{"id":"https://openalex.org/W4290987548","doi":"https://doi.org/10.1613/jair.1.13981","title":"Joint Optimization of Concave Scalarized Multi-Objective Reinforcement Learning with Policy Gradient Based Algorithm","display_name":"Joint Optimization of Concave Scalarized Multi-Objective Reinforcement Learning with Policy Gradient Based Algorithm","publication_year":2022,"publication_date":"2022-08-09","ids":{"openalex":"https://openalex.org/W4290987548","doi":"https://doi.org/10.1613/jair.1.13981"},"language":"en","primary_location":{"id":"doi:10.1613/jair.1.13981","is_oa":true,"landing_page_url":"https://doi.org/10.1613/jair.1.13981","pdf_url":"https://jair.org/index.php/jair/article/download/13981/26834","source":{"id":"https://openalex.org/S139930977","display_name":"Journal of Artificial Intelligence Research","issn_l":"1076-9757","issn":["1076-9757","1943-5037"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310315760","host_organization_name":"AI Access Foundation","host_organization_lineage":["https://openalex.org/P4310315760"],"host_organization_lineage_names":["AI Access Foundation"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Artificial Intelligence Research","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://jair.org/index.php/jair/article/download/13981/26834","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5075904309","display_name":"Qinbo Bai","orcid":"https://orcid.org/0000-0003-2933-1180"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Qinbo Bai","raw_affiliation_strings":["Purdue University"],"affiliations":[{"raw_affiliation_string":"Purdue University","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111079060","display_name":"Mridul Agarwal","orcid":null},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mridul Agarwal","raw_affiliation_strings":["Purdue University,"],"affiliations":[{"raw_affiliation_string":"Purdue University,","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064822688","display_name":"Vaneet Aggarwal","orcid":"https://orcid.org/0000-0001-9131-4723"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vaneet Aggarwal","raw_affiliation_strings":["a:1:{s:5:\"en_US\";s:17:\"Purdue University\";}","a:1:{s:5:\"en_US\"","s:17:\"Purdue University\""],"affiliations":[{"raw_affiliation_string":"a:1:{s:5:\"en_US\";s:17:\"Purdue University\";}","institution_ids":["https://openalex.org/I219193219"]},{"raw_affiliation_string":"a:1:{s:5:\"en_US\"","institution_ids":[]},{"raw_affiliation_string":"s:17:\"Purdue University\"","institution_ids":["https://openalex.org/I219193219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5075904309"],"corresponding_institution_ids":["https://openalex.org/I219193219"],"apc_list":null,"apc_paid":null,"fwci":0.7305,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.73401245,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"74","issue":null,"first_page":"1565","last_page":"1597"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.9987000226974487,"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/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.9987000226974487,"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.9779999852180481,"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"}},{"id":"https://openalex.org/T11663","display_name":"Viral Infectious Diseases and Gene Expression in Insects","score":0.9642000198364258,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.755835235118866},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.6438234448432922},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.6394109129905701},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.5948611497879028},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.5272062420845032},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5264376401901245},{"id":"https://openalex.org/keywords/gradient-method","display_name":"Gradient method","score":0.516435444355011},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.45964717864990234},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.45843276381492615},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.4163472354412079},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.37492769956588745},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2349798083305359},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.1094450056552887}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.755835235118866},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6438234448432922},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.6394109129905701},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.5948611497879028},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.5272062420845032},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5264376401901245},{"id":"https://openalex.org/C115680565","wikidata":"https://www.wikidata.org/wiki/Q5977448","display_name":"Gradient method","level":2,"score":0.516435444355011},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.45964717864990234},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.45843276381492615},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.4163472354412079},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.37492769956588745},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2349798083305359},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.1094450056552887},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"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/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","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/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1613/jair.1.13981","is_oa":true,"landing_page_url":"https://doi.org/10.1613/jair.1.13981","pdf_url":"https://jair.org/index.php/jair/article/download/13981/26834","source":{"id":"https://openalex.org/S139930977","display_name":"Journal of Artificial Intelligence Research","issn_l":"1076-9757","issn":["1076-9757","1943-5037"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310315760","host_organization_name":"AI Access Foundation","host_organization_lineage":["https://openalex.org/P4310315760"],"host_organization_lineage_names":["AI Access Foundation"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Artificial Intelligence Research","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1613/jair.1.13981","is_oa":true,"landing_page_url":"https://doi.org/10.1613/jair.1.13981","pdf_url":"https://jair.org/index.php/jair/article/download/13981/26834","source":{"id":"https://openalex.org/S139930977","display_name":"Journal of Artificial Intelligence Research","issn_l":"1076-9757","issn":["1076-9757","1943-5037"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310315760","host_organization_name":"AI Access Foundation","host_organization_lineage":["https://openalex.org/P4310315760"],"host_organization_lineage_names":["AI Access Foundation"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Artificial Intelligence Research","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.5,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4290987548.pdf","grobid_xml":"https://content.openalex.org/works/W4290987548.grobid-xml"},"referenced_works_count":52,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2098441552","https://openalex.org/W2112964839","https://openalex.org/W2116383462","https://openalex.org/W2119717200","https://openalex.org/W2122011919","https://openalex.org/W2125612430","https://openalex.org/W2130801532","https://openalex.org/W2148053762","https://openalex.org/W2155027007","https://openalex.org/W2156737235","https://openalex.org/W2169206416","https://openalex.org/W2769015503","https://openalex.org/W2902298341","https://openalex.org/W2947580152","https://openalex.org/W2951915386","https://openalex.org/W2959895084","https://openalex.org/W2963049774","https://openalex.org/W2964410826","https://openalex.org/W2964986650","https://openalex.org/W2971587637","https://openalex.org/W2974544365","https://openalex.org/W2990118529","https://openalex.org/W3007795330","https://openalex.org/W3012855655","https://openalex.org/W3024652448","https://openalex.org/W3038915804","https://openalex.org/W3041202696","https://openalex.org/W3046395471","https://openalex.org/W3046626913","https://openalex.org/W3103047293","https://openalex.org/W3109546547","https://openalex.org/W3132054471","https://openalex.org/W3139377883","https://openalex.org/W3200353301","https://openalex.org/W4230563027","https://openalex.org/W4238557920","https://openalex.org/W4285580167","https://openalex.org/W4286979736","https://openalex.org/W4287825207","https://openalex.org/W4289760659","https://openalex.org/W4320473289","https://openalex.org/W6601295022","https://openalex.org/W6631190155","https://openalex.org/W6676898700","https://openalex.org/W6679257226","https://openalex.org/W6683195989","https://openalex.org/W6751972096","https://openalex.org/W6752725515","https://openalex.org/W6757058172","https://openalex.org/W6774253666","https://openalex.org/W6780394890"],"related_works":["https://openalex.org/W3074294383","https://openalex.org/W4206669594","https://openalex.org/W2959276766","https://openalex.org/W4295941380","https://openalex.org/W260766989","https://openalex.org/W3139193008","https://openalex.org/W1988224349","https://openalex.org/W3111983280","https://openalex.org/W3164468573","https://openalex.org/W2030530201"],"abstract_inverted_index":{"Many":[0],"engineering":[1],"problems":[2],"have":[3],"multiple":[4,33],"objectives,":[5],"and":[6,86],"the":[7,24,44,51,72,83,89,92,96,102,107],"overall":[8],"aim":[9],"is":[10,41,57,62,82,88],"to":[11,64,67],"optimize":[12],"a":[13,28],"non-linear":[14,29],"function":[15,31],"of":[16,26,32,50,71,91],"these":[17],"objectives.":[18,35],"In":[19],"this":[20],"paper,":[21],"we":[22],"formulate":[23],"problem":[25],"maximizing":[27],"concave":[30],"long-term":[34],"A":[36],"policy-gradient":[37],"based":[38],"model-free":[39],"algorithm":[40,61,105],"proposed":[42,60],"for":[43,106],"problem.":[45],"To":[46],"compute":[47],"an":[48,53,69],"estimate":[49],"gradient,":[52],"asymptotically":[54],"biased":[55],"estimator":[56],"proposed.":[58],"The":[59],"shown":[63],"achieve":[65],"convergence":[66],"within":[68],"\u03b5":[70,100],"global":[73],"optima":[74],"after":[75],"sampling":[76],"O(M4":[77],"\u03c32/(1-\u03b3)8\u03b54)":[78],"trajectories":[79],"where":[80],"\u03b3":[81],"discount":[84],"factor":[85],"M":[87],"number":[90],"agents,":[93],"thus":[94],"achieving":[95],"same":[97],"dependence":[98],"on":[99],"as":[101],"policy":[103],"gradient":[104],"standard":[108],"reinforcement":[109],"learning.":[110]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2022-08-13T00:00:00"}
