{"id":"https://openalex.org/W4210527295","doi":"https://doi.org/10.1109/cdc45484.2021.9683088","title":"Augmented Lagrangian Method for Instantaneously Constrained Reinforcement Learning Problems","display_name":"Augmented Lagrangian Method for Instantaneously Constrained Reinforcement Learning Problems","publication_year":2021,"publication_date":"2021-12-14","ids":{"openalex":"https://openalex.org/W4210527295","doi":"https://doi.org/10.1109/cdc45484.2021.9683088"},"language":"en","primary_location":{"id":"doi:10.1109/cdc45484.2021.9683088","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc45484.2021.9683088","pdf_url":null,"source":{"id":"https://openalex.org/S4363607724","display_name":"2021 60th IEEE Conference on Decision and Control (CDC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 60th IEEE Conference on Decision and Control (CDC)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5102857137","display_name":"Jingqi Li","orcid":null},"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":"Jingqi Li","raw_affiliation_strings":["University of California, Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070827615","display_name":"David Fridovich-Keil","orcid":"https://orcid.org/0000-0002-5866-6441"},"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":"David Fridovich-Keil","raw_affiliation_strings":["Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072786751","display_name":"Somayeh Sojoudi","orcid":"https://orcid.org/0000-0001-7177-7712"},"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":"Somayeh Sojoudi","raw_affiliation_strings":["University of California, Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045155646","display_name":"Claire J. Tomlin","orcid":"https://orcid.org/0000-0003-3192-3185"},"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":"Claire J. Tomlin","raw_affiliation_strings":["University of California, Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.4651,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.85900971,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2982","last_page":"2989"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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":0.9998999834060669,"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/T12288","display_name":"Optimization and Search Problems","score":0.9896000027656555,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9819999933242798,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8290492296218872},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7944770455360413},{"id":"https://openalex.org/keywords/augmented-lagrangian-method","display_name":"Augmented Lagrangian method","score":0.7296599745750427},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.7054569721221924},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5615630149841309},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5140255689620972},{"id":"https://openalex.org/keywords/lagrangian-relaxation","display_name":"Lagrangian relaxation","score":0.4736053943634033},{"id":"https://openalex.org/keywords/lagrangian","display_name":"Lagrangian","score":0.46724677085876465},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.44656118750572205},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.44551753997802734},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.44100168347358704},{"id":"https://openalex.org/keywords/duality","display_name":"Duality (order theory)","score":0.4392673969268799},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.35000646114349365},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.21233174204826355},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.14117392897605896}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8290492296218872},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7944770455360413},{"id":"https://openalex.org/C150452318","wikidata":"https://www.wikidata.org/wiki/Q4820432","display_name":"Augmented Lagrangian method","level":2,"score":0.7296599745750427},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.7054569721221924},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5615630149841309},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5140255689620972},{"id":"https://openalex.org/C91765299","wikidata":"https://www.wikidata.org/wiki/Q3424292","display_name":"Lagrangian relaxation","level":2,"score":0.4736053943634033},{"id":"https://openalex.org/C53469067","wikidata":"https://www.wikidata.org/wiki/Q505735","display_name":"Lagrangian","level":2,"score":0.46724677085876465},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.44656118750572205},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.44551753997802734},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.44100168347358704},{"id":"https://openalex.org/C2778023678","wikidata":"https://www.wikidata.org/wiki/Q554403","display_name":"Duality (order theory)","level":2,"score":0.4392673969268799},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.35000646114349365},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.21233174204826355},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.14117392897605896},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc45484.2021.9683088","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc45484.2021.9683088","pdf_url":null,"source":{"id":"https://openalex.org/S4363607724","display_name":"2021 60th IEEE Conference on Decision and Control (CDC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 60th IEEE Conference on Decision and Control (CDC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.8100000023841858,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320338279","display_name":"Air Force Office of Scientific Research","ror":"https://ror.org/011e9bt93"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":55,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W1518931405","https://openalex.org/W1771410628","https://openalex.org/W1778554682","https://openalex.org/W1971086298","https://openalex.org/W2027579135","https://openalex.org/W2038818107","https://openalex.org/W2108114251","https://openalex.org/W2145339207","https://openalex.org/W2155007355","https://openalex.org/W2284269953","https://openalex.org/W2342662072","https://openalex.org/W2530849036","https://openalex.org/W2575705757","https://openalex.org/W2583891003","https://openalex.org/W2766413382","https://openalex.org/W2781726626","https://openalex.org/W2803974723","https://openalex.org/W2895492910","https://openalex.org/W2902298341","https://openalex.org/W2905810301","https://openalex.org/W2950471160","https://openalex.org/W2963293747","https://openalex.org/W2963864421","https://openalex.org/W2968547875","https://openalex.org/W2998619042","https://openalex.org/W3004186391","https://openalex.org/W3083356404","https://openalex.org/W3085121432","https://openalex.org/W3156919398","https://openalex.org/W3162902207","https://openalex.org/W4293545785","https://openalex.org/W4294562617","https://openalex.org/W4297824337","https://openalex.org/W4300448178","https://openalex.org/W4301501993","https://openalex.org/W4320930577","https://openalex.org/W6638018090","https://openalex.org/W6638026421","https://openalex.org/W6676576766","https://openalex.org/W6682849425","https://openalex.org/W6684921986","https://openalex.org/W6687063787","https://openalex.org/W6696324988","https://openalex.org/W6704571135","https://openalex.org/W6737893269","https://openalex.org/W6745594345","https://openalex.org/W6746023985","https://openalex.org/W6747473740","https://openalex.org/W6751437432","https://openalex.org/W6751535212","https://openalex.org/W6757058172","https://openalex.org/W6770009701","https://openalex.org/W6770036965","https://openalex.org/W6780559895"],"related_works":["https://openalex.org/W3007368744","https://openalex.org/W2390246627","https://openalex.org/W4285149922","https://openalex.org/W2376104286","https://openalex.org/W1967010422","https://openalex.org/W2088707050","https://openalex.org/W166252871","https://openalex.org/W2027569164","https://openalex.org/W4236384091","https://openalex.org/W3010376936"],"abstract_inverted_index":{"In":[0],"this":[1,103],"paper,":[2],"we":[3,14,69],"study":[4],"the":[5,36,46,57,62,111,160],"Instantaneously":[6],"Constrained":[7,40],"Reinforcement":[8],"Learning":[9],"(ICRL)":[10],"problem,":[11],"in":[12,45,66,152],"which":[13,78],"are":[15],"tasked":[16],"to":[17,110,159],"find":[18],"a":[19,33,50,71,93,119,130,134,153],"reward-maximizing":[20],"policy":[21,97,113],"while":[22],"satisfying":[23],"certain":[24,107],"constraints":[25],"at":[26],"each":[27],"time":[28],"step.":[29],"We":[30,89],"first":[31],"extend":[32],"result":[34],"on":[35,118],"strong":[37,54],"duality":[38,55],"of":[39,56,156],"Markov":[41,121],"Decision":[42,122],"Process":[43,123],"(CMDP)":[44],"literature":[47],"and":[48,95,124,133,140,150],"propose":[49,70],"sufficient":[51],"condition":[52],"for":[53,76],"ICRL":[58],"problem.":[59],"Inspired":[60],"by":[61,83,101],"Augmented":[63],"Lagrangian":[64],"Method":[65],"constrained":[67,131,135],"optimization,":[68],"new":[72],"surrogate":[73,104],"objective":[74],"function":[75],"ICRL,":[77],"could":[79,98,145],"be":[80,99],"efficiently":[81],"optimized":[82],"common":[84],"policy-gradient":[85],"based":[86],"RL":[87],"algorithms.":[88,162],"show":[90],"theoretically":[91],"that":[92,142],"feasible":[94,112],"optimal":[96,127],"obtained":[100],"optimizing":[102],"function,":[105],"under":[106],"conditions":[108],"related":[109],"set.":[114],"Our":[115],"empirical":[116],"results":[117],"tabular":[120],"two":[125],"nonlinear":[126],"control":[128],"problems,":[129],"pendulum":[132],"half-cheetah,":[136],"justify":[137],"our":[138,143],"analysis,":[139],"suggest":[141],"method":[144],"promote":[146],"safety":[147],"during":[148],"learning":[149],"converge":[151],"smaller":[154],"number":[155],"iterations":[157],"compared":[158],"existing":[161]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-31T08:31:51.225901","created_date":"2025-10-10T00:00:00"}