{"id":"https://openalex.org/W4385768055","doi":"https://doi.org/10.24963/ijcai.2023/470","title":"MA2CL:Masked Attentive Contrastive Learning for Multi-Agent Reinforcement Learning","display_name":"MA2CL:Masked Attentive Contrastive Learning for Multi-Agent Reinforcement Learning","publication_year":2023,"publication_date":"2023-08-01","ids":{"openalex":"https://openalex.org/W4385768055","doi":"https://doi.org/10.24963/ijcai.2023/470"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2023/470","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2023/470","pdf_url":"https://www.ijcai.org/proceedings/2023/0470.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2023/0470.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5036491073","display_name":"Haolin Song","orcid":"https://orcid.org/0000-0001-5931-5793"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haolin Song","raw_affiliation_strings":["EEIS Department, University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"EEIS Department, University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035851949","display_name":"Mingxiao Feng","orcid":"https://orcid.org/0000-0002-7412-0481"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingxiao Feng","raw_affiliation_strings":["EEIS Department, University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"EEIS Department, University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046805800","display_name":"Wengang Zhou","orcid":"https://orcid.org/0000-0003-1690-9836"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wengang Zhou","raw_affiliation_strings":["EEIS Department, University of Science and Technology of China","Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Hefei, China","EEIS Department, University of Science and Technology of China; Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"EEIS Department, University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Hefei, China","institution_ids":[]},{"raw_affiliation_string":"EEIS Department, University of Science and Technology of China; Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078141810","display_name":"Houqiang Li","orcid":"https://orcid.org/0000-0003-2188-3028"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Houqiang Li","raw_affiliation_strings":["EEIS Department, University of Science and Technology of China","Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Hefei, China","EEIS Department, University of Science and Technology of China; Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"EEIS Department, University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Hefei, China","institution_ids":[]},{"raw_affiliation_string":"EEIS Department, University of Science and Technology of China; Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.6316,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":{"value":0.86924571,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4226","last_page":"4234"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9958000183105469,"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"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9948999881744385,"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":0.8588230609893799},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7072991132736206},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.642707347869873},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.621590256690979},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5350882411003113},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.4226738214492798},{"id":"https://openalex.org/keywords/marl","display_name":"Marl","score":0.42129161953926086},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08307972550392151}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8588230609893799},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7072991132736206},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.642707347869873},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.621590256690979},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5350882411003113},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.4226738214492798},{"id":"https://openalex.org/C92927620","wikidata":"https://www.wikidata.org/wiki/Q184053","display_name":"Marl","level":3,"score":0.42129161953926086},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08307972550392151},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","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},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C109007969","wikidata":"https://www.wikidata.org/wiki/Q749565","display_name":"Structural basin","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2023/470","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2023/470","pdf_url":"https://www.ijcai.org/proceedings/2023/0470.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2023/470","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2023/470","pdf_url":"https://www.ijcai.org/proceedings/2023/0470.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Partnerships for the goals","id":"https://metadata.un.org/sdg/17","score":0.4300000071525574}],"awards":[{"id":"https://openalex.org/G2262853887","display_name":null,"funder_award_id":"61836011","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2944147612","display_name":null,"funder_award_id":"WK3490000007","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"}],"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":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4385768055.pdf"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W2736601468","https://openalex.org/W2747213132","https://openalex.org/W2954974210","https://openalex.org/W2977481643","https://openalex.org/W3005680577","https://openalex.org/W3009561768","https://openalex.org/W3011672202","https://openalex.org/W3021708257","https://openalex.org/W3023640063","https://openalex.org/W3035060554","https://openalex.org/W3093210455","https://openalex.org/W3115293622","https://openalex.org/W3134537774","https://openalex.org/W3157552953","https://openalex.org/W3175558129","https://openalex.org/W3208460365","https://openalex.org/W3211614623","https://openalex.org/W4200438872","https://openalex.org/W4221143473","https://openalex.org/W4221154300","https://openalex.org/W4221165949","https://openalex.org/W4281622133","https://openalex.org/W4286748781","https://openalex.org/W4287309212","https://openalex.org/W4287724327","https://openalex.org/W4287811291","https://openalex.org/W4288294128","https://openalex.org/W4288594419","https://openalex.org/W4297808394","https://openalex.org/W4304731240","https://openalex.org/W4385245566","https://openalex.org/W6755811877","https://openalex.org/W6863994431"],"related_works":["https://openalex.org/W2126019709","https://openalex.org/W1702901972","https://openalex.org/W4249798507","https://openalex.org/W2069775250","https://openalex.org/W2093541819","https://openalex.org/W2032294417","https://openalex.org/W2152754392","https://openalex.org/W1989172970","https://openalex.org/W2196316523","https://openalex.org/W1899363654"],"abstract_inverted_index":{"Recent":[0],"approaches":[1],"have":[2],"utilized":[3],"self-supervised":[4],"auxiliary":[5],"tasks":[6],"as":[7],"representation":[8,65,87],"learning":[9,20,29,66,86],"to":[10,60,88],"improve":[11],"the":[12,53,97,114,129,133,149],"performance":[13,150],"and":[14,92,113,151,158,165],"sample":[15,152],"efficiency":[16,153],"of":[17,125,135,154],"vision-based":[18,164],"reinforcement":[19,28],"algorithms":[21,157],"in":[22,26,49,52,64,101,162],"single-agent":[23],"settings.":[24],"However,":[25],"multi-agent":[27],"(MARL),":[30],"these":[31],"techniques":[32],"face":[33],"challenges":[34],"because":[35],"each":[36],"agent":[37,54,99,130],"only":[38],"receives":[39],"partial":[40],"observation":[41,100],"from":[42],"an":[43,74,107],"environment":[44],"influenced":[45],"by":[46,95],"others,":[47],"resulting":[48],"correlated":[50],"observations":[51],"dimension.":[55],"So":[56],"it":[57],"is":[58,116],"necessary":[59],"consider":[61],"agent-level":[62,93],"information":[63,127],"for":[67,111,138],"MARL.":[68],"In":[69],"this":[70],"paper,":[71],"we":[72,105],"propose":[73],"effective":[75],"framework":[76],"called":[77],"Multi-Agent":[78],"Masked":[79],"Attentive":[80],"Contrastive":[81],"Learning":[82],"(MA2CL),":[83],"which":[84],"encourages":[85],"be":[89],"both":[90],"temporal":[91],"predictive":[94],"reconstructing":[96],"masked":[98],"latent":[102],"space.":[103],"Specifically,":[104],"use":[106],"attention":[108],"reconstruction":[109],"model":[110,115],"recovering":[112],"trained":[117],"via":[118],"contrastive":[119],"learning.":[120],"MA2CL":[121],"allows":[122],"better":[123],"utilization":[124],"contextual":[126],"at":[128],"level,":[131],"facilitating":[132],"training":[134],"MARL":[136,156],"agents":[137],"cooperation":[139],"tasks.":[140],"Extensive":[141],"experiments":[142],"demonstrate":[143],"that":[144],"our":[145],"method":[146],"significantly":[147],"improves":[148],"different":[155],"outperforms":[159],"other":[160],"methods":[161],"various":[163],"state-based":[166],"scenarios.":[167]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}