{"id":"https://openalex.org/W2588295408","doi":"https://doi.org/10.1109/ssci.2016.7849369","title":"Local-utopia policy selection for multi-objective reinforcement learning","display_name":"Local-utopia policy selection for multi-objective reinforcement learning","publication_year":2016,"publication_date":"2016-12-01","ids":{"openalex":"https://openalex.org/W2588295408","doi":"https://doi.org/10.1109/ssci.2016.7849369","mag":"2588295408"},"language":"en","primary_location":{"id":"doi:10.1109/ssci.2016.7849369","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ssci.2016.7849369","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE Symposium Series on Computational Intelligence (SSCI)","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/A5055633714","display_name":"Simone Parisi","orcid":"https://orcid.org/0000-0003-3886-8131"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technical University of Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Simone Parisi","raw_affiliation_strings":["Intelligent Autonomous Systems Group, Technical University of Darmstadt, Darmstadt, Germany"],"affiliations":[{"raw_affiliation_string":"Intelligent Autonomous Systems Group, Technical University of Darmstadt, Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090832021","display_name":"Alexander Blank","orcid":null},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technical University of Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Alexander Blank","raw_affiliation_strings":["Intelligent Autonomous Systems Group, Technical University of Darmstadt, Darmstadt, Germany"],"affiliations":[{"raw_affiliation_string":"Intelligent Autonomous Systems Group, Technical University of Darmstadt, Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016453747","display_name":"Tobias Viernickel","orcid":null},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technical University of Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Tobias Viernickel","raw_affiliation_strings":["Intelligent Autonomous Systems Group, Technical University of Darmstadt, Darmstadt, Germany"],"affiliations":[{"raw_affiliation_string":"Intelligent Autonomous Systems Group, Technical University of Darmstadt, Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071367253","display_name":"Jan Peters","orcid":"https://orcid.org/0000-0002-5266-8091"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technical University of Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]},{"id":"https://openalex.org/I4210135521","display_name":"Max Planck Institute for Intelligent Systems","ror":"https://ror.org/04fq9j139","country_code":"DE","type":"facility","lineage":["https://openalex.org/I149899117","https://openalex.org/I4210135521"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jan Peters","raw_affiliation_strings":["Intelligent Autonomous Systems Group, Technical University of Darmstadt, Darmstadt, Germany","Max Planck Institute for Intelligent Systems, T\u00fcbingen, Germany"],"affiliations":[{"raw_affiliation_string":"Intelligent Autonomous Systems Group, Technical University of Darmstadt, Darmstadt, Germany","institution_ids":["https://openalex.org/I31512782"]},{"raw_affiliation_string":"Max Planck Institute for Intelligent Systems, T\u00fcbingen, Germany","institution_ids":["https://openalex.org/I4210135521"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5055633714"],"corresponding_institution_ids":["https://openalex.org/I31512782"],"apc_list":null,"apc_paid":null,"fwci":0.3613,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.7118444,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"13","issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.9987999796867371,"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":0.9987999796867371,"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":0.9934999942779541,"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/T10603","display_name":"Smart Grid Energy Management","score":0.9872999787330627,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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/pareto-principle","display_name":"Pareto principle","score":0.8293550610542297},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7795713543891907},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.6859465837478638},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5925772786140442},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5897495746612549},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.5408317446708679},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4931637644767761},{"id":"https://openalex.org/keywords/multi-objective-optimization","display_name":"Multi-objective optimization","score":0.4899060130119324},{"id":"https://openalex.org/keywords/pareto-optimal","display_name":"Pareto optimal","score":0.435986191034317},{"id":"https://openalex.org/keywords/frontier","display_name":"Frontier","score":0.42675989866256714},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40920490026474},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32713112235069275},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.22236603498458862}],"concepts":[{"id":"https://openalex.org/C137635306","wikidata":"https://www.wikidata.org/wiki/Q182667","display_name":"Pareto principle","level":2,"score":0.8293550610542297},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7795713543891907},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.6859465837478638},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5925772786140442},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5897495746612549},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.5408317446708679},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4931637644767761},{"id":"https://openalex.org/C68781425","wikidata":"https://www.wikidata.org/wiki/Q2052203","display_name":"Multi-objective optimization","level":2,"score":0.4899060130119324},{"id":"https://openalex.org/C2986314615","wikidata":"https://www.wikidata.org/wiki/Q36829","display_name":"Pareto optimal","level":3,"score":0.435986191034317},{"id":"https://openalex.org/C2778571376","wikidata":"https://www.wikidata.org/wiki/Q1355821","display_name":"Frontier","level":2,"score":0.42675989866256714},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40920490026474},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32713112235069275},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.22236603498458862},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/ssci.2016.7849369","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ssci.2016.7849369","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE Symposium Series on Computational Intelligence (SSCI)","raw_type":"proceedings-article"},{"id":"pmh:oai:tubiblio.ulb.tu-darmstadt.de:107798","is_oa":false,"landing_page_url":"http://tubiblio.ulb.tu-darmstadt.de/view/person/Parisi=3AS=2E=3A=3A.html>","pdf_url":null,"source":{"id":"https://openalex.org/S4377196390","display_name":"TUbilio (Technical University of Darmstadt)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I31512782","host_organization_name":"Technische Universit\u00e4t Darmstadt","host_organization_lineage":["https://openalex.org/I31512782"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"NonPeerReviewed"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W1482041209","https://openalex.org/W1506010655","https://openalex.org/W1518318201","https://openalex.org/W1547827494","https://openalex.org/W1574700590","https://openalex.org/W1872977731","https://openalex.org/W1990421110","https://openalex.org/W1997188340","https://openalex.org/W1998649829","https://openalex.org/W2012612381","https://openalex.org/W2024608894","https://openalex.org/W2033976720","https://openalex.org/W2045276965","https://openalex.org/W2046994261","https://openalex.org/W2049412031","https://openalex.org/W2060846151","https://openalex.org/W2087255792","https://openalex.org/W2097031964","https://openalex.org/W2116001481","https://openalex.org/W2117428849","https://openalex.org/W2117626647","https://openalex.org/W2125899728","https://openalex.org/W2132482672","https://openalex.org/W2167062306","https://openalex.org/W2185709919","https://openalex.org/W2186820913","https://openalex.org/W2278712528","https://openalex.org/W2290904103","https://openalex.org/W2625286567","https://openalex.org/W2759526291","https://openalex.org/W2963758131","https://openalex.org/W6628934745","https://openalex.org/W6632856477","https://openalex.org/W6639342017","https://openalex.org/W6674628981","https://openalex.org/W6677435986","https://openalex.org/W6677477198","https://openalex.org/W6677504650","https://openalex.org/W6686239993","https://openalex.org/W6694904549","https://openalex.org/W6744321307"],"related_works":["https://openalex.org/W1963790170","https://openalex.org/W2073298047","https://openalex.org/W2033790662","https://openalex.org/W2090178682","https://openalex.org/W2586328217","https://openalex.org/W2049264236","https://openalex.org/W2001591765","https://openalex.org/W4241467429","https://openalex.org/W2073147994","https://openalex.org/W1588199609"],"abstract_inverted_index":{"Many":[0],"real-world":[1],"applications":[2,61],"are":[3],"characterized":[4],"by":[5,15],"multiple":[6],"conflicting":[7],"objectives.":[8,36],"In":[9,67],"such":[10,62],"problems,":[11],"optimality":[12,17],"is":[13,21,53,109],"replaced":[14],"Pareto":[16,25,47,81,117],"and":[18,65,92,99,123,134],"the":[19,24,35,43,46,80,107,121],"goal":[20],"to":[22,84,137],"find":[23],"frontier,":[26,48],"a":[27,50,72,77,88],"set":[28],"of":[29,49,125],"solutions":[30],"representing":[31],"different":[32],"compromises":[33],"among":[34],"Despite":[37],"recent":[38],"advances":[39],"in":[40,59,111],"multi-objective":[41,139],"optimization,":[42],"selection,":[44],"given":[45],"Pareto-optimal":[51,103],"policy":[52,78,104],"still":[54],"an":[55,97],"important":[56],"problem,":[57],"prominent":[58],"practical":[60],"as":[63],"economics":[64],"robotics.":[66],"this":[68],"paper,":[69],"we":[70,128],"present":[71],"versatile":[73],"approach":[74,95],"for":[75,102,115],"selecting":[76],"from":[79],"frontier":[82],"according":[83],"user-defined":[85],"preferences.":[86],"Exploiting":[87],"novel":[89],"scalarization":[90,108],"function":[91],"heuristics,":[93],"our":[94,126],"provides":[96],"easy-to-use":[98],"effective":[100],"method":[101],"selection.":[105],"Furthermore,":[106],"applicable":[110],"multiple-policy":[112],"learning":[113,141],"strategies":[114],"approximating":[116],"frontiers.":[118],"To":[119],"show":[120],"simplicity":[122],"effectiveness":[124],"algorithm,":[127],"evaluate":[129],"it":[130,136],"on":[131],"two":[132],"problems":[133],"compare":[135],"classical":[138],"reinforcement":[140],"approaches.":[142]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
