{"id":"https://openalex.org/W2123516968","doi":"https://doi.org/10.1109/adprl.2014.7010622","title":"Model-based multi-objective reinforcement learning","display_name":"Model-based multi-objective reinforcement learning","publication_year":2014,"publication_date":"2014-12-01","ids":{"openalex":"https://openalex.org/W2123516968","doi":"https://doi.org/10.1109/adprl.2014.7010622","mag":"2123516968"},"language":"en","primary_location":{"id":"doi:10.1109/adprl.2014.7010622","is_oa":false,"landing_page_url":"https://doi.org/10.1109/adprl.2014.7010622","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://pure.rug.nl/ws/files/15836113/Artikel_v2.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5060596453","display_name":"Marco Wiering","orcid":"https://orcid.org/0000-0003-4331-7537"},"institutions":[{"id":"https://openalex.org/I169381384","display_name":"University of Groningen","ror":"https://ror.org/012p63287","country_code":"NL","type":"education","lineage":["https://openalex.org/I169381384"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Marco A. Wiering","raw_affiliation_strings":["Institute of Artificial Intelligence, University of Groningen, The Netherlands"],"affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence, University of Groningen, The Netherlands","institution_ids":["https://openalex.org/I169381384"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050417905","display_name":"Maikel Withagen","orcid":null},"institutions":[{"id":"https://openalex.org/I169381384","display_name":"University of Groningen","ror":"https://ror.org/012p63287","country_code":"NL","type":"education","lineage":["https://openalex.org/I169381384"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Maikel Withagen","raw_affiliation_strings":["Institute of Artificial Intelligence, University of Groningen, The Netherlands"],"affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence, University of Groningen, The Netherlands","institution_ids":["https://openalex.org/I169381384"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016131956","display_name":"M\u0103d\u0103lina M. Drugan","orcid":"https://orcid.org/0000-0001-9497-3134"},"institutions":[{"id":"https://openalex.org/I13469542","display_name":"Vrije Universiteit Brussel","ror":"https://ror.org/006e5kg04","country_code":"BE","type":"education","lineage":["https://openalex.org/I13469542"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Madalina M Drugan","raw_affiliation_strings":["Artificial Intelligence Lab, Vrije Universiteit Brussel, Belgium"],"affiliations":[{"raw_affiliation_string":"Artificial Intelligence Lab, Vrije Universiteit Brussel, Belgium","institution_ids":["https://openalex.org/I13469542"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5060596453"],"corresponding_institution_ids":["https://openalex.org/I169381384"],"apc_list":null,"apc_paid":null,"fwci":3.2903,"has_fulltext":true,"cited_by_count":37,"citation_normalized_percentile":{"value":0.92439636,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.9991999864578247,"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":0.9991999864578247,"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":0.998199999332428,"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/T10969","display_name":"Water resources management and optimization","score":0.9929999709129333,"subfield":{"id":"https://openalex.org/subfields/2212","display_name":"Ocean 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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8965167999267578},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7444773316383362},{"id":"https://openalex.org/keywords/pareto-principle","display_name":"Pareto principle","score":0.6538518667221069},{"id":"https://openalex.org/keywords/pareto-optimal","display_name":"Pareto optimal","score":0.6059523224830627},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5956363677978516},{"id":"https://openalex.org/keywords/dynamic-programming","display_name":"Dynamic programming","score":0.5100513100624084},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4937382638454437},{"id":"https://openalex.org/keywords/multi-objective-optimization","display_name":"Multi-objective optimization","score":0.41350027918815613},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.37263810634613037},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1413257122039795},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10219940543174744}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8965167999267578},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7444773316383362},{"id":"https://openalex.org/C137635306","wikidata":"https://www.wikidata.org/wiki/Q182667","display_name":"Pareto principle","level":2,"score":0.6538518667221069},{"id":"https://openalex.org/C2986314615","wikidata":"https://www.wikidata.org/wiki/Q36829","display_name":"Pareto optimal","level":3,"score":0.6059523224830627},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5956363677978516},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.5100513100624084},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4937382638454437},{"id":"https://openalex.org/C68781425","wikidata":"https://www.wikidata.org/wiki/Q2052203","display_name":"Multi-objective optimization","level":2,"score":0.41350027918815613},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37263810634613037},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1413257122039795},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10219940543174744}],"mesh":[],"locations_count":9,"locations":[{"id":"doi:10.1109/adprl.2014.7010622","is_oa":false,"landing_page_url":"https://doi.org/10.1109/adprl.2014.7010622","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL)","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.rug.nl:publications/92770ca3-8ba9-4560-a2ef-5b9b14f439ac","is_oa":true,"landing_page_url":"https://research.rug.nl/en/publications/92770ca3-8ba9-4560-a2ef-5b9b14f439ac","pdf_url":"https://pure.rug.nl/ws/files/15836113/Artikel_v2.pdf","source":{"id":"https://openalex.org/S4306400420","display_name":"University of Groningen research database (University of Groningen / Centre for Information Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I169381384","host_organization_name":"University of Groningen","host_organization_lineage":["https://openalex.org/I169381384"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Wiering, M, Withagen, M & Drugan, M 2014, Model-Based Multi-Objective Reinforcement Learning. in IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning. IEEE (The Institute of Electrical and Electronics Engineers), Orlando.","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:889205","is_oa":false,"landing_page_url":"http://library.tue.nl/csp/dare/LinkToRepository.csp?recordnumber=889205","pdf_url":null,"source":{"id":"https://openalex.org/S4406923046","display_name":"TU/e Research Portal (Eindhoven University of Technology)","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":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.718.722","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.718.722","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ai.rug.nl/%7Emwiering/GROUP/ARTICLES/Model_Based_MORL.pdf","raw_type":"text"},{"id":"pmh:oai:library.tue.nl:839857","is_oa":false,"landing_page_url":"http://repository.tue.nl/839857","pdf_url":null,"source":{"id":"https://openalex.org/S4406923046","display_name":"TU/e Research Portal (Eindhoven University of Technology)","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":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},{"id":"pmh:oai:library.tue.nl:889205","is_oa":false,"landing_page_url":"http://repository.tue.nl/889205","pdf_url":null,"source":{"id":"https://openalex.org/S4406923046","display_name":"TU/e Research Portal (Eindhoven University of Technology)","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":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},{"id":"pmh:oai:pure.rug.nl:openaire_cris_publications/92770ca3-8ba9-4560-a2ef-5b9b14f439ac","is_oa":true,"landing_page_url":"https://hdl.handle.net/11370/92770ca3-8ba9-4560-a2ef-5b9b14f439ac","pdf_url":null,"source":{"id":"https://openalex.org/S4306400420","display_name":"University of Groningen research database (University of Groningen / Centre for Information Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I169381384","host_organization_name":"University of Groningen","host_organization_lineage":["https://openalex.org/I169381384"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Wiering, M, Withagen, M & Drugan, M 2014, Model-Based Multi-Objective Reinforcement Learning. in IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning. IEEE (The Institute of Electrical and Electronics Engineers), Orlando.","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:vubissmart:VUBISSMART:2000:240664","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306402573","display_name":"VUBIR (Vrije Universiteit Brussel)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I13469542","host_organization_name":"Vrije Universiteit Brussel","host_organization_lineage":["https://openalex.org/I13469542"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},{"id":"pmh:oai:vubissmart:VUBISSMART:2000:90725","is_oa":false,"landing_page_url":"https://biblio.vub.ac.be/vubir/modelbased-multiobjective-reinforcement-learning(80d5c979-80db-4e9d-8b63-4e8456f437ee).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306402573","display_name":"VUBIR (Vrije Universiteit Brussel)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I13469542","host_organization_name":"Vrije Universiteit Brussel","host_organization_lineage":["https://openalex.org/I13469542"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:pure.rug.nl:publications/92770ca3-8ba9-4560-a2ef-5b9b14f439ac","is_oa":true,"landing_page_url":"https://research.rug.nl/en/publications/92770ca3-8ba9-4560-a2ef-5b9b14f439ac","pdf_url":"https://pure.rug.nl/ws/files/15836113/Artikel_v2.pdf","source":{"id":"https://openalex.org/S4306400420","display_name":"University of Groningen research database (University of Groningen / Centre for Information Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I169381384","host_organization_name":"University of Groningen","host_organization_lineage":["https://openalex.org/I169381384"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Wiering, M, Withagen, M & Drugan, M 2014, Model-Based Multi-Objective Reinforcement Learning. in IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning. IEEE (The Institute of Electrical and Electronics Engineers), Orlando.","raw_type":"info:eu-repo/semantics/publishedVersion"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2123516968.pdf","grobid_xml":"https://content.openalex.org/works/W2123516968.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W288089086","https://openalex.org/W291243768","https://openalex.org/W641771830","https://openalex.org/W1963665823","https://openalex.org/W1974819972","https://openalex.org/W2012612381","https://openalex.org/W2040376780","https://openalex.org/W2048226872","https://openalex.org/W2060846151","https://openalex.org/W2071279638","https://openalex.org/W2095602422","https://openalex.org/W2098907614","https://openalex.org/W2101786389","https://openalex.org/W2102660061","https://openalex.org/W2117428849","https://openalex.org/W2121863487","https://openalex.org/W2136719210","https://openalex.org/W2152213878","https://openalex.org/W2341171179","https://openalex.org/W2914656440","https://openalex.org/W3011120880","https://openalex.org/W3103262232","https://openalex.org/W4214717370","https://openalex.org/W4245108548","https://openalex.org/W6677435986","https://openalex.org/W6680384362","https://openalex.org/W6775686901"],"related_works":["https://openalex.org/W2073298047","https://openalex.org/W1963790170","https://openalex.org/W2090178682","https://openalex.org/W2586328217","https://openalex.org/W2033790662","https://openalex.org/W2049264236","https://openalex.org/W4241467429","https://openalex.org/W2001591765","https://openalex.org/W2073147994","https://openalex.org/W317165722"],"abstract_inverted_index":{"This":[0],"paper":[1,100],"describes":[2],"a":[3,14,31,94,120],"novel":[4],"multi-objective":[5,18,32,46],"reinforcement":[6,47],"learning":[7,48],"algorithm.":[8],"The":[9,41,125],"proposed":[10],"algorithm":[11],"first":[12],"learns":[13],"model":[15,27,55],"of":[16,43,62,123],"the":[17,60,68,83,86,104,133,147],"sequential":[19],"decision":[20],"making":[21],"problem,":[22],"after":[23],"which":[24],"this":[25,44,99],"learned":[26],"is":[28,50,80,137],"used":[29],"by":[30,92],"dynamic":[33,69],"programming":[34,70],"method":[35,49,71,131],"to":[36,139],"compute":[37,73],"Pareto":[38,75,143],"optimal":[39,76,144],"policies.":[40,77],"advantage":[42],"model-based":[45],"that":[51,82,129],"once":[52],"an":[53,63,89],"accurate":[54,117],"has":[56],"been":[57],"estimated":[58],"from":[59],"experiences":[61],"agent":[64,84,105],"in":[65,88,115],"some":[66],"environment,":[67],"will":[72],"all":[74,142],"Therefore":[78],"it":[79],"important":[81],"explores":[85],"environment":[87],"intelligent":[90],"way":[91],"using":[93],"good":[95],"exploration":[96,109,135],"strategy.":[97],"In":[98],"we":[101],"have":[102],"supplied":[103],"with":[106,132],"two":[107],"different":[108],"strategies":[110],"and":[111],"compare":[112],"their":[113],"effectiveness":[114],"estimating":[116],"models":[118],"within":[119],"reasonable":[121],"amount":[122],"time.":[124],"experimental":[126],"results":[127],"show":[128],"our":[130],"best":[134],"strategy":[136],"able":[138],"quickly":[140],"learn":[141],"policies":[145],"for":[146],"Deep":[148],"Sea":[149],"Treasure":[150],"problem.":[151]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":3}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}