{"id":"https://openalex.org/W4394862935","doi":"https://doi.org/10.1109/lra.2024.3389813","title":"MARRGM: Learning Framework for Multi-Agent Reinforcement Learning via Reinforcement Recommendation and Group Modification","display_name":"MARRGM: Learning Framework for Multi-Agent Reinforcement Learning via Reinforcement Recommendation and Group Modification","publication_year":2024,"publication_date":"2024-04-16","ids":{"openalex":"https://openalex.org/W4394862935","doi":"https://doi.org/10.1109/lra.2024.3389813"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2024.3389813","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2024.3389813","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"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 Robotics and Automation Letters","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/A5029620144","display_name":"Peiliang Wu","orcid":"https://orcid.org/0000-0003-1228-2757"},"institutions":[{"id":"https://openalex.org/I39333907","display_name":"Yanshan University","ror":"https://ror.org/02txfnf15","country_code":"CN","type":"education","lineage":["https://openalex.org/I39333907"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peiliang Wu","raw_affiliation_strings":["School of Information Science and Engineering, Yanshan University, Qinhuangdao, China"],"raw_orcid":"https://orcid.org/0000-0003-1228-2757","affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Yanshan University, Qinhuangdao, China","institution_ids":["https://openalex.org/I39333907"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063763076","display_name":"Liqiang Tian","orcid":"https://orcid.org/0009-0004-8053-7859"},"institutions":[{"id":"https://openalex.org/I39333907","display_name":"Yanshan University","ror":"https://ror.org/02txfnf15","country_code":"CN","type":"education","lineage":["https://openalex.org/I39333907"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liqiang Tian","raw_affiliation_strings":["School of Information Science and Engineering, Yanshan University, Qinhuangdao, China"],"raw_orcid":"https://orcid.org/0009-0004-8053-7859","affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Yanshan University, Qinhuangdao, China","institution_ids":["https://openalex.org/I39333907"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100718811","display_name":"Qian Zhang","orcid":"https://orcid.org/0009-0004-2867-7512"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qian Zhang","raw_affiliation_strings":["College of software, Nankai University, TianJin, China"],"raw_orcid":"https://orcid.org/0009-0004-2867-7512","affiliations":[{"raw_affiliation_string":"College of software, Nankai University, TianJin, China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103275250","display_name":"Bingyi Mao","orcid":"https://orcid.org/0009-0008-6547-5150"},"institutions":[{"id":"https://openalex.org/I39333907","display_name":"Yanshan University","ror":"https://ror.org/02txfnf15","country_code":"CN","type":"education","lineage":["https://openalex.org/I39333907"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bingyi Mao","raw_affiliation_strings":["School of Information Science and Engineering, Yanshan University, Qinhuangdao, China"],"raw_orcid":"https://orcid.org/0009-0008-6547-5150","affiliations":[{"raw_affiliation_string":"School of Information Science and Engineering, Yanshan University, Qinhuangdao, China","institution_ids":["https://openalex.org/I39333907"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045361189","display_name":"Wenbai Chen","orcid":"https://orcid.org/0000-0001-7683-2776"},"institutions":[{"id":"https://openalex.org/I78675632","display_name":"Beijing Information Science & Technology University","ror":"https://ror.org/04xnqep60","country_code":"CN","type":"education","lineage":["https://openalex.org/I78675632"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenbai Chen","raw_affiliation_strings":["School of Automation, Beijing Information Science and Technology University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-7683-2776","affiliations":[{"raw_affiliation_string":"School of Automation, Beijing Information Science and Technology University, Beijing, China","institution_ids":["https://openalex.org/I78675632"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.8328,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.86869739,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"9","issue":"6","first_page":"5385","last_page":"5392"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9968000054359436,"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":0.9968000054359436,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9794999957084656,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.9656999707221985,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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":0.9001127481460571},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8011434674263},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.6573846340179443},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6321608424186707},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6165916323661804},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5534685254096985},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5451818704605103},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5259205102920532},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.49765661358833313},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.48631367087364197},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.43584054708480835},{"id":"https://openalex.org/keywords/recommender-system","display_name":"Recommender system","score":0.4107985198497772},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.09432610869407654},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09185272455215454}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9001127481460571},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8011434674263},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.6573846340179443},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6321608424186707},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6165916323661804},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5534685254096985},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5451818704605103},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5259205102920532},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.49765661358833313},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.48631367087364197},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.43584054708480835},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.4107985198497772},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.09432610869407654},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09185272455215454},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2024.3389813","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2024.3389813","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"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 Robotics and Automation Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1331161382","display_name":null,"funder_award_id":"U20A20167","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1484327127","display_name":null,"funder_award_id":"62276028","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G453775460","display_name":null,"funder_award_id":"F202103079","funder_id":"https://openalex.org/F4320322163","funder_display_name":"Natural Science Foundation of Hebei Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322163","display_name":"Natural Science Foundation of Hebei Province","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W3156844209","https://openalex.org/W3214951365","https://openalex.org/W4283582213","https://openalex.org/W4306666666","https://openalex.org/W4321350720","https://openalex.org/W4386599745","https://openalex.org/W4386952173","https://openalex.org/W4388286312","https://openalex.org/W4390638728","https://openalex.org/W6734678876","https://openalex.org/W6738796088","https://openalex.org/W6740801417","https://openalex.org/W6741408367","https://openalex.org/W6755069753","https://openalex.org/W6762491519","https://openalex.org/W6780404908","https://openalex.org/W6781750019","https://openalex.org/W6783196708","https://openalex.org/W6796991022","https://openalex.org/W6922480057"],"related_works":["https://openalex.org/W2383111961","https://openalex.org/W2365952365","https://openalex.org/W2352448290","https://openalex.org/W4390273403","https://openalex.org/W2380820513","https://openalex.org/W4386781444","https://openalex.org/W2913146933","https://openalex.org/W2372385138","https://openalex.org/W4296359239","https://openalex.org/W2101155126"],"abstract_inverted_index":{"Sample":[0],"usage":[1,249],"efficiency":[2,90,250],"is":[3,34],"an":[4],"important":[5],"factor":[6],"affecting":[7],"the":[8,30,56,63,68,92,96,100,111,120,133,136,141,144,152,157,163,167,171,176,181,189,197,220,232,238,242,256],"convergence":[9],"speed":[10],"of":[11,46,59,70,99,114,127,135,147,156,166,247,258],"multi-agent":[12,101,137],"deep":[13],"reinforcement":[14,81,153,190],"learning":[15,49,154],"(MADRL)":[16],"algorithms.":[17],"Most":[18],"existing":[19],"experience":[20,26,41,60,116,145],"replay":[21,64],"(ER)":[22],"methods":[23],"manually":[24],"select":[25],"samples":[27,42,61],"to":[28,36,53,86,94,123,170,174,179,219,223],"update":[29],"agent's":[31,177],"policy.":[32],"It":[33],"difficult":[35],"give":[37],"suitable":[38],"and":[39,83,91,150,187,192,212,215,251,260],"efficient":[40],"for":[43,255],"different":[44,104],"stages":[45],"agent":[47,168],"policy":[48,142,165],"as":[50,52],"well":[51],"effectively":[54],"mine":[55],"potential":[57],"value":[58],"in":[62,103,245],"buffer.":[65],"Inspired":[66],"by":[67],"idea":[69],"recommendation":[71,82,121,148,158,191],"systems,":[72],"this":[73,217],"paper":[74],"proposes":[75],"a":[76],"MADRL":[77,198,234],"framework":[78,218,240],"based":[79],"on":[80],"group":[84,172,193],"modification":[85,194],"improve":[87,175],"sample":[88,117,146,248],"use":[89,110],"ability":[93,178],"find":[95],"optimal":[97,182],"solution":[98],"system":[102,138],"task":[105,205],"scenario":[106],"categories.":[107,262],"First,":[108],"we":[109,131,161,202],"sampling":[112,125,149],"probability":[113],"each":[115],"output":[118],"from":[119],"network":[122],"recommend":[124],"instead":[126],"manual":[128],"sampling;":[129],"simultaneously,":[130],"collect":[132],"performance":[134],"after":[139],"updating":[140],"with":[143,204,237],"construct":[151],"process":[155],"network.":[159],"Next,":[160],"modify":[162],"individual":[164],"according":[169],"rewards":[173],"learn":[180],"solution.":[183],"We":[184],"then":[185],"combine":[186],"embed":[188],"modules":[195],"into":[196],"algorithm":[199,222,244],"MAAC.":[200],"Finally,":[201],"experiment":[203],"scenarios,":[206],"including":[207],"cooperative":[208],"collection,":[209],"command":[210],"movement,":[211],"target":[213],"navigation,":[214],"extend":[216],"MADDPG":[221],"verify":[224],"its":[225],"scalability.":[226],"The":[227],"experimental":[228],"results":[229],"show":[230],"that":[231],"off-policy":[233],"algorithms":[235],"combined":[236],"proposed":[239],"outperform":[241],"baseline":[243],"terms":[246],"have":[252],"better":[253],"universality":[254],"number":[257],"agents":[259],"scene":[261]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}