{"id":"https://openalex.org/W7123353619","doi":"https://doi.org/10.1109/cdc57313.2025.11312093","title":"Predictive Lagrangian Optimization for Constrained Reinforcement Learning","display_name":"Predictive Lagrangian Optimization for Constrained Reinforcement Learning","publication_year":2025,"publication_date":"2025-12-09","ids":{"openalex":"https://openalex.org/W7123353619","doi":"https://doi.org/10.1109/cdc57313.2025.11312093"},"language":null,"primary_location":{"id":"doi:10.1109/cdc57313.2025.11312093","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc57313.2025.11312093","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 64th Conference on Decision and Control (CDC)","raw_type":"proceedings-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/A5100425396","display_name":"Tianqi Zhang","orcid":"https://orcid.org/0000-0003-3581-6184"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Tianqi Zhang","raw_affiliation_strings":["Tsinghua University,Weiyang College,Beijing,China,100084"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Weiyang College,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102646876","display_name":"Puzhen Yuan","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Puzhen Yuan","raw_affiliation_strings":["Tsinghua University,Xingjian College,Beijing,China,100084"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Xingjian College,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029301375","display_name":"Guojian Zhan","orcid":"https://orcid.org/0000-0002-1246-4860"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guojian Zhan","raw_affiliation_strings":["Tsinghua University,School of Vehicle and Mobility,Beijing,China,100084"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,School of Vehicle and Mobility,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037283185","display_name":"Ziyu Lin","orcid":"https://orcid.org/0000-0003-0532-0030"},"institutions":[{"id":"https://openalex.org/I52158045","display_name":"China Agricultural University","ror":"https://ror.org/04v3ywz14","country_code":"CN","type":"education","lineage":["https://openalex.org/I52158045"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziyu Lin","raw_affiliation_strings":["China Agricultural University,College of Engineering,Beijing,China,100083"],"affiliations":[{"raw_affiliation_string":"China Agricultural University,College of Engineering,Beijing,China,100083","institution_ids":["https://openalex.org/I52158045"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122864731","display_name":"Yao Lyu","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yao Lyu","raw_affiliation_strings":["Tsinghua University,School of Vehicle and Mobility,Beijing,China,100084"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,School of Vehicle and Mobility,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035509853","display_name":"Zhenzhi Qin","orcid":"https://orcid.org/0000-0001-7301-4743"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenzhi Qin","raw_affiliation_strings":["Tsinghua University,Department of Mathematical Sciences,Beijing,China,100084"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Mathematical Sciences,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067909017","display_name":"Jingliang Duan","orcid":"https://orcid.org/0000-0002-3697-1576"},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingliang Duan","raw_affiliation_strings":["University of Science and Technology Beijing,School of Mechanical Engineering,Beijing,China,100083"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology Beijing,School of Mechanical Engineering,Beijing,China,100083","institution_ids":["https://openalex.org/I92403157"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122848671","display_name":"Liping Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liping Zhang","raw_affiliation_strings":["Tsinghua University,Department of Mathematical Sciences,Beijing,China,100084"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Mathematical Sciences,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5122897894","display_name":"Shengbo Eben Li","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengbo Eben Li","raw_affiliation_strings":["Tsinghua University,School of Vehicle and Mobility,Beijing,China,100084"],"affiliations":[{"raw_affiliation_string":"Tsinghua University,School of Vehicle and Mobility,Beijing,China,100084","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5100425396"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.74066602,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5819","last_page":"5824"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.5911999940872192,"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":0.5911999940872192,"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":0.13220000267028809,"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":0.066600002348423,"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/lagrange-multiplier","display_name":"Lagrange multiplier","score":0.807699978351593},{"id":"https://openalex.org/keywords/augmented-lagrangian-method","display_name":"Augmented Lagrangian method","score":0.7493000030517578},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6189000010490417},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.6068999767303467},{"id":"https://openalex.org/keywords/constrained-optimization","display_name":"Constrained optimization","score":0.5494999885559082},{"id":"https://openalex.org/keywords/equivalence","display_name":"Equivalence (formal languages)","score":0.5189999938011169},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.4885999858379364},{"id":"https://openalex.org/keywords/multiplier","display_name":"Multiplier (economics)","score":0.47510001063346863},{"id":"https://openalex.org/keywords/optimization-problem","display_name":"Optimization problem","score":0.47209998965263367}],"concepts":[{"id":"https://openalex.org/C73684929","wikidata":"https://www.wikidata.org/wiki/Q598870","display_name":"Lagrange multiplier","level":2,"score":0.807699978351593},{"id":"https://openalex.org/C150452318","wikidata":"https://www.wikidata.org/wiki/Q4820432","display_name":"Augmented Lagrangian method","level":2,"score":0.7493000030517578},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6189000010490417},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.6068999767303467},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5975000262260437},{"id":"https://openalex.org/C55660270","wikidata":"https://www.wikidata.org/wiki/Q5164377","display_name":"Constrained optimization","level":2,"score":0.5494999885559082},{"id":"https://openalex.org/C2780069185","wikidata":"https://www.wikidata.org/wiki/Q7977945","display_name":"Equivalence (formal languages)","level":2,"score":0.5189999938011169},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.4885999858379364},{"id":"https://openalex.org/C124584101","wikidata":"https://www.wikidata.org/wiki/Q1053266","display_name":"Multiplier (economics)","level":2,"score":0.47510001063346863},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.47209998965263367},{"id":"https://openalex.org/C91765299","wikidata":"https://www.wikidata.org/wiki/Q3424292","display_name":"Lagrangian relaxation","level":2,"score":0.4562999904155731},{"id":"https://openalex.org/C172205157","wikidata":"https://www.wikidata.org/wiki/Q1782962","display_name":"Model predictive control","level":3,"score":0.4311999976634979},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4311000108718872},{"id":"https://openalex.org/C47116090","wikidata":"https://www.wikidata.org/wiki/Q716829","display_name":"PID controller","level":3,"score":0.4259999990463257},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4228000044822693},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.39570000767707825},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.3905999958515167},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.36070001125335693},{"id":"https://openalex.org/C53469067","wikidata":"https://www.wikidata.org/wiki/Q505735","display_name":"Lagrangian","level":2,"score":0.3248000144958496},{"id":"https://openalex.org/C3018651601","wikidata":"https://www.wikidata.org/wiki/Q183635","display_name":"Feedback control","level":2,"score":0.32100000977516174},{"id":"https://openalex.org/C62431964","wikidata":"https://www.wikidata.org/wiki/Q2271572","display_name":"Separation principle","level":4,"score":0.3174000084400177},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.3163999915122986},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2840000092983246},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.2757999897003174},{"id":"https://openalex.org/C173246807","wikidata":"https://www.wikidata.org/wiki/Q7833062","display_name":"Trajectory optimization","level":3,"score":0.2736999988555908},{"id":"https://openalex.org/C77405623","wikidata":"https://www.wikidata.org/wiki/Q598451","display_name":"System dynamics","level":2,"score":0.27219998836517334},{"id":"https://openalex.org/C2989514635","wikidata":"https://www.wikidata.org/wiki/Q5164377","display_name":"Constrained optimization problem","level":3,"score":0.250900000333786}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc57313.2025.11312093","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc57313.2025.11312093","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 64th Conference on Decision and Control (CDC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7427343130111694,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322392","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Constrained":[0],"optimization":[1,24,40,71,243],"is":[2,115,119,124,133,191],"popularly":[3],"seen":[4],"in":[5],"reinforcement":[6],"learning":[7,145],"(RL)":[8],"for":[9,76],"addressing":[10],"complex":[11],"control":[12,36,74,106,113,228],"tasks.":[13],"From":[14],"the":[15,30,67,77,93,97,112,117,122,131,157,169,172,187,207,216,231,251],"perspective":[16],"of":[17,33,79,92,171,209,218],"dynamic":[18],"system,":[19,75],"iteratively":[20],"solving":[21,101],"a":[22,34,60,102,141,201,222,237,256,264],"constrained":[23,39,70,83,174],"problem":[25,107],"can":[26],"be":[27],"framed":[28],"as":[29,43,230],"temporal":[31],"evolution":[32,95],"feedback":[35,53,73,104,212,232],"system.":[37],"Classical":[38],"methods,":[41],"such":[42],"penalty":[44],"and":[45,51,72,130,165,234,263],"Lagrangian":[46,190,242,253],"approaches,":[47],"inherently":[48],"use":[49],"proportional":[50],"integral":[52],"controllers.":[54],"In":[55,109],"this":[56,110],"paper,":[57],"we":[58,87,139,154,183,224],"propose":[59,236],"more":[61,81],"generic":[62],"equivalence":[63,180],"framework":[64,198],"to":[65,134,148,261],"build":[66],"connection":[68],"between":[69],"purpose":[78],"developing":[80],"effective":[82],"RL":[84,175],"algorithms.":[85,220],"Firstly,":[86],"define":[88],"that":[89,156,186,199],"each":[90],"step":[91],"system":[94],"determines":[96],"Lagrange":[98],"multiplier":[99,103,142],"by":[100,126],"optimal":[105,159],"(MFOCP).":[108],"problem,":[111,176],"input":[114],"multiplier,":[116],"state":[118],"policy":[120,127,144,150],"parameters,":[121],"dynamics":[123],"described":[125],"gradient":[128],"descent,":[129],"objective":[132],"minimize":[135],"constraint":[136],"violations.":[137],"Then,":[138],"introduce":[140],"guided":[143],"(MGPL)":[146],"module":[147],"perform":[149],"parameters":[151],"updating.":[152],"And":[153],"prove":[155],"resulting":[158],"policy,":[160],"achieved":[161],"through":[162],"alternating":[163],"MFOCP":[164],"MGPL,":[166],"aligns":[167],"with":[168],"solution":[170],"primal":[173],"thereby":[177,214],"establishing":[178],"our":[179,197],"framework.":[181],"Furthermore,":[182],"point":[184],"out":[185],"existing":[188],"PID":[189,202,252],"merely":[192],"one":[193],"special":[194],"case":[195],"within":[196],"utilizes":[200],"controller.":[203],"We":[204],"also":[205],"accommodate":[206],"integration":[208],"other":[210],"various":[211],"controllers,":[213],"facilitating":[215],"development":[217],"new":[219,238],"As":[221],"representative,":[223],"employ":[225],"model":[226],"predictive":[227,241],"(MPC)":[229],"controller":[233],"consequently":[235],"algorithm":[239],"called":[240],"(PLO).":[244],"Numerical":[245],"experiments":[246],"demonstrate":[247],"its":[248],"superiority":[249],"over":[250],"method,":[254],"achieving":[255],"larger":[257],"feasible":[258],"region":[259],"up":[260],"7.2%":[262],"comparable":[265],"average":[266],"reward.":[267]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2026-01-14T00:00:00"}