{"id":"https://openalex.org/W4396705778","doi":"https://doi.org/10.3389/fnbot.2024.1364587","title":"Hybrid knowledge transfer for MARL based on action advising and experience sharing","display_name":"Hybrid knowledge transfer for MARL based on action advising and experience sharing","publication_year":2024,"publication_date":"2024-05-07","ids":{"openalex":"https://openalex.org/W4396705778","doi":"https://doi.org/10.3389/fnbot.2024.1364587","pmid":"https://pubmed.ncbi.nlm.nih.gov/38774520"},"language":"en","primary_location":{"id":"doi:10.3389/fnbot.2024.1364587","is_oa":true,"landing_page_url":"http://dx.doi.org/10.3389/fnbot.2024.1364587","pdf_url":"https://public-pages-files-2025.frontiersin.org/journals/neurorobotics/articles/10.3389/fnbot.2024.1364587/pdf","source":{"id":"https://openalex.org/S115606517","display_name":"Frontiers in Neurorobotics","issn_l":"1662-5218","issn":["1662-5218"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Neurorobotics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://public-pages-files-2025.frontiersin.org/journals/neurorobotics/articles/10.3389/fnbot.2024.1364587/pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009007385","display_name":"Feng Liu","orcid":"https://orcid.org/0000-0001-9367-049X"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]},{"id":"https://openalex.org/I4210112761","display_name":"Kunming Metallurgical Research Institute","ror":"https://ror.org/01kfnjv17","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210112761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Liu","raw_affiliation_strings":["Kunming Precision Machinery Research Institute, Kunming, China","School of Marine Science and Technology, Northwestern Polytechnical University, Xi'an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kunming Precision Machinery Research Institute, Kunming, China","institution_ids":["https://openalex.org/I4210112761"]},{"raw_affiliation_string":"School of Marine Science and Technology, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050997076","display_name":"Dongqi Li","orcid":"https://orcid.org/0000-0002-4181-3441"},"institutions":[{"id":"https://openalex.org/I4210112761","display_name":"Kunming Metallurgical Research Institute","ror":"https://ror.org/01kfnjv17","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210112761"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Dongqi Li","raw_affiliation_strings":["Kunming Precision Machinery Research Institute, Kunming, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kunming Precision Machinery Research Institute, Kunming, China","institution_ids":["https://openalex.org/I4210112761"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032200261","display_name":"Jian Gao","orcid":"https://orcid.org/0000-0002-1181-4531"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Gao","raw_affiliation_strings":["School of Marine Science and Technology, Northwestern Polytechnical University, Xi'an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Marine Science and Technology, Northwestern Polytechnical University, Xi'an, China","institution_ids":["https://openalex.org/I17145004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5050997076"],"corresponding_institution_ids":["https://openalex.org/I4210112761"],"apc_list":{"value":2950,"currency":"USD","value_usd":2950},"apc_paid":{"value":2950,"currency":"USD","value_usd":2950},"fwci":0.6294,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.7208849,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"18","issue":null,"first_page":"1364587","last_page":"1364587"},"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9871000051498413,"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/T12611","display_name":"Neural Networks and Reservoir Computing","score":0.9812999963760376,"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":0.8190168738365173},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6820715665817261},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.5776252150535583},{"id":"https://openalex.org/keywords/knowledge-transfer","display_name":"Knowledge transfer","score":0.5693427324295044},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5683771967887878},{"id":"https://openalex.org/keywords/knowledge-sharing","display_name":"Knowledge sharing","score":0.556698739528656},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5196458101272583},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4830089807510376},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.47217315435409546},{"id":"https://openalex.org/keywords/knowledge-management","display_name":"Knowledge management","score":0.40409424901008606},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3704878091812134},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.09828805923461914}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8190168738365173},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6820715665817261},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.5776252150535583},{"id":"https://openalex.org/C2776960227","wikidata":"https://www.wikidata.org/wiki/Q2586354","display_name":"Knowledge transfer","level":2,"score":0.5693427324295044},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5683771967887878},{"id":"https://openalex.org/C2776604539","wikidata":"https://www.wikidata.org/wiki/Q6423395","display_name":"Knowledge sharing","level":2,"score":0.556698739528656},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5196458101272583},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4830089807510376},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.47217315435409546},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.40409424901008606},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3704878091812134},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.09828805923461914},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.3389/fnbot.2024.1364587","is_oa":true,"landing_page_url":"http://dx.doi.org/10.3389/fnbot.2024.1364587","pdf_url":"https://public-pages-files-2025.frontiersin.org/journals/neurorobotics/articles/10.3389/fnbot.2024.1364587/pdf","source":{"id":"https://openalex.org/S115606517","display_name":"Frontiers in Neurorobotics","issn_l":"1662-5218","issn":["1662-5218"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Neurorobotics","raw_type":"journal-article"},{"id":"pmid:38774520","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38774520","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":"Frontiers in neurorobotics","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:11106758","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/11106758","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC11106758/pdf/fnbot-18-1364587.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Front Neurorobot","raw_type":"Text"},{"id":"pmh:oai:doaj.org/article:360e1ded9e834f76a2a3ec3f3cdfec23","is_oa":true,"landing_page_url":"https://doaj.org/article/360e1ded9e834f76a2a3ec3f3cdfec23","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Frontiers in Neurorobotics, Vol 18 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3389/fnbot.2024.1364587","is_oa":true,"landing_page_url":"http://dx.doi.org/10.3389/fnbot.2024.1364587","pdf_url":"https://public-pages-files-2025.frontiersin.org/journals/neurorobotics/articles/10.3389/fnbot.2024.1364587/pdf","source":{"id":"https://openalex.org/S115606517","display_name":"Frontiers in Neurorobotics","issn_l":"1662-5218","issn":["1662-5218"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Neurorobotics","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.7300000190734863,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G7367001821","display_name":null,"funder_award_id":"2021YFC2803003","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4396705778.pdf","grobid_xml":"https://content.openalex.org/works/W4396705778.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W41554520","https://openalex.org/W1583837637","https://openalex.org/W1610678877","https://openalex.org/W2145339207","https://openalex.org/W2154018708","https://openalex.org/W2531563875","https://openalex.org/W2553964525","https://openalex.org/W2575731723","https://openalex.org/W2586101872","https://openalex.org/W2620645529","https://openalex.org/W2622408375","https://openalex.org/W2739657930","https://openalex.org/W2902907165","https://openalex.org/W2911825241","https://openalex.org/W2921955147","https://openalex.org/W2963658727","https://openalex.org/W2996868001","https://openalex.org/W2996913556","https://openalex.org/W3126321819","https://openalex.org/W3181216121","https://openalex.org/W3181652669","https://openalex.org/W4213377513","https://openalex.org/W4214759040","https://openalex.org/W4298857966","https://openalex.org/W4390661023","https://openalex.org/W6631533588","https://openalex.org/W6637033378","https://openalex.org/W6637967152","https://openalex.org/W6730844258","https://openalex.org/W6734678876","https://openalex.org/W6741408367","https://openalex.org/W6752059867","https://openalex.org/W6771682139","https://openalex.org/W6793862206"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W2031695474","https://openalex.org/W2024136090","https://openalex.org/W2586732548","https://openalex.org/W3049728571","https://openalex.org/W2768698792","https://openalex.org/W186767603"],"abstract_inverted_index":{"Multiagent":[0],"Reinforcement":[1],"Learning":[2],"(MARL)":[3],"has":[4],"been":[5,27,96],"well":[6],"adopted":[7],"due":[8],"to":[9,13,102,145,149,170,174],"its":[10],"exceptional":[11],"ability":[12],"solve":[14],"multiagent":[15],"decision-making":[16],"problems.":[17],"To":[18,112],"further":[19,175],"enhance":[20,146],"learning":[21,110,133],"efficiency,":[22],"knowledge":[23,66,86,127],"transfer":[24,34,67,87,128],"algorithms":[25],"have":[26,95],"developed,":[28],"among":[29],"which":[30],"experience-sharing-based":[31,85,189],"and":[32,75,119,188],"action-advising-based":[33,60],"strategies":[35],"share":[36],"the":[37,58,82,91,108,114,131,147,166,177,182],"mainstream.":[38],"However,":[39],"it":[40],"is":[41],"notable":[42],"that,":[43],"although":[44,90],"there":[45],"exist":[46],"many":[47],"successful":[48],"applications":[49],"of":[50,93,116],"both":[51,117],"strategies,":[52],"they":[53,99],"are":[54,77,100,137],"not":[55,78],"flawless.":[56],"For":[57],"long-developed":[59],"methods":[61,88,136,173],"(namely":[62],"KT-AA,":[63],"short":[64],"for":[65,81],"based":[68],"on":[69,160],"action":[70],"advising),":[71],"their":[72],"data":[73,141],"efficiency":[74,142],"scalability":[76],"satisfactory.":[79],"As":[80],"newly":[83],"proposed":[84,183],"(KT-ES),":[89],"shortcomings":[92],"KT-AA":[94,118,172],"partially":[97],"overcome,":[98],"incompetent":[101],"correct":[103],"specific":[104,162],"bad":[105],"decisions":[106],"in":[107],"later":[109],"stage.":[111],"leverage":[113],"superiority":[115],"KT-ES,":[120],"this":[121],"study":[122],"proposes":[123],"KT-Hybrid,":[124],"a":[125,150],"hybrid":[126],"approach.":[129],"In":[130],"early":[132],"phase,":[134],"KT-ES":[135,144],"employed,":[138],"expecting":[139],"better":[140],"from":[143],"policy":[148],"basic":[151,167],"level":[152],"as":[153,155],"soon":[154],"possible.":[156],"Later,":[157],"we":[158],"focus":[159],"correcting":[161],"errors":[163],"made":[164],"by":[165],"policy,":[168],"trying":[169],"use":[171],"improve":[176],"performance.":[178],"Simulations":[179],"demonstrate":[180],"that":[181],"KT-Hybrid":[184],"outperforms":[185],"well-received":[186],"action-advising-":[187],"methods.":[190]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
