{"id":"https://openalex.org/W4406354674","doi":"https://doi.org/10.1109/tpami.2025.3528944","title":"Safe and Balanced: A Framework for Constrained Multi-Objective Reinforcement Learning","display_name":"Safe and Balanced: A Framework for Constrained Multi-Objective Reinforcement Learning","publication_year":2025,"publication_date":"2025-01-14","ids":{"openalex":"https://openalex.org/W4406354674","doi":"https://doi.org/10.1109/tpami.2025.3528944","pmid":"https://pubmed.ncbi.nlm.nih.gov/40031004"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2025.3528944","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3528944","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1109/tpami.2025.3528944","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5062677595","display_name":"Shangding Gu","orcid":"https://orcid.org/0000-0002-2722-3779"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]},{"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":["DE","US"],"is_corresponding":true,"raw_author_name":"Shangding Gu","raw_affiliation_strings":["Department of Electrical Engineering and Computer Sciences, University of California, Berkeley, CA, USA","Department of Informatics, Technical University of Munich, Munich, Germany"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Sciences, University of California, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"Department of Informatics, Technical University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017539185","display_name":"Bilgehan Sel","orcid":"https://orcid.org/0000-0001-8701-6539"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bilgehan Sel","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Virginia Tech, Blacksburg, VA, USA","Department of Electrical and Computer Engineering, Virginia Tech, Blacksburg, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Virginia Tech, Blacksburg, VA, USA","institution_ids":["https://openalex.org/I859038795"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Virginia Tech, Blacksburg, USA","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102879163","display_name":"Yuhao Ding","orcid":"https://orcid.org/0000-0002-1521-7566"},"institutions":[{"id":"https://openalex.org/I4210161058","display_name":"Vital Strategies","ror":"https://ror.org/05mdyn772","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210161058"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuhao Ding","raw_affiliation_strings":["Cubist Systematic Strategies, New York City, NY, USA","Cubist Systematic Strategies (work done prior to joining or outside of Cubist Systematic Strategies), New York City, USA"],"affiliations":[{"raw_affiliation_string":"Cubist Systematic Strategies, New York City, NY, USA","institution_ids":["https://openalex.org/I4210161058"]},{"raw_affiliation_string":"Cubist Systematic Strategies (work done prior to joining or outside of Cubist Systematic Strategies), New York City, USA","institution_ids":["https://openalex.org/I4210161058"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083964854","display_name":"Lu Wang","orcid":"https://orcid.org/0000-0002-7305-1496"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lu Wang","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088646345","display_name":"Qingwei Lin","orcid":"https://orcid.org/0000-0003-2559-2383"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingwei Lin","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063781430","display_name":"Alois Knoll","orcid":"https://orcid.org/0000-0003-4840-076X"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Alois Knoll","raw_affiliation_strings":["Department of Informatics, Technical University of Munich, Munich, Germany"],"affiliations":[{"raw_affiliation_string":"Department of Informatics, Technical University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101484129","display_name":"Ming Jin","orcid":"https://orcid.org/0000-0001-7909-4545"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ming Jin","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Virginia Tech, Blacksburg, VA, USA","Department of Electrical and Computer Engineering, Virginia Tech, Blacksburg, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Virginia Tech, Blacksburg, VA, USA","institution_ids":["https://openalex.org/I859038795"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Virginia Tech, Blacksburg, USA","institution_ids":["https://openalex.org/I859038795"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5062677595"],"corresponding_institution_ids":["https://openalex.org/I62916508","https://openalex.org/I95457486"],"apc_list":null,"apc_paid":null,"fwci":22.3639,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.99198838,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"47","issue":"5","first_page":"3322","last_page":"3331"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.3634999990463257,"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":0.3634999990463257,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7306691408157349},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6189189553260803},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6072936058044434},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4494209587574005},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.37517985701560974},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20936152338981628}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7306691408157349},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6189189553260803},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6072936058044434},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4494209587574005},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.37517985701560974},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20936152338981628}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2025.3528944","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3528944","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:40031004","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40031004","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":{"id":"doi:10.1109/tpami.2025.3528944","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3528944","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W1977655452","https://openalex.org/W2012612381","https://openalex.org/W2060727197","https://openalex.org/W2143346970","https://openalex.org/W2158782408","https://openalex.org/W2535247013","https://openalex.org/W2625286567","https://openalex.org/W2787908307","https://openalex.org/W2788084076","https://openalex.org/W2892521964","https://openalex.org/W2963616027","https://openalex.org/W2964123095","https://openalex.org/W3048735518","https://openalex.org/W3081310128","https://openalex.org/W3085046840","https://openalex.org/W3109546547","https://openalex.org/W3127561923","https://openalex.org/W3157937972","https://openalex.org/W4285600796","https://openalex.org/W4292313830","https://openalex.org/W4327571609","https://openalex.org/W4382318857","https://openalex.org/W4388616010","https://openalex.org/W4402402057","https://openalex.org/W6638018090","https://openalex.org/W6677959772","https://openalex.org/W6679257226","https://openalex.org/W6683204974","https://openalex.org/W6717915398","https://openalex.org/W6737893269","https://openalex.org/W6747387971","https://openalex.org/W6751535212","https://openalex.org/W6751725685","https://openalex.org/W6758924645","https://openalex.org/W6760359693","https://openalex.org/W6771280675","https://openalex.org/W6771876938","https://openalex.org/W6777159553","https://openalex.org/W6780486084","https://openalex.org/W6780559895","https://openalex.org/W6796690604","https://openalex.org/W6803094727","https://openalex.org/W6803156713","https://openalex.org/W6804456054","https://openalex.org/W6810738896","https://openalex.org/W6810766738","https://openalex.org/W6811282592","https://openalex.org/W6850370512","https://openalex.org/W6853523444"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W4387369504","https://openalex.org/W3046775127","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W3107602296","https://openalex.org/W4364306694","https://openalex.org/W4312192474"],"abstract_inverted_index":{"In":[0],"numerous":[1],"reinforcement":[2],"learning":[3,39],"(RL)":[4],"problems":[5],"involving":[6],"safety-critical":[7],"systems,":[8],"a":[9,30,46,89,92],"key":[10],"challenge":[11],"lies":[12],"in":[13,98],"balancing":[14],"multiple":[15,55],"objectives":[16,57,78],"while":[17],"simultaneously":[18],"meeting":[19],"all":[20],"stringent":[21],"safety":[22],"constraints.":[23],"To":[24],"tackle":[25],"this":[26,105],"issue,":[27],"we":[28],"propose":[29],"primal-based":[31],"framework":[32],"that":[33],"orchestrates":[34],"policy":[35,49,102],"optimization":[36],"between":[37,62],"multi-objective":[38,128],"and":[40,58,112,116],"constraint":[41,113],"adherence.":[42],"Our":[43],"method":[44,52,119],"employs":[45],"novel":[47],"natural":[48],"gradient":[50,70],"manipulation":[51],"to":[53,80,99,103],"optimize":[54],"RL":[56,129],"overcome":[59],"conflicting":[60],"gradients":[61,82],"different":[63,84],"objectives,":[64],"since":[65],"the":[66,101],"simple":[67],"weighted":[68],"average":[69],"direction":[71],"may":[72],"not":[73],"be":[74],"beneficial":[75],"for":[76],"specific":[77],"due":[79],"misaligned":[81],"of":[83,91],"objectives.":[85],"When":[86],"there":[87],"is":[88],"violation":[90,114],"hard":[93],"constraint,":[94],"our":[95,117],"algorithm":[96],"steps":[97],"rectify":[100],"minimize":[104],"violation.":[106],"Particularly,":[107],"We":[108],"establish":[109],"theoretical":[110],"convergence":[111],"guarantees,":[115],"proposed":[118],"also":[120],"outperforms":[121],"prior":[122],"state-of-the-art":[123],"methods":[124],"on":[125],"challenging":[126],"safe":[127],"tasks.":[130]},"counts_by_year":[{"year":2025,"cited_by_count":9}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}