{"id":"https://openalex.org/W4306317385","doi":"https://doi.org/10.1145/3511808.3557292","title":"Diverse Effective Relationship Exploration for Cooperative Multi-Agent Reinforcement Learning","display_name":"Diverse Effective Relationship Exploration for Cooperative Multi-Agent Reinforcement Learning","publication_year":2022,"publication_date":"2022-10-16","ids":{"openalex":"https://openalex.org/W4306317385","doi":"https://doi.org/10.1145/3511808.3557292"},"language":"en","primary_location":{"id":"doi:10.1145/3511808.3557292","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3511808.3557292","pdf_url":null,"source":{"id":"https://openalex.org/S4363608762","display_name":"Proceedings of the 31st ACM International Conference on Information & Knowledge Management","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":"Proceedings of the 31st ACM International Conference on Information & Knowledge Management","raw_type":"proceedings-article"},"type":"conference-paper","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/A5101763478","display_name":"Hao Jiang","orcid":"https://orcid.org/0000-0002-8304-3692"},"institutions":[{"id":"https://openalex.org/I4210158522","display_name":"PLA Academy of Military Science","ror":"https://ror.org/05ct4s596","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210158522"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Jiang","raw_affiliation_strings":["Academy of Military Science, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Academy of Military Science, Beijing, China","institution_ids":["https://openalex.org/I4210158522"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100657633","display_name":"Yuntao Liu","orcid":"https://orcid.org/0000-0001-8213-582X"},"institutions":[{"id":"https://openalex.org/I4210158522","display_name":"PLA Academy of Military Science","ror":"https://ror.org/05ct4s596","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210158522"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuntao Liu","raw_affiliation_strings":["Academy of Military Science, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Academy of Military Science, Beijing, China","institution_ids":["https://openalex.org/I4210158522"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000067683","display_name":"Shengze Li","orcid":"https://orcid.org/0000-0003-2160-8675"},"institutions":[{"id":"https://openalex.org/I4210158522","display_name":"PLA Academy of Military Science","ror":"https://ror.org/05ct4s596","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210158522"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengze Li","raw_affiliation_strings":["Academy of Military Science, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Academy of Military Science, Beijing, China","institution_ids":["https://openalex.org/I4210158522"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101741623","display_name":"Jieyuan Zhang","orcid":"https://orcid.org/0000-0003-2100-1312"},"institutions":[{"id":"https://openalex.org/I4210158522","display_name":"PLA Academy of Military Science","ror":"https://ror.org/05ct4s596","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210158522"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jieyuan Zhang","raw_affiliation_strings":["Academy of Military Science, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Academy of Military Science, Beijing, China","institution_ids":["https://openalex.org/I4210158522"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101775095","display_name":"Xinhai Xu","orcid":"https://orcid.org/0009-0000-4202-9627"},"institutions":[{"id":"https://openalex.org/I4210158522","display_name":"PLA Academy of Military Science","ror":"https://ror.org/05ct4s596","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210158522"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinhai Xu","raw_affiliation_strings":["Academy of Military Science, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Academy of Military Science, Beijing, China","institution_ids":["https://openalex.org/I4210158522"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102012605","display_name":"Donghong Liu","orcid":"https://orcid.org/0000-0001-7529-2253"},"institutions":[{"id":"https://openalex.org/I4210158522","display_name":"PLA Academy of Military Science","ror":"https://ror.org/05ct4s596","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210158522"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Donghong Liu","raw_affiliation_strings":["Academy of Military Science, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Academy of Military Science, Beijing, China","institution_ids":["https://openalex.org/I4210158522"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210158522"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"842","last_page":"851"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9922999739646912,"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":0.9922999739646912,"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/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.9555000066757202,"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"}},{"id":"https://openalex.org/T11674","display_name":"Sports Analytics and Performance","score":0.9401999711990356,"subfield":{"id":"https://openalex.org/subfields/2002","display_name":"Economics and Econometrics"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8875879645347595},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7181652784347534},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5587098002433777},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4866846203804016},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4528326988220215},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4322658181190491},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.32619768381118774},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10560953617095947}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8875879645347595},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7181652784347534},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5587098002433777},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4866846203804016},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4528326988220215},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4322658181190491},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.32619768381118774},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10560953617095947},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3511808.3557292","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3511808.3557292","pdf_url":null,"source":{"id":"https://openalex.org/S4363608762","display_name":"Proceedings of the 31st ACM International Conference on Information & Knowledge Management","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":"Proceedings of the 31st ACM International Conference on Information & Knowledge Management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W265467607","https://openalex.org/W2116966230","https://openalex.org/W2617547828","https://openalex.org/W2747213132","https://openalex.org/W2806824292","https://openalex.org/W2904455790","https://openalex.org/W2904675649","https://openalex.org/W2912222576","https://openalex.org/W3101552411","https://openalex.org/W3174032342","https://openalex.org/W4212774754"],"related_works":["https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2145821588","https://openalex.org/W2086122291","https://openalex.org/W1987513656"],"abstract_inverted_index":{"In":[0],"some":[1,23],"complex":[2],"multi-agent":[3,52],"environments,":[4],"the":[5,18,42,73,93],"types":[6],"of":[7,24,75],"relationships":[8,26,35,67],"between":[9,68],"agents":[10,98],"are":[11],"diverse":[12,47],"and":[13,123],"their":[14],"intensity":[15],"changes":[16],"during":[17],"policy":[19,30],"learning":[20,54],"process.":[21],"Theoretically,":[22],"these":[25,34],"can":[27],"facilitate":[28],"cooperative":[29],"learning.":[31],"However,":[32],"acquiring":[33],"is":[36,62,89],"an":[37,80,85],"intractable":[38],"problem.":[39],"To":[40],"tackle":[41],"problem,":[43],"we":[44,78],"propose":[45],"a":[46,58],"effective":[48,76,102],"relationship":[49],"exploration":[50,74],"based":[51],"reinforcement":[53],"(DERE)":[55],"method.":[56],"Specifically,":[57],"potential":[59],"fields":[60],"model":[61],"firstly":[63],"designed":[64,90],"to":[65,71,91,99],"represent":[66],"agents.":[69],"Then":[70],"encourage":[72],"relationships,":[77],"define":[79],"information-theoretic":[81,94],"objective":[82],"function.":[83],"Finally,":[84],"intrinsic":[86],"reward":[87],"function":[88],"optimize":[92],"objective,":[95],"meanwhile,":[96],"guide":[97],"learn":[100],"more":[101],"collaborative":[103],"policies.":[104],"Experimental":[105],"results":[106],"show":[107],"that":[108],"our":[109],"method":[110],"outperforms":[111],"state-of-the-art":[112],"methods":[113],"on":[114],"both":[115],"super":[116],"hard":[117],"StarCraft":[118],"II":[119],"micromanagement":[120],"tasks":[121],"(SMAC)":[122],"Google":[124],"Research":[125],"Football":[126],"(GRF).":[127]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}