{"id":"https://openalex.org/W4406890416","doi":"https://doi.org/10.1109/tetci.2025.3529902","title":"MENTOR: Guiding Hierarchical Reinforcement Learning With Human Feedback and Dynamic Distance Constraint","display_name":"MENTOR: Guiding Hierarchical Reinforcement Learning With Human Feedback and Dynamic Distance Constraint","publication_year":2025,"publication_date":"2025-01-28","ids":{"openalex":"https://openalex.org/W4406890416","doi":"https://doi.org/10.1109/tetci.2025.3529902"},"language":"en","primary_location":{"id":"doi:10.1109/tetci.2025.3529902","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tetci.2025.3529902","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/A5112708176","display_name":"Xinglin Zhou","orcid":null},"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":"Xinglin Zhou","raw_affiliation_strings":["Southeast University-Monash University Joint Graduate School, Southeast University, Suzhou, China"],"raw_orcid":"https://orcid.org/0009-0003-5149-4450","affiliations":[{"raw_affiliation_string":"Southeast University-Monash University Joint Graduate School, Southeast University, Suzhou, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029674206","display_name":"Yifu Yuan","orcid":null},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yifu Yuan","raw_affiliation_strings":["College of Intelligence and Computing, Tianjin University, Tianjin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012649202","display_name":"Shaofu Yang","orcid":"https://orcid.org/0000-0001-7727-9669"},"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":"Shaofu Yang","raw_affiliation_strings":["School of Computer Science and Engineering, Southeast University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0001-7727-9669","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047509839","display_name":"Jianye Hao","orcid":"https://orcid.org/0000-0002-0422-8235"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianye Hao","raw_affiliation_strings":["College of Intelligence and Computing, Tianjin University, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0002-0422-8235","affiliations":[{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":9.772,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.97586228,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"9","issue":"2","first_page":"1292","last_page":"1306"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.8950999975204468,"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":0.8950999975204468,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7147141695022583},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.6028993725776672},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5369517803192139},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5351904630661011},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3935950994491577},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.33134791254997253},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.23677566647529602},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.19518929719924927},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.12414246797561646},{"id":"https://openalex.org/keywords/mechanical-engineering","display_name":"Mechanical engineering","score":0.08466118574142456}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7147141695022583},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.6028993725776672},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5369517803192139},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5351904630661011},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3935950994491577},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.33134791254997253},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.23677566647529602},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.19518929719924927},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.12414246797561646},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.08466118574142456}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tetci.2025.3529902","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tetci.2025.3529902","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":[],"awards":[{"id":"https://openalex.org/G325098684","display_name":null,"funder_award_id":"92370132","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6273817310","display_name":null,"funder_award_id":"62176056","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W2121517924","https://openalex.org/W2763110165","https://openalex.org/W2963142324","https://openalex.org/W2963523627","https://openalex.org/W2964227312","https://openalex.org/W3134002512","https://openalex.org/W3203056473","https://openalex.org/W3208890675","https://openalex.org/W4212996499","https://openalex.org/W4214809715","https://openalex.org/W4250739957","https://openalex.org/W4319663730","https://openalex.org/W4385462854","https://openalex.org/W4385819655","https://openalex.org/W4386590850","https://openalex.org/W4390874002","https://openalex.org/W4394841758","https://openalex.org/W4401024499","https://openalex.org/W6616173779","https://openalex.org/W6681840828","https://openalex.org/W6683443546","https://openalex.org/W6717230150","https://openalex.org/W6740801417","https://openalex.org/W6742461812","https://openalex.org/W6748599296","https://openalex.org/W6748603076","https://openalex.org/W6752089545","https://openalex.org/W6754978010","https://openalex.org/W6756303580","https://openalex.org/W6759871227","https://openalex.org/W6764724164","https://openalex.org/W6768425981","https://openalex.org/W6768831546","https://openalex.org/W6772008794","https://openalex.org/W6773447848","https://openalex.org/W6776824048","https://openalex.org/W6778883912","https://openalex.org/W6779463497","https://openalex.org/W6779651979","https://openalex.org/W6796168157","https://openalex.org/W6799431981","https://openalex.org/W6802965437","https://openalex.org/W6804074916","https://openalex.org/W6810044100","https://openalex.org/W6810640255","https://openalex.org/W6810738896","https://openalex.org/W6838729795","https://openalex.org/W6849750003","https://openalex.org/W6852418670","https://openalex.org/W6854341480","https://openalex.org/W6857146736"],"related_works":["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","https://openalex.org/W2145821588","https://openalex.org/W2086122291","https://openalex.org/W1987513656"],"abstract_inverted_index":{"Hierarchical":[0],"reinforcement":[1,53],"learning":[2,42,54,82,113,123],"(HRL)":[3],"provides":[4],"a":[5,18,40,50,70,120,132,151],"promising":[6],"solution":[7],"for":[8,38,129,137],"complex":[9,162],"tasks":[10,23,163],"with":[11,164],"sparse":[12,165],"rewards":[13],"of":[14,100,154],"agents,":[15],"which":[16,67],"uses":[17,150],"hierarchical":[19,52],"framework":[20,55],"that":[21,104,148],"divides":[22],"into":[24,79],"subgoals":[25,37,108],"and":[26,59],"completes":[27],"them":[28],"sequentially.":[29],"However,":[30],"current":[31],"methods":[32],"struggle":[33],"to":[34,83,117,140,157],"find":[35,84],"suitable":[36],"ensuring":[39],"stable":[41],"process.":[43,144],"To":[44],"address":[45],"the":[46,90,98,110,122,142],"issue,":[47],"we":[48,88],"propose":[49,89],"general":[51],"incorporating":[56],"human":[57,75,155],"feedback":[58,76,156],"dynamic":[60],"distance":[61],"constraints,":[62],"termed":[63],"<bold":[64],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[65,72],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">MENTOR</b>,":[66],"acts":[68],"as":[69],"\u201c<italic":[71],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">mentor</i>\u201d.":[73],"Specifically,":[74],"is":[77,135],"incorporated":[78],"high-level":[80],"policy":[81,112,134],"better":[85],"subgoals.":[86],"Furthermore,":[87],"Dynamic":[91],"Distance":[92],"Constraint":[93],"(DDC)":[94],"mechanism":[95],"dynamically":[96],"adjusting":[97],"space":[99],"optional":[101],"subgoals,":[102],"such":[103],"MENTOR":[105,149],"can":[106,125],"generate":[107],"matching":[109],"low-level":[111,130],"process":[114],"from":[115],"easy":[116],"hard.":[118],"As":[119,128],"result,":[121],"efficiency":[124],"be":[126],"improved.":[127],"policy,":[131],"dual":[133],"designed":[136],"exploration-exploitation":[138],"decoupling":[139],"stabilize":[141],"training":[143],"Extensive":[145],"experiments":[146],"demonstrate":[147],"small":[152],"amount":[153],"achieve":[158],"significant":[159],"improvement":[160],"in":[161],"rewards.":[166]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":5}],"updated_date":"2025-12-22T23:10:17.713674","created_date":"2025-10-10T00:00:00"}