":[25],"in":[26,48],"matrix":[27],"factorization.":[28],"To":[29],"tackle":[30],"this":[31],"problem,":[32],"we":[33,50],"introduced":[34],"a":[35,71],"novel":[36],"sparse":[37],"formulation":[38,54],"discounted":[40],"using":[42],"nonconvex":[43],"regularization.":[44],"Despite":[45],"being":[46],"combinatorial":[47],"nature,":[49],"show":[51],"that":[52],"the":[53],"can":[55],"be":[56],"solved":[57],"efficiently":[58],"by":[59],"an":[60],"alternating":[61],"direction":[62],"method":[63],"of":[64],"multipliers":[65],"with":[66],"linear":[67],"convergence":[68],"rate":[69],"and":[70],"state-of-the-art":[72],"performance.":[73]},"counts_by_year":[],"updated_date":"2026-02-28T06:14:18.631764","created_date":"2025-10-15T00:00:00"}