{"id":"https://openalex.org/W4392173825","doi":"https://doi.org/10.1109/tetci.2024.3361860","title":"Reinforcement Learning With Adaptive Policy Gradient Transfer Across Heterogeneous Problems","display_name":"Reinforcement Learning With Adaptive Policy Gradient Transfer Across Heterogeneous Problems","publication_year":2024,"publication_date":"2024-02-26","ids":{"openalex":"https://openalex.org/W4392173825","doi":"https://doi.org/10.1109/tetci.2024.3361860"},"language":"en","primary_location":{"id":"doi:10.1109/tetci.2024.3361860","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tetci.2024.3361860","pdf_url":null,"source":{"id":"https://openalex.org/S4210210251","display_name":"IEEE Transactions on Emerging Topics in Computational Intelligence","issn_l":"2471-285X","issn":["2471-285X"],"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 Emerging Topics in Computational Intelligence","raw_type":"journal-article"},"type":"article","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/A5005174710","display_name":"Gengzhi Zhang","orcid":"https://orcid.org/0009-0009-7960-2605"},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"education","lineage":["https://openalex.org/I158842170"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Gengzhi Zhang","raw_affiliation_strings":["College of Computer Science, Chongqing University, Chongqing, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science, Chongqing University, Chongqing, China","institution_ids":["https://openalex.org/I158842170"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051395807","display_name":"Liang Feng","orcid":"https://orcid.org/0000-0002-8356-7242"},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"education","lineage":["https://openalex.org/I158842170"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Feng","raw_affiliation_strings":["College of Computer Science, Chongqing University, Chongqing, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science, Chongqing University, Chongqing, China","institution_ids":["https://openalex.org/I158842170"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115694977","display_name":"Yu Wang","orcid":"https://orcid.org/0000-0002-8159-8723"},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Wang","raw_affiliation_strings":["Department of User Growth and Operations, Jing Dong Retail, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of User Growth and Operations, Jing Dong Retail, Beijing, China","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100400712","display_name":"Min Li","orcid":"https://orcid.org/0000-0001-9013-2020"},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Min Li","raw_affiliation_strings":["Department of User Growth and Operations, Jing Dong Retail, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of User Growth and Operations, Jing Dong Retail, Beijing, China","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064190343","display_name":"Hong Xie","orcid":null},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"education","lineage":["https://openalex.org/I158842170"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hong Xie","raw_affiliation_strings":["College of Computer Science, Chongqing University, Chongqing, China"],"affiliations":[{"raw_affiliation_string":"College of Computer Science, Chongqing University, Chongqing, China","institution_ids":["https://openalex.org/I158842170"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025285243","display_name":"Kay Chen Tan","orcid":"https://orcid.org/0000-0002-6802-2463"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Kay Chen Tan","raw_affiliation_strings":["Department of Computing, The Hong Kong Polytechnic University, Hong Kong SAR"],"affiliations":[{"raw_affiliation_string":"Department of Computing, The Hong Kong Polytechnic University, Hong Kong SAR","institution_ids":["https://openalex.org/I14243506"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5005174710"],"corresponding_institution_ids":["https://openalex.org/I158842170"],"apc_list":null,"apc_paid":null,"fwci":2.0885,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.88013479,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"8","issue":"3","first_page":"2213","last_page":"2227"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9972000122070312,"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"}},{"id":"https://openalex.org/T10524","display_name":"Traffic control and management","score":0.977400004863739,"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","display_name":"Reinforcement","score":0.7187417149543762},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6694566011428833},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.5310276746749878},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.398547500371933},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.26704496145248413},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.22178328037261963},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.09953591227531433}],"concepts":[{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.7187417149543762},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6694566011428833},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.5310276746749878},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.398547500371933},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.26704496145248413},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.22178328037261963},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.09953591227531433}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tetci.2024.3361860","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tetci.2024.3361860","pdf_url":null,"source":{"id":"https://openalex.org/S4210210251","display_name":"IEEE Transactions on Emerging Topics in Computational Intelligence","issn_l":"2471-285X","issn":["2471-285X"],"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 Emerging Topics in Computational Intelligence","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4699999988079071,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[{"id":"https://openalex.org/G1755174478","display_name":null,"funder_award_id":"P0035379","funder_id":"https://openalex.org/F4320322598","funder_display_name":"Hong Kong Polytechnic University"},{"id":"https://openalex.org/G2757623951","display_name":null,"funder_award_id":"U21A20512","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2952403178","display_name":null,"funder_award_id":"2022M710517","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"},{"id":"https://openalex.org/G4651879208","display_name":null,"funder_award_id":"P0039734","funder_id":"https://openalex.org/F4320322598","funder_display_name":"Hong Kong Polytechnic University"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"},{"id":"https://openalex.org/F4320322598","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":66,"referenced_works":["https://openalex.org/W158722652","https://openalex.org/W778742492","https://openalex.org/W1191599655","https://openalex.org/W1522301498","https://openalex.org/W1582256513","https://openalex.org/W2031727428","https://openalex.org/W2097381042","https://openalex.org/W2107726111","https://openalex.org/W2119717200","https://openalex.org/W2131600418","https://openalex.org/W2145339207","https://openalex.org/W2164114810","https://openalex.org/W2233997862","https://openalex.org/W2583993537","https://openalex.org/W2736601468","https://openalex.org/W2760355785","https://openalex.org/W2772589676","https://openalex.org/W2788862220","https://openalex.org/W2807238303","https://openalex.org/W2810440851","https://openalex.org/W2949600457","https://openalex.org/W2953334758","https://openalex.org/W2962817122","https://openalex.org/W2963095800","https://openalex.org/W2963099939","https://openalex.org/W2963890729","https://openalex.org/W2973229164","https://openalex.org/W3027186203","https://openalex.org/W3034815680","https://openalex.org/W3088310808","https://openalex.org/W3100789280","https://openalex.org/W3100944043","https://openalex.org/W3103559770","https://openalex.org/W3120732119","https://openalex.org/W3120778962","https://openalex.org/W3127561923","https://openalex.org/W3137138892","https://openalex.org/W3209989022","https://openalex.org/W4210876519","https://openalex.org/W4298174377","https://openalex.org/W4300065704","https://openalex.org/W4312576764","https://openalex.org/W4376269829","https://openalex.org/W4383112908","https://openalex.org/W6616173779","https://openalex.org/W6627932998","https://openalex.org/W6631190155","https://openalex.org/W6638018090","https://openalex.org/W6674600207","https://openalex.org/W6680962669","https://openalex.org/W6683001934","https://openalex.org/W6683195989","https://openalex.org/W6685726866","https://openalex.org/W6692846177","https://openalex.org/W6696324988","https://openalex.org/W6730038592","https://openalex.org/W6730111887","https://openalex.org/W6732665253","https://openalex.org/W6732837357","https://openalex.org/W6736469832","https://openalex.org/W6738637145","https://openalex.org/W6740879895","https://openalex.org/W6741002519","https://openalex.org/W6751285671","https://openalex.org/W6751794878","https://openalex.org/W6759225949"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856"],"abstract_inverted_index":{"To":[0,206],"date,":[1],"transfer":[2,20,39,63,100,117,136,154,196,201,253,269],"learning":[3,12,16,272],"(TL)":[4],"has":[5],"been":[6,25],"successfully":[7],"applied":[8],"for":[9,60,118,155,198,257],"enhancing":[10],"the":[11,28,33,44,56,83,87,91,98,128,156,168,208,211,222,232,243,263,271,275],"performance":[13,209],"of":[14,32,90,167,187,210,234],"reinforcement":[15],"(RL),":[17],"and":[18,191,248,274],"many":[19,72],"RL":[21,41,57,92,121,139,162,204,226,259,264],"(TRL)":[22],"approaches":[23,36],"have":[24,125,215],"proposed":[26,169,212,244],"in":[27,53,71,86,97,231,250,270],"literature.":[29],"However,":[30],"most":[31],"existing":[34,276],"TRL":[35,75,148,278],"consider":[37],"knowledge":[38,62,99,116,135,200,252,268],"between":[40],"tasks":[42,58,93,111,190],"sharing":[43],"same":[45],"state-action":[46,66,88],"space.":[47],"These":[48],"methods":[49],"thus":[50],"may":[51],"fail":[52],"cases":[54,157],"where":[55],"available":[59,113],"conducting":[61,115,199,251],"possess":[64],"heterogeneous":[65,77,109,160,188,203,229,255],"spaces,":[67],"which":[68],"is":[69,80,246],"common":[70],"real-world":[73],"applications.":[74],"across":[76,101,202,254],"problem":[78],"domains":[79],"challenging":[81],"since":[82],"differences":[84],"lie":[85],"spaces":[89],"are":[94,112],"natural":[95],"barriers":[96],"tasks.":[102,163,205],"This":[103],"becomes":[104],"more":[105],"difficult":[106],"if":[107],"multiple":[108,159],"source":[110,130,161,189],"when":[114],"a":[119,146,172,185,192],"target":[120],"task,":[122],"as":[123],"we":[124,144,214],"to":[126,179],"identify":[127],"appropriate":[129,182],"task":[131,176,183,227],"adaptively":[132],"before":[133],"performing":[134],"towards":[137],"enhanced":[138,258],"performance.":[140],"In":[141],"this":[142],"article,":[143],"propose":[145],"new":[147],"algorithm":[149,170,245,265],"with":[150,228],"adaptive":[151],"policy":[152],"gradient":[153],"having":[158,266],"The":[164,238],"core":[165],"ingredients":[166],"contain":[171],"<italic":[173,193],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[174,194],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">source":[175],"selection":[177],"module</i>":[178,197],"select":[180],"an":[181],"from":[184],"set":[186],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">knowledge":[195],"investigate":[207],"algorithm,":[213],"conducted":[216],"comprehensive":[217],"empirical":[218],"studies":[219],"based":[220],"on":[221],"well-known":[223],"continuous":[224],"robotic":[225],"settings":[230],"number":[233],"robot":[235],"arms":[236],"(links).":[237],"obtained":[239],"results":[240],"show":[241],"that":[242],"effective":[247],"efficient":[249],"problems":[256],"performance,":[260],"over":[261],"both":[262],"no":[267],"process":[273],"state-of-the-art":[277],"method.":[279]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2}],"updated_date":"2026-03-28T08:17:26.163206","created_date":"2025-10-10T00:00:00"}