{"id":"https://openalex.org/W3200466256","doi":"https://doi.org/10.1109/tnnls.2021.3107375","title":"Model-Based Transfer Reinforcement Learning Based on Graphical Model Representations","display_name":"Model-Based Transfer Reinforcement Learning Based on Graphical Model Representations","publication_year":2021,"publication_date":"2021-09-20","ids":{"openalex":"https://openalex.org/W3200466256","doi":"https://doi.org/10.1109/tnnls.2021.3107375","mag":"3200466256","pmid":"https://pubmed.ncbi.nlm.nih.gov/34543207"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2021.3107375","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2021.3107375","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5103266231","display_name":"Yuewen Sun","orcid":"https://orcid.org/0000-0001-7534-1297"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuewen Sun","raw_affiliation_strings":["School of Automation, Southeast University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0001-7534-1297","affiliations":[{"raw_affiliation_string":"School of Automation, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100342309","display_name":"Kun Zhang","orcid":"https://orcid.org/0000-0002-0738-9958"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kun Zhang","raw_affiliation_strings":["Department of Philosophy, Carnegie Mellon University, Pittsburgh, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Philosophy, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019248683","display_name":"Changyin Sun","orcid":"https://orcid.org/0000-0001-9269-334X"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changyin Sun","raw_affiliation_strings":["School of Automation, Southeast University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0001-9269-334X","affiliations":[{"raw_affiliation_string":"School of Automation, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.3202,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.90227042,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"34","issue":"2","first_page":"1035","last_page":"1048"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9990000128746033,"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":0.9990000128746033,"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":0.9986000061035156,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9884999990463257,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7636466026306152},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6943119764328003},{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.6789219975471497},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6458228230476379},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6213717460632324},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6114263534545898},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.594130277633667},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.49494093656539917},{"id":"https://openalex.org/keywords/graphical-model","display_name":"Graphical model","score":0.4452134072780609}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7636466026306152},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6943119764328003},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.6789219975471497},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6458228230476379},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6213717460632324},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6114263534545898},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.594130277633667},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.49494093656539917},{"id":"https://openalex.org/C155846161","wikidata":"https://www.wikidata.org/wiki/Q1143367","display_name":"Graphical model","level":2,"score":0.4452134072780609},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2021.3107375","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2021.3107375","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:34543207","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/34543207","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on neural networks and learning systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.5899999737739563,"id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G1586809628","display_name":null,"funder_award_id":"2018AAA0101400","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G5033343354","display_name":null,"funder_award_id":"61921004","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6231356856","display_name":null,"funder_award_id":"FA8650-17-C-7715","funder_id":"https://openalex.org/F4320332467","funder_display_name":"U.S. Air Force"},{"id":"https://openalex.org/G7121147207","display_name":null,"funder_award_id":"BK20202006","funder_id":"https://openalex.org/F4320322769","funder_display_name":"Natural Science Foundation of Jiangsu Province"},{"id":"https://openalex.org/G7735959302","display_name":null,"funder_award_id":"R01HL159805","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"}],"funders":[{"id":"https://openalex.org/F4320317469","display_name":"Apple","ror":"https://ror.org/059hsda18"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"},{"id":"https://openalex.org/F4320322769","display_name":"Natural Science Foundation of Jiangsu Province","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320332467","display_name":"U.S. Air Force","ror":"https://ror.org/006gmme17"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":76,"referenced_works":["https://openalex.org/W158722652","https://openalex.org/W1511986666","https://openalex.org/W1600437712","https://openalex.org/W1977655452","https://openalex.org/W1980035368","https://openalex.org/W1988115241","https://openalex.org/W2007245391","https://openalex.org/W2091565802","https://openalex.org/W2097381042","https://openalex.org/W2131556519","https://openalex.org/W2145339207","https://openalex.org/W2155007355","https://openalex.org/W2165698076","https://openalex.org/W2179284380","https://openalex.org/W2257979135","https://openalex.org/W2344786740","https://openalex.org/W2509783950","https://openalex.org/W2546571074","https://openalex.org/W2605102758","https://openalex.org/W2626333357","https://openalex.org/W2726279040","https://openalex.org/W2733312032","https://openalex.org/W2740437707","https://openalex.org/W2754517384","https://openalex.org/W2768956845","https://openalex.org/W2772580566","https://openalex.org/W2787933113","https://openalex.org/W2809208194","https://openalex.org/W2905249540","https://openalex.org/W2907214660","https://openalex.org/W2908643158","https://openalex.org/W2962872206","https://openalex.org/W2968021416","https://openalex.org/W2989186172","https://openalex.org/W2997891625","https://openalex.org/W3009492911","https://openalex.org/W3012211643","https://openalex.org/W3014891618","https://openalex.org/W3017042178","https://openalex.org/W3034445502","https://openalex.org/W3035825996","https://openalex.org/W3039737909","https://openalex.org/W3081678145","https://openalex.org/W3088811935","https://openalex.org/W3088813040","https://openalex.org/W3093475218","https://openalex.org/W3113734015","https://openalex.org/W3123082711","https://openalex.org/W3126833157","https://openalex.org/W4214717370","https://openalex.org/W4292824755","https://openalex.org/W4302423442","https://openalex.org/W6633949838","https://openalex.org/W6635902665","https://openalex.org/W6637967152","https://openalex.org/W6638018090","https://openalex.org/W6674600207","https://openalex.org/W6680657880","https://openalex.org/W6682849425","https://openalex.org/W6684921986","https://openalex.org/W6685726866","https://openalex.org/W6691889631","https://openalex.org/W6692846177","https://openalex.org/W6730095352","https://openalex.org/W6736469832","https://openalex.org/W6741002519","https://openalex.org/W6742103744","https://openalex.org/W6742945991","https://openalex.org/W6753264383","https://openalex.org/W6760405395","https://openalex.org/W6773110963","https://openalex.org/W6778230177","https://openalex.org/W6779512577","https://openalex.org/W6780559895","https://openalex.org/W6783144354","https://openalex.org/W6791283100"],"related_works":["https://openalex.org/W2905433371","https://openalex.org/W2888392564","https://openalex.org/W4310278675","https://openalex.org/W4388422664","https://openalex.org/W4390569940","https://openalex.org/W4361193272","https://openalex.org/W2963326959","https://openalex.org/W4388685194","https://openalex.org/W4312407344","https://openalex.org/W2768698792"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,56],"(RL)":[2],"plays":[3],"an":[4],"essential":[5],"role":[6],"in":[7,69,141,163],"the":[8,63,76,84,98,103,114,119,128,138,142,150,169,172,189,201,204],"field":[9],"of":[10,83,152,171,203],"artificial":[11],"intelligence":[12],"but":[13],"suffers":[14],"from":[15],"data":[16],"inefficiency":[17],"and":[18,37,54,65,73,156,197],"model-shift":[19],"issues.":[20],"One":[21],"possible":[22],"solution":[23],"to":[24,30,75,96,136,154,188],"deal":[25],"with":[26],"such":[27],"issues":[28],"is":[29,131],"exploit":[31],"transfer":[32,39,155,159],"learning.":[33],"However,":[34],"interpretability":[35],"problems":[36,182],"negative":[38],"may":[40],"occur":[41],"without":[42],"explainable":[43,53],"models.":[44],"In":[45],"this":[46],"article,":[47],"we":[48,89,110,175],"define":[49],"Relation":[50],"Transfer":[51],"as":[52,133,183,185],"transferable":[55],"based":[57,101,117],"on":[58,102,113,118,127,178,194],"graphical":[59],"model":[60,116,130],"representations,":[61],"inferring":[62],"skeleton":[64],"relations":[66],"among":[67],"variables":[68],"a":[70,91,164],"causal":[71,99,121],"view":[72],"generalizing":[74],"target":[77,115,129,143],"domain.":[78,144],"The":[79,145],"proposed":[80,146,173,205],"algorithm":[81],"consists":[82],"following":[85],"three":[86],"steps.":[87],"First,":[88],"leverage":[90],"suitable":[92],"casual":[93],"discovery":[94],"method":[95,147],"identify":[97],"graph":[100],"augmented":[104],"source":[105],"domain":[106],"data.":[107],"After":[108],"that,":[109],"make":[111],"inferences":[112],"prior":[120,134],"knowledge.":[122],"Finally,":[123],"offline":[124],"RL":[125],"training":[126,140],"utilized":[132],"knowledge":[135],"improve":[137],"policy":[139],"can":[148],"answer":[149],"question":[151],"what":[153],"realize":[157],"zero-shot":[158],"across":[160],"related":[161],"domains":[162],"principled":[165],"way.":[166],"To":[167],"demonstrate":[168,200],"robustness":[170],"framework,":[174],"conduct":[176],"experiments":[177],"four":[179],"classical":[180],"control":[181],"well":[184],"one":[186],"simulation":[187],"real-world":[190],"application.":[191],"Experimental":[192],"results":[193],"both":[195],"continuous":[196],"discrete":[198],"cases":[199],"efficacy":[202],"method.":[206]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}