{"id":"https://openalex.org/W4416748684","doi":"https://doi.org/10.1109/iros60139.2025.11245885","title":"Decentralized but Not Compromised: Modular Architecture with Refined Observation for Multi-Agent Model-Based Reinforcement Learning","display_name":"Decentralized but Not Compromised: Modular Architecture with Refined Observation for Multi-Agent Model-Based Reinforcement Learning","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416748684","doi":"https://doi.org/10.1109/iros60139.2025.11245885"},"language":null,"primary_location":{"id":"doi:10.1109/iros60139.2025.11245885","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11245885","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/A5100439217","display_name":"Shuqi Wang","orcid":"https://orcid.org/0009-0009-3605-9331"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shuqi Wang","raw_affiliation_strings":["Zhejiang University,College of Electrical Engineering,Hangzhou,China,310027"],"affiliations":[{"raw_affiliation_string":"Zhejiang University,College of Electrical Engineering,Hangzhou,China,310027","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033808402","display_name":"Meiqin Liu","orcid":"https://orcid.org/0000-0003-0693-6574"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meiqin Liu","raw_affiliation_strings":["Xi’an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence,Xi’an,China,710049"],"affiliations":[{"raw_affiliation_string":"Xi’an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence,Xi’an,China,710049","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029942279","display_name":"Ronghao Zheng","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ronghao Zheng","raw_affiliation_strings":["Zhejiang University,College of Electrical Engineering,Hangzhou,China,310027"],"affiliations":[{"raw_affiliation_string":"Zhejiang University,College of Electrical Engineering,Hangzhou,China,310027","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004998505","display_name":"Shanling Dong","orcid":"https://orcid.org/0000-0002-1754-1829"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shanling Dong","raw_affiliation_strings":["Zhejiang University,College of Electrical Engineering,Hangzhou,China,310027"],"affiliations":[{"raw_affiliation_string":"Zhejiang University,College of Electrical Engineering,Hangzhou,China,310027","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101947241","display_name":"Ping Wei","orcid":"https://orcid.org/0000-0002-8535-9527"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ping Wei","raw_affiliation_strings":["Xi’an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence,Xi’an,China,710049"],"affiliations":[{"raw_affiliation_string":"Xi’an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence,Xi’an,China,710049","institution_ids":["https://openalex.org/I87445476"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100439217"],"corresponding_institution_ids":["https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.20546061,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"9760","last_page":"9767"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.570900022983551,"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":0.570900022983551,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.20110000669956207,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.04340000078082085,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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/modular-design","display_name":"Modular design","score":0.7646999955177307},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7247999906539917},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5591999888420105},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.5557000041007996},{"id":"https://openalex.org/keywords/decomposition","display_name":"Decomposition","score":0.5146999955177307},{"id":"https://openalex.org/keywords/decoupling","display_name":"Decoupling (probability)","score":0.48489999771118164},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.47699999809265137},{"id":"https://openalex.org/keywords/decentralised-system","display_name":"Decentralised system","score":0.46779999136924744}],"concepts":[{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.7646999955177307},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7247999906539917},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6699000000953674},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5853000283241272},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5591999888420105},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.5557000041007996},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.5146999955177307},{"id":"https://openalex.org/C205606062","wikidata":"https://www.wikidata.org/wiki/Q5249645","display_name":"Decoupling (probability)","level":2,"score":0.48489999771118164},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4821999967098236},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.47699999809265137},{"id":"https://openalex.org/C205875254","wikidata":"https://www.wikidata.org/wiki/Q17156857","display_name":"Decentralised system","level":3,"score":0.46779999136924744},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.39239999651908875},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.35920000076293945},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.3531000018119812},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3325999975204468},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.32910001277923584},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.3181000053882599},{"id":"https://openalex.org/C98025372","wikidata":"https://www.wikidata.org/wiki/Q477538","display_name":"Systems architecture","level":3,"score":0.2921999990940094},{"id":"https://openalex.org/C13687954","wikidata":"https://www.wikidata.org/wiki/Q4826847","display_name":"Autonomous agent","level":2,"score":0.28630000352859497},{"id":"https://openalex.org/C169337768","wikidata":"https://www.wikidata.org/wiki/Q2446723","display_name":"Swarm robotics","level":3,"score":0.28439998626708984},{"id":"https://openalex.org/C193415008","wikidata":"https://www.wikidata.org/wiki/Q639681","display_name":"Network architecture","level":2,"score":0.26930001378059387},{"id":"https://openalex.org/C137703981","wikidata":"https://www.wikidata.org/wiki/Q4692093","display_name":"Agent architecture","level":3,"score":0.26750001311302185},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2590999901294708},{"id":"https://openalex.org/C181335050","wikidata":"https://www.wikidata.org/wiki/Q14915018","display_name":"Swarm behaviour","level":2,"score":0.25609999895095825}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros60139.2025.11245885","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11245885","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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":4,"referenced_works":["https://openalex.org/W1980035368","https://openalex.org/W2747213132","https://openalex.org/W4382464003","https://openalex.org/W4385245566"],"related_works":[],"abstract_inverted_index":{"Multi-agent":[0],"adversarial":[1],"tasks":[2],"such":[3],"as":[4],"swarm":[5],"robotics":[6],"and":[7,87,111,134],"autonomous":[8],"vehicle":[9],"coordination,":[10],"demand":[11],"efficient":[12],"decentralized":[13],"collaboration":[14],"under":[15],"partial":[16],"observability.":[17],"While":[18],"model-free":[19],"multi-agent":[20,32],"RL":[21,34],"(MF-MARL)":[22],"methods":[23,36],"suffer":[24],"from":[25,72,115],"necessitating":[26],"extensive":[27],"environment":[28],"interactions,":[29],"most":[30],"existing":[31],"model-based":[33],"(MA-MBRL)":[35],"fail":[37],"to":[38,64,107],"align":[39],"with":[40,44,60,84],"the":[41,66,73,121,132],"Centralized":[42],"Training":[43],"Decentralized":[45],"Execution":[46],"(CTDE)":[47],"paradigm,":[48],"which":[49],"limits":[50],"system":[51],"flexibility.":[52],"This":[53],"paper":[54],"proposes":[55],"a":[56,95],"novel":[57],"modular":[58],"architecture":[59],"refined":[61],"observations":[62,106],"(MARO)":[63],"achieve":[65],"CTDE":[67],"paradigm":[68],"by":[69],"decoupling":[70],"agents":[71],"world":[74,82],"model.":[75],"Key":[76],"innovations":[77],"include:":[78],"1)":[79],"an":[80],"enhanced":[81],"model":[83],"weighted":[85],"loss":[86],"history-augmented":[88],"rollout":[89],"for":[90],"high-quality":[91],"data":[92],"generation;":[93],"2)":[94],"dual-stream":[96],"semantic":[97],"decomposition":[98,104],"network":[99],"(DSDN)":[100],"that":[101],"performs":[102],"fine-grained":[103],"of":[105,136],"refine":[108],"action":[109],"mapping":[110],"mitigate":[112],"performance":[113,128],"degradation":[114],"information":[116],"loss.":[117],"Extensive":[118],"experiments":[119],"on":[120],"StarCraft":[122],"Multi-Agent":[123],"Challenge":[124],"(SMAC)":[125],"demonstrate":[126],"superior":[127],"over":[129],"opponents,":[130],"validating":[131],"effectiveness":[133],"advancement":[135],"MARO.":[137]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-28T00:00:00"}