{"id":"https://openalex.org/W2004030284","doi":"https://doi.org/10.1145/1390156.1390225","title":"Transfer of samples in batch reinforcement learning","display_name":"Transfer of samples in batch reinforcement learning","publication_year":2008,"publication_date":"2008-01-01","ids":{"openalex":"https://openalex.org/W2004030284","doi":"https://doi.org/10.1145/1390156.1390225","mag":"2004030284"},"language":"en","primary_location":{"id":"doi:10.1145/1390156.1390225","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1390156.1390225","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th international conference on Machine learning - ICML '08","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/A5014791481","display_name":"Alessandro Lazaric","orcid":"https://orcid.org/0000-0002-8970-413X"},"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":"Alessandro Lazaric","raw_affiliation_strings":["Politecnico di Milano, Milan, Italy","Politecnico di Milano, Milan (Italy)#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Politecnico di Milano, Milan, Italy","institution_ids":["https://openalex.org/I93860229"]},{"raw_affiliation_string":"Politecnico di Milano, Milan (Italy)#TAB#","institution_ids":["https://openalex.org/I93860229"]}]},{"author_position":"middle","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, Milan, Italy","Politecnico di Milano, Milan (Italy)#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Politecnico di Milano, Milan, Italy","institution_ids":["https://openalex.org/I93860229"]},{"raw_affiliation_string":"Politecnico di Milano, Milan (Italy)#TAB#","institution_ids":["https://openalex.org/I93860229"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060263666","display_name":"Andrea Bonarini","orcid":"https://orcid.org/0000-0002-4880-4521"},"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 Bonarini","raw_affiliation_strings":["Politecnico di Milano, Milan, Italy","Politecnico di Milano, Milan (Italy)#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Politecnico di Milano, Milan, Italy","institution_ids":["https://openalex.org/I93860229"]},{"raw_affiliation_string":"Politecnico di Milano, Milan (Italy)#TAB#","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":169,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"544","last_page":"551"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9948999881744385,"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":0.9948999881744385,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9815999865531921,"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/T11663","display_name":"Viral Infectious Diseases and Gene Expression in Insects","score":0.9690999984741211,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8826316595077515},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7931823134422302},{"id":"https://openalex.org/keywords/tuple","display_name":"Tuple","score":0.7507103681564331},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.7403841018676758},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7384000420570374},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.6444436311721802},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5629713535308838},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5479556918144226},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4872931241989136},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4657517075538635},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"Multi-task learning","score":0.4543572664260864},{"id":"https://openalex.org/keywords/sample-complexity","display_name":"Sample complexity","score":0.4493381381034851},{"id":"https://openalex.org/keywords/transfer","display_name":"Transfer (computing)","score":0.42260679602622986},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10147607326507568}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8826316595077515},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7931823134422302},{"id":"https://openalex.org/C118930307","wikidata":"https://www.wikidata.org/wiki/Q600590","display_name":"Tuple","level":2,"score":0.7507103681564331},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.7403841018676758},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7384000420570374},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.6444436311721802},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5629713535308838},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5479556918144226},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4872931241989136},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4657517075538635},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.4543572664260864},{"id":"https://openalex.org/C2778445095","wikidata":"https://www.wikidata.org/wiki/Q18354077","display_name":"Sample complexity","level":2,"score":0.4493381381034851},{"id":"https://openalex.org/C2776175482","wikidata":"https://www.wikidata.org/wiki/Q1195816","display_name":"Transfer (computing)","level":2,"score":0.42260679602622986},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10147607326507568},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","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}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1145/1390156.1390225","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1390156.1390225","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th international conference on Machine learning - ICML '08","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.140.2407","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.140.2407","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://home.dei.polimi.it/lazaric/papers/lazaric2008transfer.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.149.8448","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.149.8448","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://icml2008.cs.helsinki.fi/papers/479.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.931.3947","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.931.3947","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://www.researchgate.net/profile/Alessandro_Lazaric/publication/221345289_Transfer_of_samples_in_batch_reinforcement_learning/links/0fcfd50b38be0eace2000000.pdf","raw_type":"text"},{"id":"pmh:oai:re.public.polimi.it:11311/549209","is_oa":false,"landing_page_url":"http://hdl.handle.net/11311/549209","pdf_url":null,"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W131458779","https://openalex.org/W1492014007","https://openalex.org/W1582256513","https://openalex.org/W2090170171","https://openalex.org/W2109102709","https://openalex.org/W2110292307","https://openalex.org/W2120346334","https://openalex.org/W2131831090","https://openalex.org/W2132057084","https://openalex.org/W2133040789","https://openalex.org/W2568646110","https://openalex.org/W3035219538"],"related_works":["https://openalex.org/W2821676139","https://openalex.org/W3043695725","https://openalex.org/W4382138864","https://openalex.org/W4387770285","https://openalex.org/W3022215768","https://openalex.org/W3135975972","https://openalex.org/W3016888008","https://openalex.org/W4385864216","https://openalex.org/W4387183713","https://openalex.org/W4403518771"],"abstract_inverted_index":{"The":[0],"main":[1],"objective":[2],"of":[3,13,17,31,103,130],"transfer":[4,129],"in":[5,134],"reinforcement":[6],"learning":[7,14,137],"is":[8,118,132],"to":[9,53,72,83,89,108,114],"reduce":[10],"the":[11,15,24,57,76,84,101,111,125,128,136,148],"complexity":[12],"solution":[16,117],"a":[18,29,39,70,99],"target":[19,54,85,112,149],"task":[20,113],"by":[21],"effectively":[22],"reusing":[23],"knowledge":[25],"retained":[26],"from":[27,51,75,110,147],"solving":[28],"set":[30],"source":[32,52,77,142],"tasks.":[33,55],"In":[34],"this":[35],"paper,":[36],"we":[37,68],"introduce":[38],"novel":[40],"algorithm":[41],"that":[42,59,79],"transfers":[43],"samples":[44,74,104,131],"(i.e.,":[45],"tuples":[46],"\u3008s,":[47],"a,":[48],"s',":[49],"r\u3009)":[50],"Under":[56],"assumption":[58],"tasks":[60,78,143],"have":[61],"similar":[62,82],"transition":[63],"models":[64],"and":[65],"reward":[66],"functions,":[67],"propose":[69],"method":[71],"select":[73],"are":[80,144],"mostly":[81],"task,":[86],"and,":[87],"then,":[88],"use":[90],"them":[91],"as":[92],"input":[93],"for":[94],"batch":[95],"reinforcement-learning":[96],"algorithms.":[97],"As":[98],"result,":[100],"number":[102],"an":[105],"agent":[106],"needs":[107],"collect":[109],"learn":[115],"its":[116],"reduced.":[119],"We":[120],"empirically":[121],"show":[122],"that,":[123],"following":[124],"proposed":[126],"approach,":[127],"effective":[133],"reducing":[135],"complexity,":[138],"even":[139],"when":[140],"some":[141],"significantly":[145],"different":[146],"task.":[150]},"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":10},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":18},{"year":2020,"cited_by_count":34},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":18},{"year":2017,"cited_by_count":10},{"year":2016,"cited_by_count":9},{"year":2015,"cited_by_count":8},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":11},{"year":2012,"cited_by_count":10}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}