{"id":"https://openalex.org/W4321021411","doi":"https://doi.org/10.1109/jsyst.2023.3240768","title":"An Attentive Consensus Platform for Collaborative Reinforcement Learning Agents","display_name":"An Attentive Consensus Platform for Collaborative Reinforcement Learning Agents","publication_year":2023,"publication_date":"2023-02-16","ids":{"openalex":"https://openalex.org/W4321021411","doi":"https://doi.org/10.1109/jsyst.2023.3240768"},"language":"en","primary_location":{"id":"doi:10.1109/jsyst.2023.3240768","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jsyst.2023.3240768","pdf_url":null,"source":{"id":"https://openalex.org/S95999327","display_name":"IEEE Systems Journal","issn_l":"1932-8184","issn":["1932-8184","1937-9234","2373-7816"],"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 Systems Journal","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/A5066851929","display_name":"Maxwell Hwang","orcid":"https://orcid.org/0000-0002-9505-6263"},"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":true,"raw_author_name":"Maxwell Hwang","raw_affiliation_strings":["School of Microelectronics, Northwestern Polytechnical University, Xi’an, China"],"affiliations":[{"raw_affiliation_string":"School of Microelectronics, Northwestern Polytechnical University, Xi’an, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055362696","display_name":"Jin-Ling Lin","orcid":"https://orcid.org/0000-0002-5762-4557"},"institutions":[{"id":"https://openalex.org/I68348662","display_name":"Shih Hsin University","ror":"https://ror.org/03ynprv96","country_code":"TW","type":"education","lineage":["https://openalex.org/I68348662"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Jin-Ling Lin","raw_affiliation_strings":["Information Management, Shih Hsin University, Taipei, Taiwan"],"affiliations":[{"raw_affiliation_string":"Information Management, Shih Hsin University, Taipei, Taiwan","institution_ids":["https://openalex.org/I68348662"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091811499","display_name":"Shao-Wei Kao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shao-Wei Kao","raw_affiliation_strings":["a renowned high-tech electronics company, Hsinchu"],"affiliations":[{"raw_affiliation_string":"a renowned high-tech electronics company, Hsinchu","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5066851929"],"corresponding_institution_ids":["https://openalex.org/I17145004"],"apc_list":null,"apc_paid":null,"fwci":0.3497,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.62199344,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":"17","issue":"3","first_page":"3783","last_page":"3793"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994999766349792,"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":0.9994999766349792,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9785000085830688,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9710999727249146,"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":0.8039576411247253},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7479875087738037},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.5692437887191772},{"id":"https://openalex.org/keywords/collaborative-learning","display_name":"Collaborative learning","score":0.5401027202606201},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.5126694440841675},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5104633569717407},{"id":"https://openalex.org/keywords/train","display_name":"Train","score":0.5071065425872803},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.5054385662078857},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4962819218635559},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.485320508480072},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.4306224286556244},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.42756757140159607},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3701488971710205},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1717667579650879},{"id":"https://openalex.org/keywords/knowledge-management","display_name":"Knowledge management","score":0.14094951748847961},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.10934367775917053}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8039576411247253},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7479875087738037},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.5692437887191772},{"id":"https://openalex.org/C138020889","wikidata":"https://www.wikidata.org/wiki/Q2349659","display_name":"Collaborative learning","level":2,"score":0.5401027202606201},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5126694440841675},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5104633569717407},{"id":"https://openalex.org/C190839683","wikidata":"https://www.wikidata.org/wiki/Q2448197","display_name":"Train","level":2,"score":0.5071065425872803},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.5054385662078857},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4962819218635559},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.485320508480072},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.4306224286556244},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.42756757140159607},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3701488971710205},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1717667579650879},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.14094951748847961},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.10934367775917053},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/jsyst.2023.3240768","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jsyst.2023.3240768","pdf_url":null,"source":{"id":"https://openalex.org/S95999327","display_name":"IEEE Systems Journal","issn_l":"1932-8184","issn":["1932-8184","1937-9234","2373-7816"],"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 Systems Journal","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W206679605","https://openalex.org/W2107544712","https://openalex.org/W2119717200","https://openalex.org/W2122277562","https://openalex.org/W2141399712","https://openalex.org/W2145339207","https://openalex.org/W2257979135","https://openalex.org/W2335723117","https://openalex.org/W2520432673","https://openalex.org/W2602275733","https://openalex.org/W2617547828","https://openalex.org/W2768629321","https://openalex.org/W2771807014","https://openalex.org/W2803155336","https://openalex.org/W2963658727","https://openalex.org/W3042654266","https://openalex.org/W3175552386","https://openalex.org/W3208624098","https://openalex.org/W6630875275","https://openalex.org/W6639478124","https://openalex.org/W6680834391","https://openalex.org/W6682137061","https://openalex.org/W6683204974","https://openalex.org/W6684205842","https://openalex.org/W6713411898","https://openalex.org/W6738796088","https://openalex.org/W6739901393","https://openalex.org/W6746042458","https://openalex.org/W6751139674","https://openalex.org/W6752380930","https://openalex.org/W6761837902","https://openalex.org/W6779450612"],"related_works":["https://openalex.org/W618248309","https://openalex.org/W2377336366","https://openalex.org/W1568097102","https://openalex.org/W1601203902","https://openalex.org/W2075798043","https://openalex.org/W4390419160","https://openalex.org/W4225671779","https://openalex.org/W2102464536","https://openalex.org/W2361332776","https://openalex.org/W2248934910"],"abstract_inverted_index":{"This":[0],"work":[1],"integrates":[2,102],"concurrent":[3,98],"team":[4,41],"learning":[5,10],"into":[6],"a":[7,18,109,140,183],"deep":[8],"reinforcement":[9],"model":[11,121,181],"for":[12,97,150,188],"collaborative":[13,46,60,73,120,186],"multiagent":[14,189],"problems":[15],"to":[16,25,37,87,118,122,133],"reach":[17],"common":[19],"goal.":[20],"RL":[21],"trains":[22],"each":[23],"agent":[24,49,96,148],"decide":[26],"its":[27],"best":[28],"actions,":[29],"and":[30,52,80,157],"then":[31],"the":[32,39,45,54,63,119,124,135,168,171,179,192],"joint":[33,136],"decision":[34,64,137],"is":[35,85,116],"made":[36],"accomplish":[38],"assigned":[40],"task":[42],"based":[43,65],"on":[44,66,146],"platform.":[47],"Each":[48],"learns":[50],"individually":[51],"shares":[53],"observed":[55],"feature":[56],"with":[57],"others.":[58],"The":[59,72,82,100,174],"platform":[61,74,101],"makes":[62],"these":[67],"features":[68,91],"provided":[69],"by":[70,93],"agents.":[71],"consists":[75],"of":[76,126,139,143,162,170],"two":[77],"attention":[78,111],"mechanisms\u2014soft":[79],"self-attention.":[81],"self-attention":[83],"module":[84],"applied":[86],"distinguish":[88],"local":[89],"environmental":[90],"sensed":[92],"an":[94],"individual":[95],"learning.":[99],"collective":[103],"information":[104,132],"locally":[105],"from":[106],"agents":[107],"through":[108],"soft":[110],"interface.":[112],"A":[113],"termination":[114],"network":[115],"introduced":[117],"determine":[123],"number":[125,142],"elapsed":[127],"sequences":[128],"in":[129],"collecting":[130],"sufficient":[131],"support":[134],"instead":[138],"fixed":[141],"iterations.":[144],"Experiments":[145],"limit-sighted":[147],"deployment":[149],"static":[151],"image":[152,159],"classifications,":[153],"video":[154],"game":[155],"playing,":[156],"aerial":[158],"object":[160],"detection":[161],"multiple":[163],"airborne":[164],"sensors":[165],"have":[166],"evaluated":[167],"performance":[169],"proposed":[172,180],"model.":[173],"experimental":[175],"results":[176],"show":[177],"that":[178],"provides":[182],"more":[184],"efficient":[185],"mechanism":[187],"systems":[190],"than":[191],"state-of-the-art":[193],"methods.":[194]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}