{"id":"https://openalex.org/W3195378132","doi":"https://doi.org/10.3390/e23081043","title":"KnowRU: Knowledge Reuse via Knowledge Distillation in Multi-Agent Reinforcement Learning","display_name":"KnowRU: Knowledge Reuse via Knowledge Distillation in Multi-Agent Reinforcement Learning","publication_year":2021,"publication_date":"2021-08-13","ids":{"openalex":"https://openalex.org/W3195378132","doi":"https://doi.org/10.3390/e23081043","mag":"3195378132","pmid":"https://pubmed.ncbi.nlm.nih.gov/34441184"},"language":"en","primary_location":{"id":"doi:10.3390/e23081043","is_oa":true,"landing_page_url":"https://doi.org/10.3390/e23081043","pdf_url":"https://www.mdpi.com/1099-4300/23/8/1043/pdf","source":{"id":"https://openalex.org/S195231649","display_name":"Entropy","issn_l":"1099-4300","issn":["1099-4300"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Entropy","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/1099-4300/23/8/1043/pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5016262505","display_name":"Zijian Gao","orcid":"https://orcid.org/0000-0001-5151-3381"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zijian Gao","raw_affiliation_strings":["College of Computer, National University of Defense Technology, Changsha 410000, China"],"affiliations":[{"raw_affiliation_string":"College of Computer, National University of Defense Technology, Changsha 410000, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013340793","display_name":"Kele Xu","orcid":"https://orcid.org/0000-0001-5997-5169"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Kele Xu","raw_affiliation_strings":["College of Computer, National University of Defense Technology, Changsha 410000, China"],"affiliations":[{"raw_affiliation_string":"College of Computer, National University of Defense Technology, Changsha 410000, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088885490","display_name":"Bo Ding","orcid":"https://orcid.org/0000-0002-1236-8318"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Ding","raw_affiliation_strings":["College of Computer, National University of Defense Technology, Changsha 410000, China"],"affiliations":[{"raw_affiliation_string":"College of Computer, National University of Defense Technology, Changsha 410000, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101522100","display_name":"Huaimin Wang","orcid":"https://orcid.org/0000-0002-3245-1901"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huaimin Wang","raw_affiliation_strings":["College of Computer, National University of Defense Technology, Changsha 410000, China"],"affiliations":[{"raw_affiliation_string":"College of Computer, National University of Defense Technology, Changsha 410000, China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5013340793"],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":{"value":2000,"currency":"CHF","value_usd":2165},"apc_paid":{"value":2000,"currency":"CHF","value_usd":2165},"fwci":1.5396,"has_fulltext":true,"cited_by_count":16,"citation_normalized_percentile":{"value":0.86103826,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"23","issue":"8","first_page":"1043","last_page":"1043"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9940999746322632,"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":0.9853000044822693,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.818520724773407},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7729908227920532},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.6640666723251343},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6328043937683105},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4423221945762634},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.37881025671958923},{"id":"https://openalex.org/keywords/knowledge-management","display_name":"Knowledge management","score":0.3260446786880493},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1296946108341217},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.06784951686859131},{"id":"https://openalex.org/keywords/waste-management","display_name":"Waste management","score":0.06579092144966125},{"id":"https://openalex.org/keywords/chromatography","display_name":"Chromatography","score":0.04989200830459595}],"concepts":[{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.818520724773407},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7729908227920532},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.6640666723251343},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6328043937683105},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4423221945762634},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37881025671958923},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.3260446786880493},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1296946108341217},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.06784951686859131},{"id":"https://openalex.org/C548081761","wikidata":"https://www.wikidata.org/wiki/Q180388","display_name":"Waste management","level":1,"score":0.06579092144966125},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.04989200830459595}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.3390/e23081043","is_oa":true,"landing_page_url":"https://doi.org/10.3390/e23081043","pdf_url":"https://www.mdpi.com/1099-4300/23/8/1043/pdf","source":{"id":"https://openalex.org/S195231649","display_name":"Entropy","issn_l":"1099-4300","issn":["1099-4300"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Entropy","raw_type":"journal-article"},{"id":"pmid:34441184","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/34441184","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":"Entropy (Basel, Switzerland)","raw_type":null},{"id":"pmh:oai:arXiv.org:2103.14891","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2103.14891","pdf_url":"https://arxiv.org/pdf/2103.14891","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},{"id":"pmh:oai:doaj.org/article:2a6df7a8341741e8bfd51485f6b67aef","is_oa":true,"landing_page_url":"https://doaj.org/article/2a6df7a8341741e8bfd51485f6b67aef","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Entropy, Vol 23, Iss 8, p 1043 (2021)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/1099-4300/23/8/1043/","is_oa":true,"landing_page_url":"https://dx.doi.org/10.3390/e23081043","pdf_url":null,"source":{"id":"https://openalex.org/S4306400947","display_name":"MDPI (MDPI AG)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210097602","host_organization_name":"Multidisciplinary Digital Publishing Institute (Switzerland)","host_organization_lineage":["https://openalex.org/I4210097602"],"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":"Entropy; Volume 23; Issue 8; Pages: 1043","raw_type":"Text"},{"id":"pmh:oai:pubmedcentral.nih.gov:8393270","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/8393270","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Entropy (Basel)","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/e23081043","is_oa":true,"landing_page_url":"https://doi.org/10.3390/e23081043","pdf_url":"https://www.mdpi.com/1099-4300/23/8/1043/pdf","source":{"id":"https://openalex.org/S195231649","display_name":"Entropy","issn_l":"1099-4300","issn":["1099-4300"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Entropy","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3500858790","display_name":null,"funder_award_id":"61751208","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5069775644","display_name":null,"funder_award_id":"6175120","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5939423041","display_name":null,"funder_award_id":"Technology","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","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":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3195378132.pdf","grobid_xml":"https://content.openalex.org/works/W3195378132.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1641379095","https://openalex.org/W1990320219","https://openalex.org/W2020573190","https://openalex.org/W2097381042","https://openalex.org/W2131600418","https://openalex.org/W2139982068","https://openalex.org/W2145339207","https://openalex.org/W2165698076","https://openalex.org/W2294370754","https://openalex.org/W2395579298","https://openalex.org/W2623431351","https://openalex.org/W2769567824","https://openalex.org/W2787259794","https://openalex.org/W2890332809","https://openalex.org/W2894976951","https://openalex.org/W2921955147","https://openalex.org/W2982316857","https://openalex.org/W2987046690","https://openalex.org/W2993562816","https://openalex.org/W3003498399","https://openalex.org/W3034225898","https://openalex.org/W3099134564","https://openalex.org/W6674600207","https://openalex.org/W6683195989","https://openalex.org/W6705225276"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2384475851","https://openalex.org/W2000444236","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W3084456289","https://openalex.org/W2353602216","https://openalex.org/W2024136090","https://openalex.org/W4391331176"],"abstract_inverted_index":{"Recently,":[0],"deep":[1],"reinforcement":[2,84],"learning":[3,85],"(RL)":[4],"algorithms":[5,87,135],"have":[6],"achieved":[7],"significant":[8],"progress":[9],"in":[10,40,52,79,136],"the":[11,80,95,106,114,122,155,161,165,168],"multi-agent":[12,83],"domain.":[13],"However,":[14],"training":[15,107,156,162],"for":[16,69,109,172],"increasingly":[17],"complex":[18],"tasks":[19,111],"would":[20],"be":[21,76],"time-consuming":[22],"and":[23,124,138,150],"resource":[24],"intensive.":[25],"To":[26,119],"alleviate":[27],"this":[28,50,63],"problem,":[29],"efficient":[30],"leveraging":[31],"of":[32,82,117,126,167],"historical":[33],"experience":[34],"is":[35,38],"essential,":[36],"which":[37,74],"under-explored":[39],"previous":[41],"studies":[42],"because":[43],"most":[44],"existing":[45],"methods":[46,149],"fail":[47],"to":[48,58,99,104],"achieve":[49],"goal":[51],"a":[53,67],"continuously":[54],"dynamic":[55],"system":[56],"owing":[57],"their":[59],"complicated":[60,90],"design.":[61,92],"In":[62],"paper,":[64],"we":[65,128],"propose":[66],"method":[68],"knowledge":[70,96,101,170],"reuse":[71,171],"called":[72],"\"KnowRU\",":[73],"can":[75],"easily":[77],"deployed":[78],"majority":[81],"(MARL)":[86],"without":[88],"requiring":[89],"hand-coded":[91],"We":[93],"employ":[94],"distillation":[97],"paradigm":[98],"transfer":[100],"among":[102],"agents":[103],"shorten":[105],"phase":[108],"new":[110],"while":[112],"improving":[113],"asymptotic":[115],"performance":[116],"agents.":[118],"empirically":[120],"demonstrate":[121],"robustness":[123],"effectiveness":[125],"KnowRU,":[127],"perform":[129],"extensive":[130],"experiments":[131],"on":[132],"state-of-the-art":[133],"MARL":[134],"collaborative":[137],"competitive":[139],"scenarios.":[140],"The":[141],"results":[142],"show":[143],"that":[144],"KnowRU":[145],"outperforms":[146],"recently":[147],"reported":[148],"not":[151],"only":[152],"successfully":[153],"accelerates":[154],"phase,":[157],"but":[158],"also":[159],"improves":[160],"performance,":[163],"emphasizing":[164],"importance":[166],"proposed":[169],"MARL.":[173]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}
