{"id":"https://openalex.org/W1582256513","doi":"https://doi.org/10.1109/ijcnn.2005.1555955","title":"Task similarity measures for transfer in reinforcement learning task libraries","display_name":"Task similarity measures for transfer in reinforcement learning task libraries","publication_year":2006,"publication_date":"2006-01-05","ids":{"openalex":"https://openalex.org/W1582256513","doi":"https://doi.org/10.1109/ijcnn.2005.1555955","mag":"1582256513"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn.2005.1555955","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2005.1555955","pdf_url":null,"source":{"id":"https://openalex.org/S4363609022","display_name":"Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005.","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005.","raw_type":"proceedings-article"},"type":"conference-paper","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/A5111897802","display_name":"James L. Carroll","orcid":"https://orcid.org/0000-0002-6152-4911"},"institutions":[{"id":"https://openalex.org/I100005738","display_name":"Brigham Young University","ror":"https://ror.org/047rhhm47","country_code":"US","type":"education","lineage":["https://openalex.org/I100005738"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"J.L. Carroll","raw_affiliation_strings":["Department of Computer Science, Brigham Young University, Provo, UT, USA","[Department of Computer Science, Brigham Young University, Provo, UT, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Brigham Young University, Provo, UT, USA","institution_ids":["https://openalex.org/I100005738"]},{"raw_affiliation_string":"[Department of Computer Science, Brigham Young University, Provo, UT, USA]","institution_ids":["https://openalex.org/I100005738"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029074659","display_name":"Kevin Seppi","orcid":"https://orcid.org/0000-0002-4932-2700"},"institutions":[{"id":"https://openalex.org/I100005738","display_name":"Brigham Young University","ror":"https://ror.org/047rhhm47","country_code":"US","type":"education","lineage":["https://openalex.org/I100005738"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"K. Seppi","raw_affiliation_strings":["Department of Computer Science, Brigham Young University, Provo, UT, USA","[Department of Computer Science, Brigham Young University, Provo, UT, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Brigham Young University, Provo, UT, USA","institution_ids":["https://openalex.org/I100005738"]},{"raw_affiliation_string":"[Department of Computer Science, Brigham Young University, Provo, UT, USA]","institution_ids":["https://openalex.org/I100005738"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I100005738"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":41,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"2","issue":null,"first_page":"803","last_page":"808"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.989799976348877,"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":0.989799976348877,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9850999712944031,"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":0.9656000137329102,"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/task","display_name":"Task (project management)","score":0.7853095531463623},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.7799298763275146},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6804208755493164},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.5940223932266235},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5878474712371826},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.5720808506011963},{"id":"https://openalex.org/keywords/similarity-measure","display_name":"Similarity measure","score":0.5220708250999451},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5161738991737366},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48512372374534607},{"id":"https://openalex.org/keywords/transfer","display_name":"Transfer (computing)","score":0.46910080313682556},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.43195411562919617},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3466480076313019},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.19559046626091003},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.09614795446395874},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.08127179741859436},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.052655190229415894},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.05082395672798157}],"concepts":[{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7853095531463623},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.7799298763275146},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6804208755493164},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.5940223932266235},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5878474712371826},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.5720808506011963},{"id":"https://openalex.org/C2776517306","wikidata":"https://www.wikidata.org/wiki/Q29017317","display_name":"Similarity measure","level":2,"score":0.5220708250999451},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5161738991737366},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48512372374534607},{"id":"https://openalex.org/C2776175482","wikidata":"https://www.wikidata.org/wiki/Q1195816","display_name":"Transfer (computing)","level":2,"score":0.46910080313682556},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.43195411562919617},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3466480076313019},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.19559046626091003},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.09614795446395874},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.08127179741859436},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.052655190229415894},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.05082395672798157},{"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/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/ijcnn.2005.1555955","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2005.1555955","pdf_url":null,"source":{"id":"https://openalex.org/S4363609022","display_name":"Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005.","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005.","raw_type":"proceedings-article"},{"id":"pmh:oai:scholarsarchive.byu.edu:facpub-2006","is_oa":false,"landing_page_url":"https://scholarsarchive.byu.edu/facpub/1007","pdf_url":null,"source":{"id":"https://openalex.org/S4377196308","display_name":"ScholarsArchive  (Brigham Young University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I100005738","host_organization_name":"Brigham Young University","host_organization_lineage":["https://openalex.org/I100005738"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Faculty Publications","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.81.1753","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.81.1753","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://james.jlcarroll.net/publications/similarity3.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W121337034","https://openalex.org/W1499408472","https://openalex.org/W1560550898","https://openalex.org/W1566538838","https://openalex.org/W2114451917","https://openalex.org/W2122451452","https://openalex.org/W2172405120","https://openalex.org/W4254949128","https://openalex.org/W6655340590","https://openalex.org/W6676772908"],"related_works":["https://openalex.org/W2920061524","https://openalex.org/W4310083477","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2089013912","https://openalex.org/W2107890255","https://openalex.org/W2076061571","https://openalex.org/W2106552856","https://openalex.org/W1987513656","https://openalex.org/W2072376847"],"abstract_inverted_index":{"Recent":[0],"research":[1],"in":[2,16,80,118],"task":[3,6,13,20,37,41,57,65,72,88],"transfer":[4,26,73,105],"and":[5,33,84,97,110],"clustering":[7],"has":[8],"necessitated":[9],"the":[10,71,104],"need":[11],"for":[12,24],"similarity":[14,21,42,58,66,79,89],"measures":[15],"reinforcement":[17],"learning.":[18],"Determining":[19],"is":[22,46,60,68],"necessary":[23],"selective":[25],"where":[27],"only":[28],"information":[29],"from":[30],"relevant":[31],"tasks":[32],"portions":[34],"of":[35,82],"a":[36],"are":[38,101],"transferred.":[39],"Which":[40],"measure":[43,59,67],"to":[44],"use":[45],"not":[47],"immediately":[48],"obvious.":[49],"It":[50],"can":[51],"be":[52],"shown":[53],"that":[54],"no":[55],"single":[56],"uniformly":[61],"superior.":[62],"The":[63],"optimal":[64],"dependent":[69],"upon":[70],"method":[74],"being":[75],"employed.":[76],"We":[77,114],"define":[78],"terms":[81],"tasks,":[83],"propose":[85],"several":[86],"possible":[87],"measures,":[90],"d/sub":[91,93,95,98],"T/,":[92],"P/,":[94],"Q/,":[96],"R/":[99],"which":[100],"based":[102],"on":[103],"time,":[106],"policy":[107],"overlap,":[108],"Q-values,":[109],"reward":[111],"structure":[112],"respectively.":[113],"evaluate":[115],"their":[116],"performance":[117],"three":[119],"separate":[120],"experimental":[121],"situations.":[122]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":4},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}