{"id":"https://openalex.org/W4391985038","doi":"https://doi.org/10.1137/21m1468851","title":"Accelerating Primal-Dual Methods for Regularized Markov Decision Processes","display_name":"Accelerating Primal-Dual Methods for Regularized Markov Decision Processes","publication_year":2024,"publication_date":"2024-02-20","ids":{"openalex":"https://openalex.org/W4391985038","doi":"https://doi.org/10.1137/21m1468851"},"language":"en","primary_location":{"id":"doi:10.1137/21m1468851","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1137/21m1468851","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":"https://openalex.org/A5069020700","display_name":"Haoya Li","orcid":"https://orcid.org/0000-0001-7076-7600"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Haoya Li","raw_affiliation_strings":["Department of Mathematics, Stanford University, Stanford, CA 94305 USA"],"affiliations":[{"raw_affiliation_string":"Department of Mathematics, Stanford University, Stanford, CA 94305 USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023183059","display_name":"Hsiang\u2010Fu Yu","orcid":"https://orcid.org/0000-0001-5235-2962"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hsiang-Fu Yu","raw_affiliation_strings":["Amazon Search, Palo Alto, CA 94301 USA"],"affiliations":[{"raw_affiliation_string":"Amazon Search, Palo Alto, CA 94301 USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011918131","display_name":"Lexing Ying","orcid":"https://orcid.org/0000-0003-1547-1457"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lexing Ying","raw_affiliation_strings":["Department of Mathematics, Stanford University, Stanford, CA 94305 USA"],"affiliations":[{"raw_affiliation_string":"Department of Mathematics, Stanford University, Stanford, CA 94305 USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063459703","display_name":"Inderjit S. Dhillon","orcid":"https://orcid.org/0000-0002-2759-1416"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Inderjit S. Dhillon","raw_affiliation_strings":["Department of Computer Science, University of Texas at Austin, Austin, TX 78712 USA, and Google, Mountain View, CA 94043 USA. This work was done while this author was at Amazon Search"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Texas at Austin, Austin, TX 78712 USA, and Google, Mountain View, CA 94043 USA. This work was done while this author was at Amazon Search","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5069020700"],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01383002,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"34","issue":"1","first_page":"764","last_page":"789"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994999766349792,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994999766349792,"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/T11195","display_name":"Simulation Techniques and Applications","score":0.996399998664856,"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.993399977684021,"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/mathematics","display_name":"Mathematics","score":0.7674108147621155},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.6951757669448853},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5740594863891602},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.4957329034805298},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.4672270715236664},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.4550808370113373},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.39743471145629883},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.20269492268562317}],"concepts":[{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.7674108147621155},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.6951757669448853},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5740594863891602},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.4957329034805298},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.4672270715236664},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.4550808370113373},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.39743471145629883},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.20269492268562317},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1137/21m1468851","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1137/21m1468851","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":[{"id":"https://metadata.un.org/sdg/16","score":0.5799999833106995,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W1966397236","https://openalex.org/W1977777567","https://openalex.org/W1995713768","https://openalex.org/W2058935279","https://openalex.org/W2119717200","https://openalex.org/W2492794003","https://openalex.org/W2980326798","https://openalex.org/W2999905431","https://openalex.org/W3111550499","https://openalex.org/W3127686539","https://openalex.org/W3160598148","https://openalex.org/W4298023569","https://openalex.org/W4298300677","https://openalex.org/W4301018745","https://openalex.org/W4387047329"],"related_works":["https://openalex.org/W1660242800","https://openalex.org/W2077211377","https://openalex.org/W2379651310","https://openalex.org/W2113019827","https://openalex.org/W1541249122","https://openalex.org/W2413828414","https://openalex.org/W2367222340","https://openalex.org/W187740018","https://openalex.org/W2162286586","https://openalex.org/W4255368532"],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2025-12-25T23:11:45.687758","created_date":"2025-10-10T00:00:00"}
