{"id":"https://openalex.org/W4220889482","doi":"https://doi.org/10.3390/e24040470","title":"Knowledge Reuse of Multi-Agent Reinforcement Learning in Cooperative Tasks","display_name":"Knowledge Reuse of Multi-Agent Reinforcement Learning in Cooperative Tasks","publication_year":2022,"publication_date":"2022-03-28","ids":{"openalex":"https://openalex.org/W4220889482","doi":"https://doi.org/10.3390/e24040470","pmid":"https://pubmed.ncbi.nlm.nih.gov/35455134"},"language":"en","primary_location":{"id":"doi:10.3390/e24040470","is_oa":true,"landing_page_url":"https://doi.org/10.3390/e24040470","pdf_url":"https://www.mdpi.com/1099-4300/24/4/470/pdf?version=1648708627","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":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/1099-4300/24/4/470/pdf?version=1648708627","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5012434681","display_name":"Daming Shi","orcid":"https://orcid.org/0000-0001-8327-555X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Daming Shi","raw_affiliation_strings":["Department of Automation, Tsinghua University, Beijing 100084, China"],"affiliations":[{"raw_affiliation_string":"Department of Automation, Tsinghua University, Beijing 100084, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078280733","display_name":"Junbo Tong","orcid":"https://orcid.org/0000-0002-7433-0788"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junbo Tong","raw_affiliation_strings":["Department of Automation, Tsinghua University, Beijing 100084, China"],"affiliations":[{"raw_affiliation_string":"Department of Automation, Tsinghua University, Beijing 100084, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100330660","display_name":"Yi Liu","orcid":"https://orcid.org/0009-0001-4797-7826"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Liu","raw_affiliation_strings":["Department of Automation, Tsinghua University, Beijing 100084, China"],"affiliations":[{"raw_affiliation_string":"Department of Automation, Tsinghua University, Beijing 100084, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100693811","display_name":"Wenhui Fan","orcid":"https://orcid.org/0000-0002-0040-5759"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenhui Fan","raw_affiliation_strings":["Department of Automation, Tsinghua University, Beijing 100084, China"],"affiliations":[{"raw_affiliation_string":"Department of Automation, Tsinghua University, Beijing 100084, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5012434681"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":{"value":2000,"currency":"CHF","value_usd":2165},"apc_paid":{"value":2000,"currency":"CHF","value_usd":2165},"fwci":0.6947,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.74269602,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"24","issue":"4","first_page":"470","last_page":"470"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9991000294685364,"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":0.9991000294685364,"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/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9890000224113464,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.9670000076293945,"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":0.8307210206985474},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8010381460189819},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7760428190231323},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.625800371170044},{"id":"https://openalex.org/keywords/scratch","display_name":"Scratch","score":0.5648295283317566},{"id":"https://openalex.org/keywords/homogeneous","display_name":"Homogeneous","score":0.4323367476463318},{"id":"https://openalex.org/keywords/knowledge-sharing","display_name":"Knowledge sharing","score":0.42658400535583496},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41581499576568604},{"id":"https://openalex.org/keywords/knowledge-management","display_name":"Knowledge management","score":0.38232970237731934},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3519635796546936},{"id":"https://openalex.org/keywords/systems-engineering","display_name":"Systems engineering","score":0.12651541829109192},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10588684678077698}],"concepts":[{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.8307210206985474},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8010381460189819},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7760428190231323},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.625800371170044},{"id":"https://openalex.org/C2781235140","wikidata":"https://www.wikidata.org/wiki/Q275131","display_name":"Scratch","level":2,"score":0.5648295283317566},{"id":"https://openalex.org/C66882249","wikidata":"https://www.wikidata.org/wiki/Q169336","display_name":"Homogeneous","level":2,"score":0.4323367476463318},{"id":"https://openalex.org/C2776604539","wikidata":"https://www.wikidata.org/wiki/Q6423395","display_name":"Knowledge sharing","level":2,"score":0.42658400535583496},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41581499576568604},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.38232970237731934},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3519635796546936},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.12651541829109192},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10588684678077698},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C548081761","wikidata":"https://www.wikidata.org/wiki/Q180388","display_name":"Waste management","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":5,"locations":[{"id":"doi:10.3390/e24040470","is_oa":true,"landing_page_url":"https://doi.org/10.3390/e24040470","pdf_url":"https://www.mdpi.com/1099-4300/24/4/470/pdf?version=1648708627","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:35455134","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/35455134","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:doaj.org/article:2a28b778e9bd4939b54ba001cd5e3271","is_oa":true,"landing_page_url":"https://doaj.org/article/2a28b778e9bd4939b54ba001cd5e3271","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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Entropy, Vol 24, Iss 4, p 470 (2022)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/1099-4300/24/4/470/","is_oa":true,"landing_page_url":"https://dx.doi.org/10.3390/e24040470","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 24; Issue 4; Pages: 470","raw_type":"Text"},{"id":"pmh:oai:pubmedcentral.nih.gov:9025018","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/9025018","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/e24040470","is_oa":true,"landing_page_url":"https://doi.org/10.3390/e24040470","pdf_url":"https://www.mdpi.com/1099-4300/24/4/470/pdf?version=1648708627","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":[{"display_name":"Partnerships for the goals","score":0.5,"id":"https://metadata.un.org/sdg/17"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4220889482.pdf","grobid_xml":"https://content.openalex.org/works/W4220889482.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W1529399279","https://openalex.org/W1560074431","https://openalex.org/W1641379095","https://openalex.org/W1973039793","https://openalex.org/W2099618002","https://openalex.org/W2106025020","https://openalex.org/W2127350252","https://openalex.org/W2139993574","https://openalex.org/W2145339207","https://openalex.org/W2147492008","https://openalex.org/W2160643434","https://openalex.org/W2388350909","https://openalex.org/W2585821313","https://openalex.org/W2604355867","https://openalex.org/W2604873668","https://openalex.org/W2984647659","https://openalex.org/W2997536466","https://openalex.org/W2999963940","https://openalex.org/W3029065915","https://openalex.org/W3046841642","https://openalex.org/W3108171015","https://openalex.org/W3109234674","https://openalex.org/W3124799513","https://openalex.org/W3130418699","https://openalex.org/W3161730384","https://openalex.org/W4226171518","https://openalex.org/W6786145963"],"related_works":["https://openalex.org/W2475116013","https://openalex.org/W2066741154","https://openalex.org/W2770018148","https://openalex.org/W2358308169","https://openalex.org/W2385135707","https://openalex.org/W2140315382","https://openalex.org/W2059109728","https://openalex.org/W2082556335","https://openalex.org/W322691623","https://openalex.org/W2494989134"],"abstract_inverted_index":{"With":[0],"the":[1,25,35,83,90,107,114,130,141,146,151,155,158,175],"development":[2],"and":[3,62,64,98,137,144,167],"appliance":[4],"of":[5,24,39,48,87],"multi-agent":[6,8,31,65],"systems,":[7],"cooperation":[9],"is":[10,22],"becoming":[11],"an":[12],"important":[13],"problem":[14],"in":[15,45,51],"artificial":[16],"intelligence.":[17],"Multi-agent":[18],"reinforcement":[19,41],"learning":[20,42],"(MARL)":[21],"one":[23,91],"most":[26],"effective":[27],"methods":[28,43,86],"for":[29,53],"solving":[30],"cooperative":[32,54,164],"tasks.":[33],"However,":[34],"huge":[36],"sample":[37],"complexity":[38],"traditional":[40],"results":[44],"two":[46,79],"kinds":[47],"training":[49,68,104,142,171],"waste":[50,123],"MARL":[52],"tasks:":[55],"all":[56],"homogeneous":[57],"agents":[58,101],"are":[59],"trained":[60],"independently":[61],"repetitively,":[63],"systems":[66],"need":[67],"from":[69,154,184],"scratch":[70],"when":[71,124],"adding":[72,125],"a":[73,126,169],"new":[74,127],"teammate.":[75],"To":[76],"tackle":[77],"these":[78],"problems,":[80],"we":[81],"propose":[82],"knowledge":[84,122],"reuse":[85],"MARL.":[88],"On":[89,106],"hand,":[92,109],"this":[93,110],"paper":[94,111],"proposes":[95,112],"sharing":[96,135],"experience":[97,136],"policy":[99,138],"within":[100],"to":[102,120,161,177,182],"mitigate":[103],"waste.":[105],"other":[108],"reusing":[113],"policies":[115,153],"learned":[116,152],"by":[117],"original":[118],"teams":[119],"avoid":[121],"agent.":[128],"Experimentally,":[129],"Pursuit":[131],"task":[132],"demonstrates":[133],"how":[134],"can":[139,173],"accelerate":[140],"speed":[143],"enhance":[145],"performance":[147,180],"simultaneously.":[148],"Additionally,":[149],"transferring":[150],"N-agent":[156],"enables":[157],"(N+1)-agent":[159],"team":[160],"immediately":[162],"perform":[163],"tasks":[165],"successfully,":[166],"only":[168],"minor":[170],"resource":[172],"allow":[174],"multi-agents":[176],"reach":[178],"optimal":[179],"identical":[181],"that":[183],"scratch.":[185]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-04-02T15:55:50.835912","created_date":"2025-10-10T00:00:00"}