{"id":"https://openalex.org/W3109234674","doi":"https://doi.org/10.1145/3447268","title":"A Q-values Sharing Framework for Multi-agent Reinforcement Learning under Budget Constraint","display_name":"A Q-values Sharing Framework for Multi-agent Reinforcement Learning under Budget Constraint","publication_year":2020,"publication_date":"2020-06-30","ids":{"openalex":"https://openalex.org/W3109234674","doi":"https://doi.org/10.1145/3447268","mag":"3109234674"},"language":"en","primary_location":{"id":"doi:10.1145/3447268","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3447268","pdf_url":null,"source":{"id":"https://openalex.org/S16632050","display_name":"ACM Transactions on Autonomous and Adaptive Systems","issn_l":"1556-4665","issn":["1556-4665","1556-4703"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Autonomous and Adaptive Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2011.14281.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5053438680","display_name":"Changxi Zhu","orcid":"https://orcid.org/0000-0002-2910-5506"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changxi Zhu","raw_affiliation_strings":["School of Software Engineering, South China University of Technology, Guangdong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Software Engineering, South China University of Technology, Guangdong, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022683388","display_name":"Ho-fung Leung","orcid":"https://orcid.org/0000-0003-4914-2934"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Ho-Fung Leung","raw_affiliation_strings":["Department of Computer Science and Engineering, The Chinese University of Hong Kong and Department of Sociology, The Chinese University of Hong Kong, Hong Kong SAR, China","The Chinese University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Chinese University of Hong Kong and Department of Sociology, The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052387391","display_name":"Shuyue Hu","orcid":"https://orcid.org/0000-0002-1908-1344"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Shuyue Hu","raw_affiliation_strings":["Department of Computer Science, National University of Singapore, Singapore","National University of Singapore,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"National University of Singapore,","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089123257","display_name":"Yi Cai","orcid":"https://orcid.org/0000-0002-1767-789X"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Cai","raw_affiliation_strings":["School of Software Engineering, South China University of Technology and Key Laboratory of Big Data and Intelligent Robot (South China University of Technology), Ministry of Education, Guangzhou, Guangdong, China","South china university of technology)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Software Engineering, South China University of Technology and Key Laboratory of Big Data and Intelligent Robot (South China University of Technology), Ministry of Education, Guangzhou, Guangdong, China","institution_ids":["https://openalex.org/I90610280"]},{"raw_affiliation_string":"South china university of technology)","institution_ids":["https://openalex.org/I90610280"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4021,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.71869007,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"15","issue":"2","first_page":"1","last_page":"28"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994000196456909,"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":0.9994000196456909,"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/T11182","display_name":"Auction Theory and Applications","score":0.988099992275238,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9765999913215637,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8630699515342712},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7151072025299072},{"id":"https://openalex.org/keywords/budget-constraint","display_name":"Budget constraint","score":0.704952597618103},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.5805926322937012},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5366522669792175},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37513044476509094},{"id":"https://openalex.org/keywords/microeconomics","display_name":"Microeconomics","score":0.1550074815750122},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09812915325164795},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.08888235688209534}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8630699515342712},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7151072025299072},{"id":"https://openalex.org/C8505890","wikidata":"https://www.wikidata.org/wiki/Q605095","display_name":"Budget constraint","level":2,"score":0.704952597618103},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.5805926322937012},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5366522669792175},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37513044476509094},{"id":"https://openalex.org/C175444787","wikidata":"https://www.wikidata.org/wiki/Q39072","display_name":"Microeconomics","level":1,"score":0.1550074815750122},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09812915325164795},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.08888235688209534},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3447268","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3447268","pdf_url":null,"source":{"id":"https://openalex.org/S16632050","display_name":"ACM Transactions on Autonomous and Adaptive Systems","issn_l":"1556-4665","issn":["1556-4665","1556-4703"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Autonomous and Adaptive Systems","raw_type":"journal-article"},{"id":"mag:3109234674","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2011.14281.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2011.14281","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2011.14281","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"mag:3109234674","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2011.14281.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"arXiv (Cornell University)","raw_type":null},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8189774080","display_name":null,"funder_award_id":"62076100","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":false,"pdf":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1529399279","https://openalex.org/W1557517019","https://openalex.org/W1580572138","https://openalex.org/W1584580530","https://openalex.org/W1589064538","https://openalex.org/W1641379095","https://openalex.org/W2007933500","https://openalex.org/W2030520188","https://openalex.org/W2053241734","https://openalex.org/W2082607648","https://openalex.org/W2095989982","https://openalex.org/W2096145798","https://openalex.org/W2104602264","https://openalex.org/W2115211925","https://openalex.org/W2133040789","https://openalex.org/W2134269720","https://openalex.org/W2144366468","https://openalex.org/W2153427071","https://openalex.org/W2156578004","https://openalex.org/W2312609093","https://openalex.org/W2549225575","https://openalex.org/W2552300487","https://openalex.org/W2563829177","https://openalex.org/W2601465345","https://openalex.org/W2620645529","https://openalex.org/W2621262673","https://openalex.org/W2735506162","https://openalex.org/W2739573821","https://openalex.org/W2739657930","https://openalex.org/W2740912559","https://openalex.org/W2747213132","https://openalex.org/W2768629321","https://openalex.org/W2921596426","https://openalex.org/W2921955147","https://openalex.org/W2962747693","https://openalex.org/W2963259091","https://openalex.org/W2963390684","https://openalex.org/W2963939962","https://openalex.org/W2976108375","https://openalex.org/W2978894944","https://openalex.org/W3099324303"],"related_works":["https://openalex.org/W3156248677","https://openalex.org/W2775322888","https://openalex.org/W2353310609","https://openalex.org/W3477136","https://openalex.org/W2470978173","https://openalex.org/W2569013745","https://openalex.org/W3160136687","https://openalex.org/W2418374443","https://openalex.org/W3005746415","https://openalex.org/W3090197898","https://openalex.org/W2150202214","https://openalex.org/W2788984134","https://openalex.org/W2395943808","https://openalex.org/W2778197332","https://openalex.org/W2107552654","https://openalex.org/W141173203","https://openalex.org/W1968040064","https://openalex.org/W3094270515","https://openalex.org/W2946012239","https://openalex.org/W2047467754"],"abstract_inverted_index":{"In":[0,25,109],"a":[1,4,38,50,96],"teacher-student":[2],"framework,":[3],"more":[5],"experienced":[6],"agent":[7,15,163],"(teacher)":[8],"helps":[9],"accelerate":[10],"the":[11,55,65,137,154],"learning":[12,29,105,130],"of":[13,57,67,156],"another":[14,74],"(student)":[16],"by":[17,48],"suggesting":[18],"actions":[19,87,158],"to":[20,42,116],"take":[21],"in":[22,126],"certain":[23],"states.":[24],"cooperative":[26,102],"multi-agent":[27,129],"reinforcement":[28],"(MARL),":[30],"where":[31],"agents":[32,59,70,104],"must":[33],"cooperate":[34,43],"with":[35,45,72,106],"one":[36,73],"another,":[37],"student":[39],"could":[40,90],"fail":[41],"effectively":[44],"others":[46],"even":[47],"following":[49],"teacher\u2019s":[51],"suggested":[52],"actions,":[53],"as":[54,88],"policies":[56],"all":[58],"can":[60,113],"change":[61],"before":[62],"convergence.":[63],"When":[64],"number":[66],"times":[68],"that":[69,85,136],"communicate":[71],"is":[75],"limited":[76],"(i.e.,":[77],"there":[78],"are":[79],"budget":[80,107],"constraints),":[81],"an":[82],"advising":[83,98,143,157],"strategy":[84],"uses":[86],"advice":[89],"be":[91],"less":[92],"effective.":[93],"We":[94,123],"propose":[95],"partaker-sharer":[97],"framework":[99],"(PSAF)":[100],"for":[101,118],"MARL":[103],"constraints.":[108],"PSAF,":[110],"each":[111],"Q-learner":[112],"decide":[114],"when":[115],"ask":[117],"and":[119,148,159],"share":[120],"its":[121],"Q-values.":[122],"perform":[124],"experiments":[125],"three":[127],"typical":[128],"problems.":[131],"The":[132],"evaluation":[133],"results":[134],"indicate":[135],"proposed":[138],"PSAF":[139],"approach":[140],"outperforms":[141],"existing":[142],"methods":[144],"under":[145],"both":[146],"constrained":[147],"unconstrained":[149],"budgets.":[150],"Moreover,":[151],"we":[152],"analyse":[153],"influence":[155],"sharing":[160],"Q-values":[161],"on":[162],"learning.":[164]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-10T00:00:00"}