{"id":"https://openalex.org/W4416251251","doi":"https://doi.org/10.1109/ijcnn64981.2025.11228644","title":"Leveraging World Model Disentanglement in Value-Based Multi-Agent Reinforcement Learning","display_name":"Leveraging World Model Disentanglement in Value-Based Multi-Agent Reinforcement Learning","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4416251251","doi":"https://doi.org/10.1109/ijcnn64981.2025.11228644"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11228644","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11228644","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","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/A5074462772","display_name":"Zhizun Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I5023651","display_name":"McGill University","ror":"https://ror.org/01pxwe438","country_code":"CA","type":"education","lineage":["https://openalex.org/I5023651"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Zhizun Wang","raw_affiliation_strings":["McGill University,Montreal,Canada"],"affiliations":[{"raw_affiliation_string":"McGill University,Montreal,Canada","institution_ids":["https://openalex.org/I5023651"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109496264","display_name":"David Meger","orcid":null},"institutions":[{"id":"https://openalex.org/I5023651","display_name":"McGill University","ror":"https://ror.org/01pxwe438","country_code":"CA","type":"education","lineage":["https://openalex.org/I5023651"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"David Meger","raw_affiliation_strings":["McGill University,Montreal,Canada"],"affiliations":[{"raw_affiliation_string":"McGill University,Montreal,Canada","institution_ids":["https://openalex.org/I5023651"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5074462772"],"corresponding_institution_ids":["https://openalex.org/I5023651"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19457062,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.6732000112533569,"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":0.6732000112533569,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.12680000066757202,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.03220000118017197,"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":0.7972999811172485},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6108999848365784},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.498199999332428},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4361000061035156},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.43540000915527344},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.42480000853538513},{"id":"https://openalex.org/keywords/sample-complexity","display_name":"Sample complexity","score":0.40139999985694885},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.35120001435279846}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7972999811172485},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7146999835968018},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6352999806404114},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6108999848365784},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5785999894142151},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.498199999332428},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4361000061035156},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.43540000915527344},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.42480000853538513},{"id":"https://openalex.org/C2778445095","wikidata":"https://www.wikidata.org/wiki/Q18354077","display_name":"Sample complexity","level":2,"score":0.40139999985694885},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.35120001435279846},{"id":"https://openalex.org/C3020493868","wikidata":"https://www.wikidata.org/wiki/Q55631277","display_name":"Real world data","level":2,"score":0.34860000014305115},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.3249000012874603},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.2930000126361847},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.29170000553131104},{"id":"https://openalex.org/C52740198","wikidata":"https://www.wikidata.org/wiki/Q1539564","display_name":"Importance sampling","level":3,"score":0.28380000591278076},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.27790001034736633},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.2551000118255615},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.25189998745918274},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.25049999356269836}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11228644","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11228644","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1641379095","https://openalex.org/W1980035368","https://openalex.org/W2158782408","https://openalex.org/W2292533394","https://openalex.org/W2617547828","https://openalex.org/W2747213132","https://openalex.org/W2963658727","https://openalex.org/W2972568824","https://openalex.org/W2981450816","https://openalex.org/W3193101426","https://openalex.org/W4382202546","https://openalex.org/W4391259941","https://openalex.org/W4403577383"],"related_works":[],"abstract_inverted_index":{"In":[0,62],"this":[1],"paper,":[2],"we":[3,64],"propose":[4],"a":[5,26,55,66,120,164],"novel":[6],"model-based":[7],"multi-agent":[8,49,168],"reinforcement":[9],"learning":[10,169],"approach":[11],"named":[12],"Value":[13],"Decomposition":[14],"Framework":[15],"with":[16,37,119],"Disentangled":[17],"World":[18],"Model":[19],"to":[20,42,77,107,123,160],"address":[21],"the":[22,34,79,96,109,113,125,131],"challenge":[23],"of":[24,29,58,71,167],"achieving":[25],"common":[27],"goal":[28],"multiple":[30],"agents":[31],"interacting":[32],"in":[33],"same":[35],"environment":[36,81],"reduced":[38],"sample":[39,153],"complexity.":[40],"Due":[41],"scalability":[43],"and":[44,74,103,129,143,155],"non-stationarity":[45],"problems":[46],"posed":[47],"by":[48],"systems,":[50],"model-free":[51],"methods":[52],"rely":[53],"on":[54,89,137],"considerable":[56],"number":[57],"samples":[59],"for":[60,112],"training.":[61],"contrast,":[63],"use":[65],"modularized":[67],"world":[68,114],"model,":[69,115],"composed":[70],"action-conditioned,":[72],"action-free,":[73],"static":[75],"branches,":[76],"unravel":[78],"complicated":[80],"dynamics.":[82],"Our":[83],"model":[84],"produces":[85],"imagined":[86],"outcomes":[87],"based":[88],"past":[90],"experience,":[91],"without":[92],"sampling":[93],"directly":[94],"from":[95],"real":[97],"environment.":[98],"We":[99],"employ":[100],"variational":[101,104],"auto-encoders":[102,106],"graph":[105],"learn":[108],"latent":[110],"representations":[111],"which":[116],"is":[117],"merged":[118],"value-based":[121],"framework":[122],"predict":[124],"joint":[126],"action-value":[127],"function":[128],"optimize":[130],"overall":[132],"training":[133],"objective.":[134],"Experimental":[135],"results":[136],"StarCraft":[138],"II":[139],"micro-management,":[140],"Multi-Agent":[141],"MuJoCo,":[142],"Level-Based":[144],"Foraging":[145],"challenges":[146],"demonstrate":[147],"that":[148],"our":[149],"method":[150],"achieves":[151],"high":[152],"efficiency":[154],"exhibits":[156],"superior":[157],"performance":[158],"compared":[159],"other":[161],"baselines":[162],"across":[163],"wide":[165],"range":[166],"tasks.":[170]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-14T00:00:00"}