{"id":"https://openalex.org/W2899658755","doi":"https://doi.org/10.1109/iros40897.2019.8968092","title":"Meta-Learning for Multi-objective Reinforcement Learning","display_name":"Meta-Learning for Multi-objective Reinforcement Learning","publication_year":2019,"publication_date":"2019-11-01","ids":{"openalex":"https://openalex.org/W2899658755","doi":"https://doi.org/10.1109/iros40897.2019.8968092","mag":"2899658755"},"language":"en","primary_location":{"id":"doi:10.1109/iros40897.2019.8968092","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros40897.2019.8968092","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1811.03376","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100329867","display_name":"Xi Chen","orcid":"https://orcid.org/0000-0001-7965-9198"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Xi Chen","raw_affiliation_strings":["RPL, KTH Royal Institute of Technology,Sweden","Royal Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RPL, KTH Royal Institute of Technology,Sweden","institution_ids":["https://openalex.org/I86987016"]},{"raw_affiliation_string":"Royal Institute of Technology","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038342432","display_name":"Ali Ghadirzadeh","orcid":null},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Ali Ghadirzadeh","raw_affiliation_strings":["RPL, KTH Royal Institute of Technology,Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RPL, KTH Royal Institute of Technology,Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082269387","display_name":"M\u00e5rten Bj\u00f6rkman","orcid":null},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"M\u00e5rten Bj\u00f6rkman","raw_affiliation_strings":["RPL, KTH Royal Institute of Technology,Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RPL, KTH Royal Institute of Technology,Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028082686","display_name":"Patric Jensfelt","orcid":"https://orcid.org/0000-0002-1170-7162"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Patric Jensfelt","raw_affiliation_strings":["RPL, KTH Royal Institute of Technology,Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RPL, KTH Royal Institute of Technology,Sweden","institution_ids":["https://openalex.org/I86987016"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I86987016"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"977","last_page":"983"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9961000084877014,"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/T11954","display_name":"Energy Efficiency and Management","score":0.9776999950408936,"subfield":{"id":"https://openalex.org/subfields/2105","display_name":"Renewable Energy, Sustainability and the Environment"},"field":{"id":"https://openalex.org/fields/21","display_name":"Energy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8890209197998047},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.7537062168121338},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6600966453552246},{"id":"https://openalex.org/keywords/pareto-principle","display_name":"Pareto principle","score":0.6385080218315125},{"id":"https://openalex.org/keywords/pareto-optimal","display_name":"Pareto optimal","score":0.6158579587936401},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5583145022392273},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5567307472229004},{"id":"https://openalex.org/keywords/preference","display_name":"Preference","score":0.4894353449344635},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4528622329235077},{"id":"https://openalex.org/keywords/meta-learning","display_name":"Meta learning (computer science)","score":0.44318172335624695},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4301179051399231},{"id":"https://openalex.org/keywords/degrees-of-freedom","display_name":"Degrees of freedom (physics and chemistry)","score":0.4159350097179413},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.329836368560791},{"id":"https://openalex.org/keywords/multi-objective-optimization","display_name":"Multi-objective optimization","score":0.28940796852111816},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.24348905682563782},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0813460648059845},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.06458926200866699}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8890209197998047},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.7537062168121338},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6600966453552246},{"id":"https://openalex.org/C137635306","wikidata":"https://www.wikidata.org/wiki/Q182667","display_name":"Pareto principle","level":2,"score":0.6385080218315125},{"id":"https://openalex.org/C2986314615","wikidata":"https://www.wikidata.org/wiki/Q36829","display_name":"Pareto optimal","level":3,"score":0.6158579587936401},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5583145022392273},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5567307472229004},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.4894353449344635},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4528622329235077},{"id":"https://openalex.org/C2781002164","wikidata":"https://www.wikidata.org/wiki/Q6822311","display_name":"Meta learning (computer science)","level":3,"score":0.44318172335624695},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4301179051399231},{"id":"https://openalex.org/C208081375","wikidata":"https://www.wikidata.org/wiki/Q274502","display_name":"Degrees of freedom (physics and chemistry)","level":2,"score":0.4159350097179413},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.329836368560791},{"id":"https://openalex.org/C68781425","wikidata":"https://www.wikidata.org/wiki/Q2052203","display_name":"Multi-objective optimization","level":2,"score":0.28940796852111816},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.24348905682563782},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0813460648059845},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.06458926200866699},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/iros40897.2019.8968092","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros40897.2019.8968092","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1811.03376","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1811.03376","pdf_url":"https://arxiv.org/pdf/1811.03376","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:2899658755","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1811.03376","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1811.03376","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1811.03376","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1811.03376","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1811.03376","pdf_url":"https://arxiv.org/pdf/1811.03376","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[{"score":0.8100000023841858,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G8657455129","display_name":null,"funder_award_id":"H2020-FETPROACT-2014","funder_id":"https://openalex.org/F4320332999","funder_display_name":"Horizon 2020 Framework Programme"}],"funders":[{"id":"https://openalex.org/F4320332999","display_name":"Horizon 2020 Framework Programme","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2899658755.pdf","grobid_xml":"https://content.openalex.org/works/W2899658755.grobid-xml"},"referenced_works_count":43,"referenced_works":["https://openalex.org/W288089086","https://openalex.org/W291243768","https://openalex.org/W1553373771","https://openalex.org/W1585939719","https://openalex.org/W1603565681","https://openalex.org/W1771410628","https://openalex.org/W1968535060","https://openalex.org/W1987725948","https://openalex.org/W1988210060","https://openalex.org/W1998649829","https://openalex.org/W2012612381","https://openalex.org/W2044986207","https://openalex.org/W2058192020","https://openalex.org/W2060846151","https://openalex.org/W2090218528","https://openalex.org/W2102660061","https://openalex.org/W2126105956","https://openalex.org/W2147995533","https://openalex.org/W2186820913","https://openalex.org/W2278712528","https://openalex.org/W2592538810","https://openalex.org/W2604763608","https://openalex.org/W2625286567","https://openalex.org/W2625456521","https://openalex.org/W2733961795","https://openalex.org/W2736601468","https://openalex.org/W2788781499","https://openalex.org/W2789008106","https://openalex.org/W2949608212","https://openalex.org/W2963641140","https://openalex.org/W2964001908","https://openalex.org/W3103262232","https://openalex.org/W6610454638","https://openalex.org/W6635097213","https://openalex.org/W6638018090","https://openalex.org/W6684212943","https://openalex.org/W6694904549","https://openalex.org/W6704571135","https://openalex.org/W6736057607","https://openalex.org/W6740801417","https://openalex.org/W6741002519","https://openalex.org/W6748523217","https://openalex.org/W6748599296"],"related_works":["https://openalex.org/W3004325772","https://openalex.org/W3187584516","https://openalex.org/W3109669325","https://openalex.org/W2792838926","https://openalex.org/W2575990004","https://openalex.org/W2961186683","https://openalex.org/W2151889438","https://openalex.org/W2990239702","https://openalex.org/W3130192094","https://openalex.org/W2530195778","https://openalex.org/W2156578004","https://openalex.org/W3167797283","https://openalex.org/W3170197122","https://openalex.org/W2154023516","https://openalex.org/W2386496952","https://openalex.org/W2101307636","https://openalex.org/W1556201700","https://openalex.org/W72400652","https://openalex.org/W2146957157","https://openalex.org/W3160027457"],"abstract_inverted_index":{"Multi-objective":[0],"reinforcement":[1,9],"learning":[2,10],"(MORL)":[3],"is":[4,31,99],"the":[5,39,57,97,106,114,128,136,139],"generalization":[6],"of":[7,21,46,56,87,127,134,154,161],"standard":[8],"(RL)":[11],"approaches":[12],"to":[13,49],"solve":[14],"sequential":[15],"decision":[16,91],"making":[17],"problems":[18,157],"that":[19,118],"consist":[20],"several,":[22],"possibly":[23],"conflicting,":[24],"objectives.":[25,58],"Generally,":[26],"in":[27,123,132],"such":[28,119],"formulations,":[29],"there":[30],"no":[32],"single":[33],"optimal":[34,130,149],"policy":[35,73],"which":[36],"optimizes":[37],"all":[38],"objectives":[40],"simultaneously,":[41],"and":[42,138],"instead,":[43],"a":[44,54,64,70,72,81,85,102,111,120,124,152],"number":[45,86,153],"policies":[47,150],"has":[48],"be":[50],"found":[51],"each":[52],"optimizing":[53],"preference":[55],"In":[59,94],"this":[60],"paper,":[61],"we":[62],"introduce":[63],"novel":[65],"MORL":[66,98],"approach":[67],"by":[68,110],"training":[69],"meta-policy,":[71],"simultaneously":[74],"trained":[75],"with":[76,105,158],"multiple":[77],"tasks":[78],"sampled":[79,89],"from":[80],"task":[82,107],"distribution,":[83],"for":[84],"randomly":[88],"Markov":[90],"processes":[92],"(MDPs).":[93],"other":[95],"words,":[96],"framed":[100],"as":[101],"meta-learning":[103],"problem,":[104],"distribution":[108,112],"given":[109],"over":[113],"preferences.":[115],"We":[116,142],"demonstrate":[117],"formulation":[121],"results":[122],"better":[125],"approximation":[126],"Pareto":[129,148],"solutions":[131],"terms":[133],"both":[135],"optimality":[137],"computational":[140],"efficiency.":[141],"evaluated":[143],"our":[144],"method":[145],"on":[146],"obtaining":[147],"using":[151],"continuous":[155],"control":[156],"high":[159],"degrees":[160],"freedom.":[162]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}