{"id":"https://openalex.org/W7119487890","doi":"https://doi.org/10.1137/23m1621071","title":"Fast Policy Learning for Linear-Quadratic Control with Entropy Regularization","display_name":"Fast Policy Learning for Linear-Quadratic Control with Entropy Regularization","publication_year":2026,"publication_date":"2026-01-09","ids":{"openalex":"https://openalex.org/W7119487890","doi":"https://doi.org/10.1137/23m1621071"},"language":"en","primary_location":{"id":"doi:10.1137/23m1621071","is_oa":false,"landing_page_url":"https://doi.org/10.1137/23m1621071","pdf_url":null,"source":{"id":"https://openalex.org/S897311980","display_name":"SIAM Journal on Control and Optimization","issn_l":"0363-0129","issn":["0363-0129","1095-7138"],"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 Control and 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":"Xin Guo","orcid":"https://orcid.org/0000-0002-3350-4606"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xin Guo","raw_affiliation_strings":["Department of Industrial Engineering and Operations Research, University of California, Berkeley, Berkeley, CA 94720 USA"],"raw_orcid":"https://orcid.org/0000-0002-3350-4606","affiliations":[{"raw_affiliation_string":"Department of Industrial Engineering and Operations Research, University of California, Berkeley, Berkeley, CA 94720 USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xinyu Li","orcid":"https://orcid.org/0009-0005-1206-716X"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Xinyu Li","raw_affiliation_strings":["Department of Mathematics, University of Oxford, Oxford OX2 6GG, UK"],"raw_orcid":"https://orcid.org/0009-0005-1206-716X","affiliations":[{"raw_affiliation_string":"Department of Mathematics, University of Oxford, Oxford OX2 6GG, UK","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"last","author":{"id":null,"display_name":"Renyuan Xu","orcid":"https://orcid.org/0000-0003-4293-3450"},"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":"Renyuan Xu","raw_affiliation_strings":["Department of Management Science and Engineering, Stanford University, Stanford, CA 94305 USA"],"raw_orcid":"https://orcid.org/0000-0003-4293-3450","affiliations":[{"raw_affiliation_string":"Department of Management Science and Engineering, Stanford University, Stanford, CA 94305 USA","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":2,"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":0.07237368,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"64","issue":"1","first_page":"124","last_page":"151"},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.6654999852180481,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.6654999852180481,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.1467999964952469,"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.027000000700354576,"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/entropy","display_name":"Entropy (arrow of time)","score":0.5385000109672546},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.4765999913215637},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.390500009059906},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.35519999265670776},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.3538999855518341},{"id":"https://openalex.org/keywords/principle-of-maximum-entropy","display_name":"Principle of maximum entropy","score":0.31380000710487366}],"concepts":[{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.7164000272750854},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.5385000109672546},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.4765999913215637},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.42739999294281006},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.4178999960422516},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.390500009059906},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.35519999265670776},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3538999855518341},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3215000033378601},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.31380000710487366},{"id":"https://openalex.org/C2982736386","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Statistical learning","level":2,"score":0.3027999997138977},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.2996000051498413},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.28610000014305115},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2639000117778778},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.25699999928474426}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1137/23m1621071","is_oa":false,"landing_page_url":"https://doi.org/10.1137/23m1621071","pdf_url":null,"source":{"id":"https://openalex.org/S897311980","display_name":"SIAM Journal on Control and Optimization","issn_l":"0363-0129","issn":["0363-0129","1095-7138"],"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 Control and Optimization","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6834831930","display_name":"Mathematical Foundations of Intelligence: An "Erlangen Programme" for AI","funder_award_id":"EP/Y028872/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1499669280","https://openalex.org/W1993411524","https://openalex.org/W2395579298","https://openalex.org/W2941034199","https://openalex.org/W2998050631","https://openalex.org/W3098412154","https://openalex.org/W3118666236","https://openalex.org/W3133092968","https://openalex.org/W3135939397","https://openalex.org/W3203485495","https://openalex.org/W3209135762","https://openalex.org/W3216656735","https://openalex.org/W3217314940","https://openalex.org/W4214597064","https://openalex.org/W4309029392","https://openalex.org/W4313591116","https://openalex.org/W4315786096","https://openalex.org/W4362722548","https://openalex.org/W4383112908","https://openalex.org/W4385495268","https://openalex.org/W4389458504","https://openalex.org/W4390949195","https://openalex.org/W4400467694","https://openalex.org/W4413293830"],"related_works":[],"abstract_inverted_index":{"Abstract.":[0],"This":[1],"paper":[2],"proposes":[3],"and":[4,14],"analyzes":[5],"two":[6,122],"new":[7],"policy":[8,12,16,41,83,100],"learning":[9,87],"methods,":[10],"regularized":[11,57],"gradient":[13],"iterative":[15],"optimization":[17],"(IPO),":[18],"for":[19,84],"a":[20,65,72,85,91,117],"class":[21],"of":[22,55,130,138],"discounted":[23],"linear-quadratic":[24],"control":[25],"(LQC)":[26],"problems":[27],"over":[28],"an":[29,102,106],"infinite":[30],"time":[31],"horizon":[32],"with":[33,90,105],"entropy":[34],"regularization.":[35],"Assuming":[36],"access":[37],"to":[38,48,101,114],"the":[39,56,60,76,81,98,109,121,131],"exact":[40],"evaluation,":[42],"both":[43],"proposed":[44,140],"approaches":[45],"are":[46,124,142],"proved":[47],"converge":[49,115],"linearly":[50],"in":[51],"finding":[52],"optimal":[53,77,82],"policies":[54],"LQC.":[58],"Moreover,":[59],"IPO":[61,110],"method":[62,111],"can":[63],"achieve":[64],"superlinear":[66,118],"convergence":[67],"rate":[68,119],"once":[69],"it":[70],"enters":[71],"local":[73],"region":[74],"around":[75],"policy.":[78],"Finally,":[79],"when":[80],"reinforcement":[86],"(RL)":[88],"problem":[89,104],"known":[92],"environment":[93],"is":[94,112,134],"appropriately":[95],"transferred":[96],"as":[97],"initial":[99],"RL":[103],"unknown":[107],"environment,":[108],"shown":[113],"at":[116],"if":[120],"environments":[123],"sufficiently":[125],"close.":[126],"A":[127],"model-free":[128],"version":[129],"policy-based":[132],"methods":[133],"also":[135],"discussed.":[136],"Performances":[137],"these":[139],"algorithms":[141],"supported":[143],"by":[144],"numerical":[145],"examples.":[146]},"counts_by_year":[],"updated_date":"2026-08-22T07:34:49.880490","created_date":"2025-10-10T00:00:00"}