{"id":"https://openalex.org/W2963758131","doi":"https://doi.org/10.1609/aaai.v29i1.9617","title":"Multi-Objective Reinforcement Learning with Continuous Pareto Frontier Approximation","display_name":"Multi-Objective Reinforcement Learning with Continuous Pareto Frontier Approximation","publication_year":2015,"publication_date":"2015-02-21","ids":{"openalex":"https://openalex.org/W2963758131","doi":"https://doi.org/10.1609/aaai.v29i1.9617","mag":"2963758131"},"language":"en","primary_location":{"id":"pmh:oai:ojs.aaai.org:article/9617","doi":"https://doi.org/10.1609/aaai.v29i1.9617","is_oa":true,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/9617","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/9617/9476","source":{"id":"https://openalex.org/S4306400155","display_name":"AAAI Publications (The Association for the Advancement of Artificial Intelligence (AAAI))","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2801652627","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/I2801652627"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"},"volume":null,"type":"article","indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/9617/9476","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5091526684","display_name":"Matteo Pirotta","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Pirotta, Matteo","raw_affiliation_strings":["Politecnico di Milano"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Politecnico di Milano","institution_ids":["https://openalex.org/I93860229"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Parisi, Simone","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Parisi, Simone","raw_affiliation_strings":["Politecnico di Milano"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Politecnico di Milano","institution_ids":["https://openalex.org/I93860229"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017130830","display_name":"Marcello Restelli","orcid":"https://orcid.org/0000-0002-6322-1076","observed_orcids":["https://orcid.org/0000-0002-6322-1076"]},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Restelli, Marcello","raw_affiliation_strings":["Politecnico di Milano"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Politecnico di Milano","institution_ids":["https://openalex.org/I93860229"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I93860229"],"apc_list":null,"apc_paid":null,"fwci":2.4878,"has_fulltext":true,"cited_by_count":42,"citation_normalized_percentile":{"value":0.91108589,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.7846999764442444,"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":0.7846999764442444,"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/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.2134000062942505,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.00039999998989515007,"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/multi-objective-reinforcement-learning","display_name":"multi-objective reinforcement learning","score":0.996999979019165},{"id":"https://openalex.org/keywords/pareto-front-approximation","display_name":"Pareto front approximation","score":0.9039999842643738},{"id":"https://openalex.org/keywords/multi-objective-markov-decision-process","display_name":"multi-objective Markov decision process","score":0.9399999976158142},{"id":"https://openalex.org/keywords/policy-gradient","display_name":"policy gradient","score":0.8270000219345093},{"id":"https://openalex.org/keywords/gradient-ascent","display_name":"gradient ascent","score":0.6200000047683716},{"id":"https://openalex.org/keywords/gradient-estimation","display_name":"gradient estimation","score":0.4860000014305115},{"id":"https://openalex.org/keywords/continuum-approximation","display_name":"continuum approximation","score":0.4429999887943268}],"concepts":[{"id":"https://openalex.org/C137635306","wikidata":"https://www.wikidata.org/wiki/Q182667","display_name":"Pareto principle","level":2,"score":0.8386828899383545},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.6670087575912476},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.6153777241706848},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5637645125389099},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5298298001289368},{"id":"https://openalex.org/C68781425","wikidata":"https://www.wikidata.org/wiki/Q2052203","display_name":"Multi-objective optimization","level":2,"score":0.4522862136363983},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.43893855810165405},{"id":"https://openalex.org/C38814450","wikidata":"https://www.wikidata.org/wiki/Q7136870","display_name":"Pareto interpolation","level":4,"score":0.4344594180583954},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.32523125410079956},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.20141685009002686},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.11362653970718384},{"id":"https://openalex.org/C133514767","wikidata":"https://www.wikidata.org/wiki/Q5532448","display_name":"Generalized Pareto distribution","level":3,"score":0.10316246747970581},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C147581598","wikidata":"https://www.wikidata.org/wiki/Q729429","display_name":"Extreme value theory","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:ojs.aaai.org:article/9617","doi":"https://doi.org/10.1609/aaai.v29i1.9617","is_oa":true,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/9617","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/9617/9476","source":{"id":"https://openalex.org/S4306400155","display_name":"AAAI Publications (The Association for the Advancement of Artificial Intelligence (AAAI))","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2801652627","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/I2801652627"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"pmh:oai:ojs.aaai.org:article/9617","doi":"https://doi.org/10.1609/aaai.v29i1.9617","is_oa":true,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/9617","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/9617/9476","source":{"id":"https://openalex.org/S4306400155","display_name":"AAAI Publications (The Association for the Advancement of Artificial Intelligence (AAAI))","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2801652627","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/I2801652627"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, justice, and strong institutions","score":0.6700000166893005}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2963758131.pdf","grobid_xml":"https://content.openalex.org/works/W2963758131.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W1518318201","https://openalex.org/W1606011487","https://openalex.org/W1872977731","https://openalex.org/W1885890946","https://openalex.org/W1988210060","https://openalex.org/W2012612381","https://openalex.org/W2033976720","https://openalex.org/W2047437401","https://openalex.org/W2070365265","https://openalex.org/W2095792542","https://openalex.org/W2098907614","https://openalex.org/W2112964839","https://openalex.org/W2115126871","https://openalex.org/W2125612430","https://openalex.org/W2133275519","https://openalex.org/W2155027007","https://openalex.org/W2156679542","https://openalex.org/W2963286541","https://openalex.org/W3103262232","https://openalex.org/W4214717370","https://openalex.org/W4230563027","https://openalex.org/W4231176797","https://openalex.org/W4292691288"],"related_works":["https://openalex.org/W2402393579","https://openalex.org/W3089681648","https://openalex.org/W2012991245","https://openalex.org/W4240829493","https://openalex.org/W3130787283","https://openalex.org/W3133591683","https://openalex.org/W2006511703","https://openalex.org/W2058192020","https://openalex.org/W2333837981","https://openalex.org/W2090178682"],"abstract_inverted_index":{"This":[0],"paper":[1],"is":[2,70],"about":[3],"learning":[4],"a":[5,19,52,73,81,85,127],"continuous":[6,63],"approximation":[7,64],"of":[8,65,80,125,133,140],"the":[9,31,66,78,88,94,98,107,122,131,134,138,141],"Pareto":[10,32,67,108,136],"frontier":[11],"in":[12,87,97],"Multi-Objective":[13],"Markov":[14],"Decision":[15],"Problems":[16],"(MOMDPs).We":[17],"propose":[18],"policy-based":[20],"approach":[21,50,75,143],"that":[22,56,83,93],"exploits":[23],"gradient":[24],"information":[25],"to":[26,30,45,71,76,106,112,129],"generate":[27],"solutions":[28],"close":[29,103],"ones.Differently":[33],"from":[34],"previous":[35],"policy-gradient":[36],"multi-objective":[37],"algorithms,":[38],"where":[39],"n":[40,47],"optimization":[41],"routines":[42],"are":[43,144],"used":[44],"have":[46],"solutions,":[48],"our":[49],"performs":[51],"single":[53],"gradient-ascent":[54],"run":[55],"at":[57],"each":[58],"step":[59],"generates":[60],"an":[61],"improved":[62],"frontier.The":[68],"idea":[69],"exploit":[72],"gradient-based":[74],"optimize":[77],"parameters":[79],"function":[82],"defines":[84],"manifold":[86],"policy":[89],"parameter":[90],"space":[91,100],"so":[92],"corresponding":[95],"image":[96],"objective":[99],"gets":[101],"as":[102,104],"possible":[105],"frontier.Besides":[109],"deriving":[110],"how":[111],"compute":[113],"and":[114],"estimate":[115],"such":[116],"gradient,":[117],"we":[118],"will":[119],"also":[120],"discuss":[121],"non-trivial":[123],"issue":[124],"defining":[126],"metric":[128],"assess":[130],"quality":[132],"candidate":[135],"frontiers.Finally,":[137],"properties":[139],"proposed":[142],"empirically":[145],"evaluated":[146],"on":[147],"two":[148],"interesting":[149],"MOMDPs.":[150]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":5},{"year":2014,"cited_by_count":2}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2025-10-10T00:00:00"}