{"id":"https://openalex.org/W4225307256","doi":"https://doi.org/10.1109/icassp43922.2022.9747852","title":"Qrelation: an Agent Relation-Based Approach for Multi-Agent Reinforcement Learning Value Function Factorization","display_name":"Qrelation: an Agent Relation-Based Approach for Multi-Agent Reinforcement Learning Value Function Factorization","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4225307256","doi":"https://doi.org/10.1109/icassp43922.2022.9747852"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747852","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747852","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-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/A5035174613","display_name":"Siqi Shen","orcid":"https://orcid.org/0000-0001-7479-0189"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Siqi Shen","raw_affiliation_strings":["Xiamen University,Fujian Key Lab of Sensing and Computing for Smart Cities, School of Informatics,China","Fujian Key Lab of Sensing and Computing for Smart Cities, School of Informatics, Xiamen University, China"],"affiliations":[{"raw_affiliation_string":"Xiamen University,Fujian Key Lab of Sensing and Computing for Smart Cities, School of Informatics,China","institution_ids":["https://openalex.org/I191208505"]},{"raw_affiliation_string":"Fujian Key Lab of Sensing and Computing for Smart Cities, School of Informatics, Xiamen University, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100362109","display_name":"Jun Liu","orcid":"https://orcid.org/0000-0003-4007-6109"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Liu","raw_affiliation_strings":["Xiamen University,Fujian Key Lab of Sensing and Computing for Smart Cities, School of Informatics,China","Fujian Key Lab of Sensing and Computing for Smart Cities, School of Informatics, Xiamen University, China"],"affiliations":[{"raw_affiliation_string":"Xiamen University,Fujian Key Lab of Sensing and Computing for Smart Cities, School of Informatics,China","institution_ids":["https://openalex.org/I191208505"]},{"raw_affiliation_string":"Fujian Key Lab of Sensing and Computing for Smart Cities, School of Informatics, Xiamen University, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065055295","display_name":"Mengwei Qiu","orcid":null},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mengwei Qiu","raw_affiliation_strings":["Xiamen University,Fujian Key Lab of Sensing and Computing for Smart Cities, School of Informatics,China","Fujian Key Lab of Sensing and Computing for Smart Cities, School of Informatics, Xiamen University, China"],"affiliations":[{"raw_affiliation_string":"Xiamen University,Fujian Key Lab of Sensing and Computing for Smart Cities, School of Informatics,China","institution_ids":["https://openalex.org/I191208505"]},{"raw_affiliation_string":"Fujian Key Lab of Sensing and Computing for Smart Cities, School of Informatics, Xiamen University, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066301734","display_name":"Weiquan Liu","orcid":"https://orcid.org/0000-0002-5934-1139"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weiquan Liu","raw_affiliation_strings":["Xiamen University,Fujian Key Lab of Sensing and Computing for Smart Cities, School of Informatics,China","Fujian Key Lab of Sensing and Computing for Smart Cities, School of Informatics, Xiamen University, China"],"affiliations":[{"raw_affiliation_string":"Xiamen University,Fujian Key Lab of Sensing and Computing for Smart Cities, School of Informatics,China","institution_ids":["https://openalex.org/I191208505"]},{"raw_affiliation_string":"Fujian Key Lab of Sensing and Computing for Smart Cities, School of Informatics, Xiamen University, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100416961","display_name":"Cheng Wang","orcid":"https://orcid.org/0000-0001-6075-796X"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cheng Wang","raw_affiliation_strings":["Xiamen University,Fujian Key Lab of Sensing and Computing for Smart Cities, School of Informatics,China","Fujian Key Lab of Sensing and Computing for Smart Cities, School of Informatics, Xiamen University, China"],"affiliations":[{"raw_affiliation_string":"Xiamen University,Fujian Key Lab of Sensing and Computing for Smart Cities, School of Informatics,China","institution_ids":["https://openalex.org/I191208505"]},{"raw_affiliation_string":"Fujian Key Lab of Sensing and Computing for Smart Cities, School of Informatics, Xiamen University, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003730869","display_name":"Yongquan Fu","orcid":"https://orcid.org/0000-0002-7564-5239"},"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":"Yongquan Fu","raw_affiliation_strings":["National University of Defense Technology,Parallel and Distributed Processing Laboratory,China","Parallel and Distributed Processing Laboratory, National University of Defense Technology, China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,Parallel and Distributed Processing Laboratory,China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"Parallel and Distributed Processing Laboratory, National University of Defense Technology, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101913669","display_name":"Qinglin Wang","orcid":"https://orcid.org/0000-0002-8286-6566"},"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":"Qinglin Wang","raw_affiliation_strings":["National University of Defense Technology,Parallel and Distributed Processing Laboratory,China","Parallel and Distributed Processing Laboratory, National University of Defense Technology, China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,Parallel and Distributed Processing Laboratory,China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"Parallel and Distributed Processing Laboratory, National University of Defense Technology, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058476148","display_name":"Peng Qiao","orcid":"https://orcid.org/0000-0001-6752-7892"},"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":"Peng Qiao","raw_affiliation_strings":["National University of Defense Technology,Parallel and Distributed Processing Laboratory,China","Parallel and Distributed Processing Laboratory, National University of Defense Technology, China"],"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,Parallel and Distributed Processing Laboratory,China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"Parallel and Distributed Processing Laboratory, National University of Defense Technology, China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5035174613"],"corresponding_institution_ids":["https://openalex.org/I191208505"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02289377,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4108","last_page":"4112"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9995999932289124,"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":0.9995999932289124,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.957099974155426,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.9521999955177307,"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":0.8712787628173828},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7615982294082642},{"id":"https://openalex.org/keywords/factorization","display_name":"Factorization","score":0.5821268558502197},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5228272676467896},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.512475311756134},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.505847692489624},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47637149691581726},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4569767415523529},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.45348307490348816},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.4263143539428711},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.38184088468551636},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3035535514354706},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.27852368354797363},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.14563539624214172},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.14076051115989685},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10994729399681091}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8712787628173828},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7615982294082642},{"id":"https://openalex.org/C187834632","wikidata":"https://www.wikidata.org/wiki/Q188804","display_name":"Factorization","level":2,"score":0.5821268558502197},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5228272676467896},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.512475311756134},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.505847692489624},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47637149691581726},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4569767415523529},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.45348307490348816},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.4263143539428711},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.38184088468551636},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3035535514354706},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.27852368354797363},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.14563539624214172},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.14076051115989685},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10994729399681091},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747852","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747852","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.49000000953674316}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W2012812921","https://openalex.org/W2166533447","https://openalex.org/W2396783599","https://openalex.org/W2604314403","https://openalex.org/W2617547828","https://openalex.org/W2747213132","https://openalex.org/W2807741983","https://openalex.org/W2894976951","https://openalex.org/W2895865957","https://openalex.org/W2949963774","https://openalex.org/W2951896791","https://openalex.org/W2964199361","https://openalex.org/W2979284752","https://openalex.org/W2995937146","https://openalex.org/W3004640943","https://openalex.org/W3044976552","https://openalex.org/W3046288222","https://openalex.org/W3091970450","https://openalex.org/W3133438440","https://openalex.org/W3162388386","https://openalex.org/W4287755265","https://openalex.org/W4288594419","https://openalex.org/W4295598622","https://openalex.org/W4297733535","https://openalex.org/W6653736999","https://openalex.org/W6712348848","https://openalex.org/W6735632219","https://openalex.org/W6736572398","https://openalex.org/W6745537798","https://openalex.org/W6749304979","https://openalex.org/W6752380930","https://openalex.org/W6755069753","https://openalex.org/W6758846586","https://openalex.org/W6762491519","https://openalex.org/W6768539364","https://openalex.org/W6773620346","https://openalex.org/W6780768476","https://openalex.org/W6781750019","https://openalex.org/W6783906689","https://openalex.org/W6784152626","https://openalex.org/W6791043475"],"related_works":["https://openalex.org/W4234874385","https://openalex.org/W4306904969","https://openalex.org/W2323648130","https://openalex.org/W2157140558","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W2386410636","https://openalex.org/W3038962357","https://openalex.org/W2025663273","https://openalex.org/W3099153698"],"abstract_inverted_index":{"The":[0],"Centralized":[1],"Training":[2],"with":[3,12],"Decentralized":[4],"Execution":[5],"paradigm":[6],"(CTDE),":[7],"which":[8,72],"trains":[9],"policies":[10],"centrally":[11],"additional":[13],"information,":[14],"is":[15,73],"important":[16],"for":[17,44,62,79],"Multi-Agent":[18],"Reinforcement":[19],"Learning":[20],"(MARL).":[21],"For":[22],"CTDE,":[23],"value":[24,37,42,80],"function":[25,38,81],"factorization":[26],"methods":[27,107],"make":[28],"use":[29],"of":[30],"state":[31],"during":[32],"training":[33],"and":[34,92],"factorize":[35],"the":[36,53,86],"into":[39],"multiple":[40],"local":[41],"functions":[43],"decentralized":[45],"execution.":[46],"These":[47],"approaches":[48],"do":[49],"not":[50],"fully":[51],"consider":[52],"relational":[54],"information":[55],"among":[56],"agents,":[57],"resulting":[58],"in":[59],"sub-optimal":[60],"models":[61],"complex":[63],"tasks.":[64],"To":[65],"remedy":[66],"this":[67],"issue,":[68],"we":[69],"propose":[70],"QRelation":[71,100],"a":[74],"graph":[75],"neural":[76],"network":[77],"approach":[78],"factorization.":[82],"It":[83],"considers":[84],"both":[85],"static":[87],"relations":[88,94],"(e.g.,":[89,95],"agent":[90],"types)":[91],"dynamic":[93],"close-by).":[96],"We":[97],"show":[98],"that":[99],"can":[101],"obtain":[102],"better":[103],"results":[104],"than":[105],"state-of-the-art":[106],"on":[108],"challenging":[109],"StarCraft":[110],"II":[111],"benchmarks.":[112]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}