{"id":"https://openalex.org/W4408353617","doi":"https://doi.org/10.1109/icassp49660.2025.10887769","title":"Diverse Collaboration in Multi-Agent Reinforcement Learning via Self-Adaptive Method","display_name":"Diverse Collaboration in Multi-Agent Reinforcement Learning via Self-Adaptive Method","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408353617","doi":"https://doi.org/10.1109/icassp49660.2025.10887769"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10887769","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887769","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5101443264","display_name":"Xiang Xue","orcid":"https://orcid.org/0000-0003-2822-3188"},"institutions":[{"id":"https://openalex.org/I3923682","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I3923682"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiang Xue","raw_affiliation_strings":["Soochow University,School of Computer Science and Technology,Suzhou,P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Soochow University,School of Computer Science and Technology,Suzhou,P.R. China","institution_ids":["https://openalex.org/I3923682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072478964","display_name":"Quan Liu","orcid":"https://orcid.org/0000-0001-7730-5775"},"institutions":[{"id":"https://openalex.org/I3923682","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I3923682"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Quan Liu","raw_affiliation_strings":["Soochow University,School of Computer Science and Technology,Suzhou,P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Soochow University,School of Computer Science and Technology,Suzhou,P.R. China","institution_ids":["https://openalex.org/I3923682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100579324","display_name":"Meilong Shi","orcid":null},"institutions":[{"id":"https://openalex.org/I3923682","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I3923682"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meilong Shi","raw_affiliation_strings":["Soochow University,School of Computer Science and Technology,Suzhou,P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Soochow University,School of Computer Science and Technology,Suzhou,P.R. China","institution_ids":["https://openalex.org/I3923682"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057715341","display_name":"Yuchao Jin","orcid":null},"institutions":[{"id":"https://openalex.org/I3923682","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I3923682"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuchao Jin","raw_affiliation_strings":["Soochow University,School of Computer Science and Technology,Suzhou,P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Soochow University,School of Computer Science and Technology,Suzhou,P.R. China","institution_ids":["https://openalex.org/I3923682"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I3923682"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.6355000138282776,"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":0.6355000138282776,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.5828999876976013,"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/T12784","display_name":"Modular Robots and Swarm Intelligence","score":0.5807999968528748,"subfield":{"id":"https://openalex.org/subfields/2210","display_name":"Mechanical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8753899335861206},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7593735456466675},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4863736927509308},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4379889965057373},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.41517576575279236},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10916483402252197}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8753899335861206},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7593735456466675},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4863736927509308},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4379889965057373},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.41517576575279236},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10916483402252197},{"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:10.1109/icassp49660.2025.10887769","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887769","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.44999998807907104}],"awards":[],"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":21,"referenced_works":["https://openalex.org/W2145339207","https://openalex.org/W2747213132","https://openalex.org/W2968526727","https://openalex.org/W3205046940","https://openalex.org/W4226071977","https://openalex.org/W4302774970","https://openalex.org/W4306786778","https://openalex.org/W4310705874","https://openalex.org/W4312222142","https://openalex.org/W4388486449","https://openalex.org/W6752380930","https://openalex.org/W6758846586","https://openalex.org/W6762491519","https://openalex.org/W6766805167","https://openalex.org/W6772005887","https://openalex.org/W6775529125","https://openalex.org/W6781750019","https://openalex.org/W6783196708","https://openalex.org/W6791040878","https://openalex.org/W6797584944","https://openalex.org/W6848308608"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","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"],"abstract_inverted_index":{"Multi-Agent":[0,50],"Reinforcement":[1,51],"Learning":[2,52],"(MARL)":[3],"has":[4],"shown":[5],"significant":[6],"promise":[7],"in":[8,30,49,87],"tackling":[9],"complex":[10],"cooperative":[11],"tasks,":[12],"largely":[13],"due":[14],"to":[15,72,81],"parameter":[16],"sharing":[17,23],"among":[18],"agents.":[19],"However,":[20],"while":[21],"this":[22,39],"facilitates":[24],"teamwork,":[25],"it":[26],"can":[27],"also":[28],"result":[29],"agent":[31],"homogenization,":[32],"which":[33],"limits":[34],"individualized":[35,59],"behaviors.":[36],"To":[37],"address":[38],"issue,":[40],"we":[41],"introduce":[42],"a":[43],"novel":[44],"method":[45,77],"called":[46],"Diverse":[47],"Collaboration":[48],"via":[53],"Self-Adaptive":[54],"Method":[55],"(DC-SA).":[56],"DC-SA":[57,98],"advances":[58],"behaviors":[60],"by":[61],"maximizing":[62],"the":[63,103],"mutual":[64],"information":[65],"between":[66],"agents\u2019":[67],"representations":[68],"and":[69,84],"their":[70],"trajectories":[71],"enhance":[73],"diversity":[74],"collaboration.":[75],"The":[76],"employs":[78],"adaptive":[79],"weights":[80],"balance":[82],"collaboration":[83,90],"individualization,":[85],"particularly":[86],"scenarios":[88],"where":[89],"is":[91],"challenging.":[92],"Our":[93],"empirical":[94],"results":[95],"demonstrate":[96],"that":[97],"outperforms":[99],"five":[100],"baselines":[101],"on":[102],"StarCraft":[104],"II":[105],"micromanagement":[106],"tasks.":[107]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
