{"id":"https://openalex.org/W2953335040","doi":"https://doi.org/10.24963/ijcai.2019/320","title":"Curriculum Learning for Cumulative Return Maximization","display_name":"Curriculum Learning for Cumulative Return Maximization","publication_year":2019,"publication_date":"2019-07-28","ids":{"openalex":"https://openalex.org/W2953335040","doi":"https://doi.org/10.24963/ijcai.2019/320","mag":"2953335040"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2019/320","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/320","pdf_url":"https://www.ijcai.org/proceedings/2019/0320.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2019/0320.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5061715907","display_name":"Francesco Foglino","orcid":null},"institutions":[{"id":"https://openalex.org/I130828816","display_name":"University of Leeds","ror":"https://ror.org/024mrxd33","country_code":"GB","type":"education","lineage":["https://openalex.org/I130828816"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Francesco Foglino","raw_affiliation_strings":["University of Leeds, United Kingdom","University of Leeds"],"affiliations":[{"raw_affiliation_string":"University of Leeds, United Kingdom","institution_ids":["https://openalex.org/I130828816"]},{"raw_affiliation_string":"University of Leeds","institution_ids":["https://openalex.org/I130828816"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020854938","display_name":"Christiano Coletto Christakou","orcid":null},"institutions":[{"id":"https://openalex.org/I130828816","display_name":"University of Leeds","ror":"https://ror.org/024mrxd33","country_code":"GB","type":"education","lineage":["https://openalex.org/I130828816"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Christiano Coletto Christakou","raw_affiliation_strings":["University of Leeds, United Kingdom","University of Leeds"],"affiliations":[{"raw_affiliation_string":"University of Leeds, United Kingdom","institution_ids":["https://openalex.org/I130828816"]},{"raw_affiliation_string":"University of Leeds","institution_ids":["https://openalex.org/I130828816"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002515819","display_name":"Ricardo Luna Guti\u00e9rrez","orcid":"https://orcid.org/0000-0001-9915-0989"},"institutions":[{"id":"https://openalex.org/I130828816","display_name":"University of Leeds","ror":"https://ror.org/024mrxd33","country_code":"GB","type":"education","lineage":["https://openalex.org/I130828816"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ricardo Luna Gutierrez","raw_affiliation_strings":["University of Leeds, United Kingdom","University of Leeds"],"affiliations":[{"raw_affiliation_string":"University of Leeds, United Kingdom","institution_ids":["https://openalex.org/I130828816"]},{"raw_affiliation_string":"University of Leeds","institution_ids":["https://openalex.org/I130828816"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058021734","display_name":"Matteo Leonetti","orcid":"https://orcid.org/0000-0002-3831-2400"},"institutions":[{"id":"https://openalex.org/I130828816","display_name":"University of Leeds","ror":"https://ror.org/024mrxd33","country_code":"GB","type":"education","lineage":["https://openalex.org/I130828816"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Matteo Leonetti","raw_affiliation_strings":["University of Leeds, United Kingdom","University of Leeds"],"affiliations":[{"raw_affiliation_string":"University of Leeds, United Kingdom","institution_ids":["https://openalex.org/I130828816"]},{"raw_affiliation_string":"University of Leeds","institution_ids":["https://openalex.org/I130828816"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5061715907"],"corresponding_institution_ids":["https://openalex.org/I130828816"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.06110579,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2308","last_page":"2314"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994000196456909,"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":0.9994000196456909,"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/T10551","display_name":"Scheduling and Optimization Algorithms","score":0.991100013256073,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing 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/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.9785000085830688,"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/computer-science","display_name":"Computer science","score":0.742887020111084},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7330427765846252},{"id":"https://openalex.org/keywords/maximization","display_name":"Maximization","score":0.6661801934242249},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5737558603286743},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5447394251823425},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5313758254051208},{"id":"https://openalex.org/keywords/curriculum","display_name":"Curriculum","score":0.5204484462738037},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.5150575637817383},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4219065010547638},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4201611280441284},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0898294746875763},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08031162619590759}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.742887020111084},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7330427765846252},{"id":"https://openalex.org/C2776330181","wikidata":"https://www.wikidata.org/wiki/Q18358244","display_name":"Maximization","level":2,"score":0.6661801934242249},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5737558603286743},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5447394251823425},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5313758254051208},{"id":"https://openalex.org/C47177190","wikidata":"https://www.wikidata.org/wiki/Q207137","display_name":"Curriculum","level":2,"score":0.5204484462738037},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.5150575637817383},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4219065010547638},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4201611280441284},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0898294746875763},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08031162619590759},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.24963/ijcai.2019/320","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/320","pdf_url":"https://www.ijcai.org/proceedings/2019/0320.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.whiterose.ac.uk:147036","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306400854","display_name":"White Rose Research Online (University of Leeds, The University of Sheffield, University of York)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2800616092","host_organization_name":"White Rose University Consortium","host_organization_lineage":["https://openalex.org/I2800616092"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Proceedings Paper"},{"id":"pmh:oai:arXiv.org:1906.06178","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1906.06178","pdf_url":"https://arxiv.org/pdf/1906.06178","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:2953335040","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1906.06178.pdf","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.1906.06178","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1906.06178","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":"article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2019/320","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/320","pdf_url":"https://www.ijcai.org/proceedings/2019/0320.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.5299999713897705,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[{"id":"https://openalex.org/G4748445076","display_name":"COMMOTIONS: Computational Models of Traffic Interactions for Testing of Automated Vehicles","funder_award_id":"EP/S005056/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G5671623886","display_name":"Humanlike physics understanding for autonomous robots","funder_award_id":"EP/R031193/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G8695752716","display_name":null,"funder_award_id":"EP/R031193/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320320298","display_name":"University of Leeds","ror":"https://ror.org/024mrxd33"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2953335040.pdf","grobid_xml":"https://content.openalex.org/works/W2953335040.grobid-xml"},"referenced_works_count":17,"referenced_works":["https://openalex.org/W158722652","https://openalex.org/W1519626139","https://openalex.org/W2097381042","https://openalex.org/W2104670598","https://openalex.org/W2169743339","https://openalex.org/W2426267443","https://openalex.org/W2476301537","https://openalex.org/W2581240229","https://openalex.org/W2736601468","https://openalex.org/W2751516180","https://openalex.org/W2808418309","https://openalex.org/W2886885155","https://openalex.org/W2963293881","https://openalex.org/W2963577640","https://openalex.org/W2963890729","https://openalex.org/W2964118020","https://openalex.org/W2978129546"],"related_works":["https://openalex.org/W2056107474","https://openalex.org/W3133227558","https://openalex.org/W3104364497","https://openalex.org/W2910911697","https://openalex.org/W3160027457","https://openalex.org/W2042357378","https://openalex.org/W3036821294","https://openalex.org/W2970199615","https://openalex.org/W3113238341","https://openalex.org/W3108562470","https://openalex.org/W1812824539","https://openalex.org/W2392808011","https://openalex.org/W2112422203","https://openalex.org/W3132255199","https://openalex.org/W3037828233","https://openalex.org/W2963179943","https://openalex.org/W3203637758","https://openalex.org/W2945732847","https://openalex.org/W2289410116","https://openalex.org/W208428353"],"abstract_inverted_index":{"Curriculum":[0],"learning":[1,8,12,66],"has":[2],"been":[3],"successfully":[4],"used":[5],"in":[6,24],"reinforcement":[7],"to":[9,40,102],"accelerate":[10],"the":[11,52,57,61,65,70,73,119],"process,":[13],"through":[14,43],"knowledge":[15],"transfer":[16],"between":[17],"tasks":[18],"of":[19,121],"increasing":[20],"complexity.":[21],"Critical":[22],"tasks,":[23],"which":[25],"suboptimal":[26,93],"exploratory":[27],"actions":[28],"must":[29],"be":[30],"minimized,":[31],"can":[32],"benefit":[33],"from":[34],"curriculum":[35],"learning,":[36],"and":[37,110],"its":[38],"ability":[39],"shape":[41],"exploration":[42],"transfer.":[44],"We":[45,95],"propose":[46],"a":[47,131,135,139],"task":[48,99],"sequencing":[49,100],"algorithm":[50,101,129],"maximizing":[51,69],"cumulative":[53,71,122],"return,":[54,72],"that":[55,112],"is,":[56],"return":[58,123],"obtained":[59],"by":[60],"agent":[62,74],"across":[63],"all":[64],"episodes.":[67],"By":[68],"not":[75],"only":[76],"aims":[77],"at":[78,88],"achieving":[79],"high":[80],"rewards":[81],"as":[82,84],"fast":[83],"possible,":[85],"but":[86],"also":[87],"doing":[89],"so":[90],"while":[91],"limiting":[92],"actions.":[94],"experimentally":[96],"compare":[97],"our":[98,128],"several":[103],"popular":[104],"metaheuristic":[105],"algorithms":[106],"for":[107,138],"combinatorial":[108],"optimization,":[109],"show":[111],"it":[113],"achieves":[114],"significantly":[115],"better":[116],"performance":[117],"on":[118,130],"problem":[120],"maximization.":[124],"Furthermore,":[125],"we":[126],"validate":[127],"critical":[132],"task,":[133],"optimizing":[134],"home":[136],"controller":[137],"micro":[140],"energy":[141],"grid.":[142]},"counts_by_year":[],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}