{"id":"https://openalex.org/W2045276965","doi":"https://doi.org/10.1109/ijcnn.2012.6252759","title":"Tree-based Fitted Q-iteration for Multi-Objective Markov Decision problems","display_name":"Tree-based Fitted Q-iteration for Multi-Objective Markov Decision problems","publication_year":2012,"publication_date":"2012-06-01","ids":{"openalex":"https://openalex.org/W2045276965","doi":"https://doi.org/10.1109/ijcnn.2012.6252759","mag":"2045276965"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn.2012.6252759","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2012.6252759","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 2012 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/11311/690408","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5088803594","display_name":"Andrea Castelletti","orcid":"https://orcid.org/0000-0002-7923-1498"},"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":"Andrea Castelletti","raw_affiliation_strings":["Politecnico di Milano, Politecnico di Milano, Milan, Italy","Dept. of Electronics and Information, Politecnico di Milano, Piazza Leonardo da Vinci, 32.- 20133 Milan, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Politecnico di Milano, Politecnico di Milano, Milan, Italy","institution_ids":["https://openalex.org/I93860229"]},{"raw_affiliation_string":"Dept. of Electronics and Information, Politecnico di Milano, Piazza Leonardo da Vinci, 32.- 20133 Milan, Italy","institution_ids":["https://openalex.org/I93860229"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054556825","display_name":"Francesca Pianosi","orcid":"https://orcid.org/0000-0002-1516-2163"},"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":"Francesca Pianosi","raw_affiliation_strings":["Politecnico di Milano, Politecnico di Milano, Milan, Italy","Dept. of Electronics and Information, Politecnico di Milano, Piazza Leonardo da Vinci, 32.- 20133 Milan, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Politecnico di Milano, Politecnico di Milano, Milan, Italy","institution_ids":["https://openalex.org/I93860229"]},{"raw_affiliation_string":"Dept. of Electronics and Information, Politecnico di Milano, Piazza Leonardo da Vinci, 32.- 20133 Milan, Italy","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"},"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":"Marcello Restelli","raw_affiliation_strings":["Politecnico di Milano, Politecnico di Milano, Milan, Italy","Dept. of Electronics and Information, Politecnico di Milano, Piazza Leonardo da Vinci, 32.- 20133 Milan, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Politecnico di Milano, Politecnico di Milano, Milan, Italy","institution_ids":["https://openalex.org/I93860229"]},{"raw_affiliation_string":"Dept. of Electronics and Information, Politecnico di Milano, Piazza Leonardo da Vinci, 32.- 20133 Milan, Italy","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":null,"has_fulltext":false,"cited_by_count":34,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10969","display_name":"Water resources management and optimization","score":0.9990000128746033,"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"}},"topics":[{"id":"https://openalex.org/T10969","display_name":"Water resources management and optimization","score":0.9990000128746033,"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"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9952999949455261,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9937999844551086,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7723124027252197},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7071861028671265},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.6054602861404419},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5984576940536499},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.5089929103851318},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.49948596954345703},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.49831271171569824},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.45981723070144653},{"id":"https://openalex.org/keywords/extension","display_name":"Extension (predicate logic)","score":0.44054824113845825},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4354023337364197},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.4295025169849396},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4119589328765869},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.3644534647464752},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2912932336330414},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.28938108682632446}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7723124027252197},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7071861028671265},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.6054602861404419},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5984576940536499},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.5089929103851318},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.49948596954345703},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.49831271171569824},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.45981723070144653},{"id":"https://openalex.org/C2778029271","wikidata":"https://www.wikidata.org/wiki/Q5421931","display_name":"Extension (predicate logic)","level":2,"score":0.44054824113845825},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4354023337364197},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.4295025169849396},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4119589328765869},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.3644534647464752},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2912932336330414},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.28938108682632446},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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},{"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/ijcnn.2012.6252759","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2012.6252759","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 2012 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},{"id":"pmh:oai:re.public.polimi.it:11311/690408","is_oa":true,"landing_page_url":"http://hdl.handle.net/11311/690408","pdf_url":"http://hdl.handle.net/11311/690408","source":{"id":"https://openalex.org/S4306400312","display_name":"Virtual Community of Pathological Anatomy (University of Castilla La Mancha)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79189158","host_organization_name":"University of Castilla-La Mancha","host_organization_lineage":["https://openalex.org/I79189158"],"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":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:re.public.polimi.it:11311/690408","is_oa":true,"landing_page_url":"http://hdl.handle.net/11311/690408","pdf_url":"http://hdl.handle.net/11311/690408","source":{"id":"https://openalex.org/S4306400312","display_name":"Virtual Community of Pathological Anatomy (University of Castilla La Mancha)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79189158","host_organization_name":"University of Castilla-La Mancha","host_organization_lineage":["https://openalex.org/I79189158"],"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":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.47999998927116394}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2045276965.pdf"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W291243768","https://openalex.org/W1482041209","https://openalex.org/W1491322982","https://openalex.org/W1506832649","https://openalex.org/W1508786153","https://openalex.org/W1601081659","https://openalex.org/W1660131149","https://openalex.org/W1834963927","https://openalex.org/W1998649829","https://openalex.org/W2012612381","https://openalex.org/W2056132907","https://openalex.org/W2103324900","https://openalex.org/W2117355432","https://openalex.org/W2117428849","https://openalex.org/W2117626647","https://openalex.org/W2120346334","https://openalex.org/W2141481921","https://openalex.org/W2487144912","https://openalex.org/W2913340405","https://openalex.org/W2914746235","https://openalex.org/W4254767886","https://openalex.org/W6610454638","https://openalex.org/W6628934745","https://openalex.org/W6677477198","https://openalex.org/W6677549092","https://openalex.org/W6677737365"],"related_works":["https://openalex.org/W2152670157","https://openalex.org/W2101748387","https://openalex.org/W4308702637","https://openalex.org/W2386410636","https://openalex.org/W176737593","https://openalex.org/W2808418668","https://openalex.org/W2156021013","https://openalex.org/W3105579180","https://openalex.org/W2807018115","https://openalex.org/W1574958246"],"abstract_inverted_index":{"This":[0],"paper":[1,72],"is":[2,44,73,111,122,138],"about":[3],"solving":[4],"multi-objective":[5,108,146],"control":[6,30,49,85],"problems":[7,50],"using":[8,63],"a":[9,33,100,153],"model-free":[10],"batch-mode":[11],"reinforcement-learning":[12,22],"approach.":[13],"Although":[14],"many":[15,47],"real-world":[16,143],"applications":[17],"have":[18],"several":[19],"conflicting":[20],"objectives,":[21,40],"(RL)":[23],"literature":[24],"has":[25],"mainly":[26],"focused":[27],"on":[28,140],"single-objective":[29,48,125],"problems.":[31],"As":[32],"consequence,":[34],"in":[35,70,99],"the":[36,41,56,84,89,97,114,118,128,133,149],"presence":[37],"of":[38,55,76,92,107,117,152],"multiple":[39],"usual":[42],"approach":[43,137],"to":[45,82,96,112,132],"consider":[46],"(resulting":[51],"from":[52],"different":[53],"combinations":[54,91],"original":[57],"problem":[58],"objectives),":[59],"each":[60],"one":[61],"solved":[62],"standard":[64],"RL":[65,147],"techniques.":[66],"The":[67,104,136],"algorithm":[68],"proposed":[69],"this":[71],"an":[74,141],"extension":[75],"Fitted":[77],"Q-iteration":[78],"(FQI)":[79],"that":[80],"enables":[81],"learn":[83],"policies":[86],"for":[87,145],"all":[88],"linear":[90],"preferences":[93],"(weights)":[94],"assigned":[95],"objectives":[98],"single":[101],"training":[102],"process.":[103],"key":[105],"idea":[106],"FQI":[109,126],"(MOFQI)":[110],"enlarge":[113],"continuous":[115],"approximation":[116],"action-value":[119],"function,":[120],"which":[121],"performed":[123],"by":[124],"over":[127],"state-action":[129],"space,":[130],"also":[131],"weight":[134],"space.":[135],"demonstrated":[139],"interesting":[142],"application":[144],"algorithms:":[148],"optimal":[150],"operation":[151],"multi-purpose":[154],"water":[155],"reservoir.":[156]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":4},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}