{"id":"https://openalex.org/W4399257591","doi":"https://doi.org/10.1145/3653804.3656282","title":"Boosting Efficiency and Scalability of Multi-Agent Reinforcement Learning via Graph-Invariant Network","display_name":"Boosting Efficiency and Scalability of Multi-Agent Reinforcement Learning via Graph-Invariant Network","publication_year":2024,"publication_date":"2024-01-19","ids":{"openalex":"https://openalex.org/W4399257591","doi":"https://doi.org/10.1145/3653804.3656282"},"language":"en","primary_location":{"id":"doi:10.1145/3653804.3656282","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3653804.3656282","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference on Computer Vision and Deep Learning","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/A5102734908","display_name":"Hongyi Fu","orcid":"https://orcid.org/0009-0003-9648-6542"},"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":true,"raw_author_name":"Hongyi Fu","raw_affiliation_strings":["University of Science and Technology of China, China"],"raw_orcid":"https://orcid.org/0009-0003-9648-6542","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061104105","display_name":"Jianmin Ji","orcid":"https://orcid.org/0000-0002-1515-0402"},"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":"Jianmin Ji","raw_affiliation_strings":["University of Science and Technology of China, China"],"raw_orcid":"https://orcid.org/0000-0002-1515-0402","affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5102734908"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.3311,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.62579233,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9986000061035156,"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":0.9986000061035156,"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":0.9757000207901001,"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":0.9681000113487244,"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/scalability","display_name":"Scalability","score":0.7002508044242859},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.686859667301178},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.628559947013855},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.46011123061180115},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.4409751296043396},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.44073840975761414},{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.4300639033317566},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40726664662361145},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.21392834186553955}],"concepts":[{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7002508044242859},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.686859667301178},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.628559947013855},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.46011123061180115},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.4409751296043396},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.44073840975761414},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.4300639033317566},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40726664662361145},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.21392834186553955},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3653804.3656282","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3653804.3656282","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference on Computer Vision and Deep Learning","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":8,"referenced_works":["https://openalex.org/W1542941925","https://openalex.org/W1981276685","https://openalex.org/W2747213132","https://openalex.org/W2982316857","https://openalex.org/W6600175266","https://openalex.org/W6605533441","https://openalex.org/W6634101208","https://openalex.org/W6744580074"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W2031695474","https://openalex.org/W2389214306","https://openalex.org/W2024136090","https://openalex.org/W2586732548","https://openalex.org/W3049728571","https://openalex.org/W2964765435"],"abstract_inverted_index":{"Within":[0],"a":[1,56,99,124,165,217],"multiagent":[2,34,48,53,87,100,149,166,229,267],"framework,":[3],"an":[4,13],"escalation":[5],"in":[6,47,164,201,235,249,263],"the":[7,17,25,29,33,39,52,81,115,140,145,160,177,185,202,236,250,255],"count":[8],"of":[9,16,32,86,105,127,148,162,179,188,261],"agents":[10,163],"leads":[11,207],"to":[12,23,190,208,241,265],"exponential":[14],"expansion":[15,21],"state-action":[18,141],"space.":[19],"This":[20],"tends":[22],"diminish":[24],"scalability":[26,46,85,260],"and":[27,45,60,69,84,108,143,173,212,224,259],"reduce":[28,139],"sample":[30,43,82,146,257],"efficiency":[31,44,83,147,258],"reinforcement":[35],"learning.":[36],"To":[37],"address":[38],"need":[40],"for":[41,153,227],"improved":[42],"algorithms,":[49],"we":[50,239,253],"characterize":[51],"system":[54,167],"as":[55,159,243],"weighted":[57],"directed":[58],"graph":[59],"propose":[61],"two":[62],"related":[63],"theorem:":[64],"Graph":[65,70],"Isomorphism":[66],"Invariant":[67,72],"(GII)":[68],"Decomposition":[71],"(GDI).":[73],"These":[74],"theorems":[75],"provide":[76],"significant":[77],"insights":[78],"into":[79],"enhancing":[80],"algorithms.The":[88],"motivation":[89,152],"behind":[90],"GII":[91,223],"arises":[92,155],"from":[93,156],"observing":[94],"various":[95,228],"\"isomorphic\"":[96],"scenarios":[97],"within":[98],"system,":[101],"e.g.,":[102],"random":[103],"shuffling":[104],"agent":[106],"indices":[107],"identical":[109],"topological":[110],"structures.":[111],"We":[112],"demonstrate":[113],"that":[114,158,220],"permutation":[116],"invariant":[117],"(PI),":[118],"previously":[119],"studied":[120],"by":[121],"others,":[122],"is":[123],"specific":[125],"case":[126],"our":[128],"proposed":[129],"GII.":[130],"Implementing":[131,182],"GII,":[132],"rather":[133],"than":[134],"solely":[135],"PI,":[136],"can":[137],"significantly":[138],"space":[142],"improve":[144],"algorithms.Similarly,":[150],"The":[151],"GDI":[154,183],"noticing":[157],"number":[161],"grows":[168],"essentially":[169],"introduces":[170],"new":[171],"vertices":[172],"edge":[174],"sets,":[175],"making":[176],"information":[178],"subgraph":[180],"exploitable.":[181],"facilitates":[184],"efficient":[186],"transfer":[187],"policies":[189],"larger-scale":[191,266],"tasks.":[192,268],"Mainstream":[193],"MARL":[194],"algorithms":[195],"often":[196],"overlook":[197],"these":[198],"properties,":[199],"learning":[200],"original":[203],"state":[204],"space,":[205],"which":[206],"inefficient":[209],"policy":[210],"search":[211],"suppresses":[213],"scalability.We":[214],"have":[215],"developed":[216],"network":[218],"architecture":[219,234],"meets":[221],"both":[222],"GDI,":[225],"suitable":[226],"algorithms.":[230],"When":[231],"implementing":[232],"this":[233],"QTRAN":[237],"algorithm,":[238],"refer":[240],"it":[242],"QTRAN-GI.":[244],"By":[245],"conducting":[246],"comprehensive":[247],"experiments":[248],"SMAC":[251],"environment,":[252],"confirm":[254],"superior":[256],"QTRAN-GI":[262],"transitioning":[264]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}