{"id":"https://openalex.org/W158722652","doi":"https://doi.org/10.1007/978-3-642-27645-3_5","title":"Transfer in Reinforcement Learning: A Framework and a Survey","display_name":"Transfer in Reinforcement Learning: A Framework and a Survey","publication_year":2012,"publication_date":"2012-01-01","ids":{"openalex":"https://openalex.org/W158722652","doi":"https://doi.org/10.1007/978-3-642-27645-3_5","mag":"158722652"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-642-27645-3_5","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-642-27645-3_5","pdf_url":null,"source":{"id":"https://openalex.org/S4210169857","display_name":"Adaptation, learning, and optimization","issn_l":"1867-4534","issn":["1867-4534","1867-4542"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Adaptation, Learning, and Optimization","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://inria.hal.science/hal-00772626","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5014791481","display_name":"Alessandro Lazaric","orcid":"https://orcid.org/0000-0002-8970-413X"},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en informatique et en automatique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I4210138412","display_name":"Centre de recherche Inria Lille - Nord Europe","ror":"https://ror.org/04eej9726","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1326498283","https://openalex.org/I4210138412"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Alessandro Lazaric","raw_affiliation_strings":["INRIA Lille-Nord Europe, Villeneuve d\u2019Ascq, France","Inria, Lille-Nord Europe"],"affiliations":[{"raw_affiliation_string":"INRIA Lille-Nord Europe, Villeneuve d\u2019Ascq, France","institution_ids":["https://openalex.org/I4210138412","https://openalex.org/I1326498283"]},{"raw_affiliation_string":"Inria, Lille-Nord Europe","institution_ids":["https://openalex.org/I1326498283"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5014791481"],"corresponding_institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I4210138412"],"apc_list":null,"apc_paid":null,"fwci":6.6531,"has_fulltext":false,"cited_by_count":261,"citation_normalized_percentile":{"value":0.97191302,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"143","last_page":"173"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.7641000151634216,"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":0.7641000151634216,"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":0.03880000114440918,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.03709999844431877,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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":0.8613007664680481},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.7506489753723145},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7473701238632202},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7255859375},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5482103228569031},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5276371836662292},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.508904218673706},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.485679030418396},{"id":"https://openalex.org/keywords/knowledge-transfer","display_name":"Knowledge transfer","score":0.48214051127433777},{"id":"https://openalex.org/keywords/negative-transfer","display_name":"Negative transfer","score":0.4804529547691345},{"id":"https://openalex.org/keywords/transfer","display_name":"Transfer (computing)","score":0.4478342831134796},{"id":"https://openalex.org/keywords/knowledge-management","display_name":"Knowledge management","score":0.16246342658996582},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.07813379168510437},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07472315430641174}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8613007664680481},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.7506489753723145},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7473701238632202},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7255859375},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5482103228569031},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5276371836662292},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.508904218673706},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.485679030418396},{"id":"https://openalex.org/C2776960227","wikidata":"https://www.wikidata.org/wiki/Q2586354","display_name":"Knowledge transfer","level":2,"score":0.48214051127433777},{"id":"https://openalex.org/C2779178101","wikidata":"https://www.wikidata.org/wiki/Q6987274","display_name":"Negative transfer","level":3,"score":0.4804529547691345},{"id":"https://openalex.org/C2776175482","wikidata":"https://www.wikidata.org/wiki/Q1195816","display_name":"Transfer (computing)","level":2,"score":0.4478342831134796},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.16246342658996582},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.07813379168510437},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07472315430641174},{"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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},{"id":"https://openalex.org/C171041071","wikidata":"https://www.wikidata.org/wiki/Q36870","display_name":"First language","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1007/978-3-642-27645-3_5","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-642-27645-3_5","pdf_url":null,"source":{"id":"https://openalex.org/S4210169857","display_name":"Adaptation, learning, and optimization","issn_l":"1867-4534","issn":["1867-4534","1867-4542"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Adaptation, Learning, and Optimization","raw_type":"book-chapter"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.372.6691","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.372.6691","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://hal.inria.fr/docs/00/77/26/26/PDF/transfer.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.699.6628","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.699.6628","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://researchers.lille.inria.fr/%7Elazaric/Webpage/Publications_files/lazaric2011transfer.pdf","raw_type":"text"},{"id":"pmh:oai:HAL:hal-00772626v1","is_oa":true,"landing_page_url":"https://inria.hal.science/hal-00772626","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"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":"Marco Wiering, Martijn van Otterlo. Reinforcement Learning - State of the art, 12, Springer, pp.143-173, 2012, ⟨10.1007/978-3-642-27645-3_5⟩","raw_type":"Book sections"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-00772626v1","is_oa":true,"landing_page_url":"https://inria.hal.science/hal-00772626","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"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":"Marco Wiering, Martijn van Otterlo. Reinforcement Learning - State of the art, 12, Springer, pp.143-173, 2012, ⟨10.1007/978-3-642-27645-3_5⟩","raw_type":"Book sections"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":76,"referenced_works":["https://openalex.org/W36691172","https://openalex.org/W203338875","https://openalex.org/W604872191","https://openalex.org/W621727291","https://openalex.org/W1487385582","https://openalex.org/W1488771041","https://openalex.org/W1492014007","https://openalex.org/W1506146479","https://openalex.org/W1510402218","https://openalex.org/W1536990779","https://openalex.org/W1557517019","https://openalex.org/W1570963478","https://openalex.org/W1573527757","https://openalex.org/W1598748993","https://openalex.org/W1600175013","https://openalex.org/W1601389419","https://openalex.org/W1607318605","https://openalex.org/W1612195517","https://openalex.org/W1662803991","https://openalex.org/W1799762961","https://openalex.org/W1822705290","https://openalex.org/W1850488217","https://openalex.org/W1977966786","https://openalex.org/W1993277309","https://openalex.org/W1994925058","https://openalex.org/W2004030284","https://openalex.org/W2014512216","https://openalex.org/W2015858749","https://openalex.org/W2040852548","https://openalex.org/W2065180801","https://openalex.org/W2079247031","https://openalex.org/W2090170171","https://openalex.org/W2097381042","https://openalex.org/W2104641222","https://openalex.org/W2104753538","https://openalex.org/W2106953752","https://openalex.org/W2109910161","https://openalex.org/W2110292307","https://openalex.org/W2114235770","https://openalex.org/W2114537044","https://openalex.org/W2117355432","https://openalex.org/W2120346334","https://openalex.org/W2121863487","https://openalex.org/W2124144580","https://openalex.org/W2126565096","https://openalex.org/W2128195326","https://openalex.org/W2128905965","https://openalex.org/W2132057084","https://openalex.org/W2133040789","https://openalex.org/W2134197408","https://openalex.org/W2138497321","https://openalex.org/W2139612737","https://openalex.org/W2143435603","https://openalex.org/W2145983895","https://openalex.org/W2148440006","https://openalex.org/W2153353285","https://openalex.org/W2154328025","https://openalex.org/W2156974606","https://openalex.org/W2158150115","https://openalex.org/W2158738729","https://openalex.org/W2161795906","https://openalex.org/W2162888803","https://openalex.org/W2163712217","https://openalex.org/W2165698076","https://openalex.org/W2165792602","https://openalex.org/W2169743339","https://openalex.org/W2169924623","https://openalex.org/W2306711933","https://openalex.org/W2411466998","https://openalex.org/W2501216414","https://openalex.org/W2548786235","https://openalex.org/W2568646110","https://openalex.org/W3103256699","https://openalex.org/W3104240813","https://openalex.org/W3140748625","https://openalex.org/W4214717370"],"related_works":["https://openalex.org/W4362501864","https://openalex.org/W4306904969","https://openalex.org/W2392266266","https://openalex.org/W2373702962","https://openalex.org/W1997778821","https://openalex.org/W2619137770","https://openalex.org/W2548360214","https://openalex.org/W2952841984","https://openalex.org/W2398668521","https://openalex.org/W2076338401"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":14},{"year":2023,"cited_by_count":21},{"year":2022,"cited_by_count":27},{"year":2021,"cited_by_count":44},{"year":2020,"cited_by_count":53},{"year":2019,"cited_by_count":24},{"year":2018,"cited_by_count":16},{"year":2017,"cited_by_count":16},{"year":2016,"cited_by_count":12},{"year":2015,"cited_by_count":13},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}