{"id":"https://openalex.org/W4312741895","doi":"https://doi.org/10.1109/iros47612.2022.9982253","title":"Scalable Model-based Policy Optimization for Decentralized Networked Systems","display_name":"Scalable Model-based Policy Optimization for Decentralized Networked Systems","publication_year":2022,"publication_date":"2022-10-23","ids":{"openalex":"https://openalex.org/W4312741895","doi":"https://doi.org/10.1109/iros47612.2022.9982253"},"language":"en","primary_location":{"id":"doi:10.1109/iros47612.2022.9982253","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros47612.2022.9982253","pdf_url":null,"source":{"id":"https://openalex.org/S4363607704","display_name":"2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 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/A5002080576","display_name":"Yali Du","orcid":"https://orcid.org/0000-0001-5683-2621"},"institutions":[{"id":"https://openalex.org/I183935753","display_name":"King's College London","ror":"https://ror.org/0220mzb33","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I183935753"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Yali Du","raw_affiliation_strings":["King's College London,London,UK"],"affiliations":[{"raw_affiliation_string":"King's College London,London,UK","institution_ids":["https://openalex.org/I183935753"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102811261","display_name":"Chengdong Ma","orcid":"https://orcid.org/0000-0002-7963-3024"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chengdong Ma","raw_affiliation_strings":["Xiamen University,Xiamen,China","Xiamen University, Xiamen, China"],"affiliations":[{"raw_affiliation_string":"Xiamen University,Xiamen,China","institution_ids":["https://openalex.org/I191208505"]},{"raw_affiliation_string":"Xiamen University, Xiamen, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100373054","display_name":"Yuchen Liu","orcid":"https://orcid.org/0000-0002-6517-0022"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuchen Liu","raw_affiliation_strings":["Peking University,Beijing,China","Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Peking University,Beijing,China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003991609","display_name":"Runji Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Runji Lin","raw_affiliation_strings":["Chinese Academy of Sciences,Beijing,China","Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Beijing,China","institution_ids":["https://openalex.org/I19820366"]},{"raw_affiliation_string":"Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100709867","display_name":"Hao Dong","orcid":"https://orcid.org/0000-0002-7984-9909"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Dong","raw_affiliation_strings":["CFCS, School of CS, Peking University"],"affiliations":[{"raw_affiliation_string":"CFCS, School of CS, Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100384686","display_name":"Jun Wang","orcid":"https://orcid.org/0000-0002-1305-5735"},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jun Wang","raw_affiliation_strings":["University College London,London,UK","University College London, London, UK"],"affiliations":[{"raw_affiliation_string":"University College London,London,UK","institution_ids":["https://openalex.org/I45129253"]},{"raw_affiliation_string":"University College London, London, UK","institution_ids":["https://openalex.org/I45129253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090073634","display_name":"Yaodong Yang","orcid":"https://orcid.org/0000-0001-8132-5613"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaodong Yang","raw_affiliation_strings":["Peking University,Beijing,China","Institute for AI, Peking University & BIGAI","Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Peking University,Beijing,China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Institute for AI, Peking University & BIGAI","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5002080576"],"corresponding_institution_ids":["https://openalex.org/I183935753"],"apc_list":null,"apc_paid":null,"fwci":2.481,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.91572074,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"9019","last_page":"9026"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10524","display_name":"Traffic control and management","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10524","display_name":"Traffic control and management","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11344","display_name":"Traffic Prediction and Management Techniques","score":0.9977999925613403,"subfield":{"id":"https://openalex.org/subfields/2215","display_name":"Building and Construction"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11942","display_name":"Transportation and Mobility Innovations","score":0.9952999949455261,"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/computer-science","display_name":"Computer science","score":0.8648293018341064},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8193788528442383},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6752585172653198},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5230066180229187},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.460624635219574},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4447006583213806},{"id":"https://openalex.org/keywords/independence","display_name":"Independence (probability theory)","score":0.4279125928878784},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.42466968297958374},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.29320067167282104},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.25034087896347046}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8648293018341064},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8193788528442383},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6752585172653198},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5230066180229187},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.460624635219574},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4447006583213806},{"id":"https://openalex.org/C35651441","wikidata":"https://www.wikidata.org/wiki/Q625303","display_name":"Independence (probability theory)","level":2,"score":0.4279125928878784},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.42466968297958374},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29320067167282104},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.25034087896347046},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"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/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros47612.2022.9982253","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros47612.2022.9982253","pdf_url":null,"source":{"id":"https://openalex.org/S4363607704","display_name":"2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":65,"referenced_works":["https://openalex.org/W6043852","https://openalex.org/W1491843047","https://openalex.org/W1936945694","https://openalex.org/W1968136409","https://openalex.org/W1968719911","https://openalex.org/W2101628261","https://openalex.org/W2107726111","https://openalex.org/W2134779831","https://openalex.org/W2145339207","https://openalex.org/W2395575420","https://openalex.org/W2617547828","https://openalex.org/W2736601468","https://openalex.org/W2788115019","https://openalex.org/W2807741983","https://openalex.org/W2859967432","https://openalex.org/W2902907165","https://openalex.org/W2904450917","https://openalex.org/W2949963774","https://openalex.org/W2964338167","https://openalex.org/W2970272688","https://openalex.org/W2982316857","https://openalex.org/W2989847975","https://openalex.org/W2991046523","https://openalex.org/W2995815314","https://openalex.org/W3035141911","https://openalex.org/W3106398159","https://openalex.org/W3118210634","https://openalex.org/W3193101426","https://openalex.org/W3194351817","https://openalex.org/W3205868665","https://openalex.org/W4205513846","https://openalex.org/W4221149741","https://openalex.org/W4286748781","https://openalex.org/W4288319859","https://openalex.org/W4289100326","https://openalex.org/W4295598622","https://openalex.org/W4297789759","https://openalex.org/W4299802797","https://openalex.org/W6600255050","https://openalex.org/W6680096503","https://openalex.org/W6680657880","https://openalex.org/W6712181171","https://openalex.org/W6713411898","https://openalex.org/W6738796088","https://openalex.org/W6741002519","https://openalex.org/W6746368081","https://openalex.org/W6749032143","https://openalex.org/W6749304979","https://openalex.org/W6752380930","https://openalex.org/W6753183898","https://openalex.org/W6755921573","https://openalex.org/W6757784512","https://openalex.org/W6762373827","https://openalex.org/W6762491519","https://openalex.org/W6764053384","https://openalex.org/W6767151588","https://openalex.org/W6771232374","https://openalex.org/W6771514159","https://openalex.org/W6779279235","https://openalex.org/W6781210820","https://openalex.org/W6785817231","https://openalex.org/W6791723018","https://openalex.org/W6800131325","https://openalex.org/W6810298798","https://openalex.org/W6840380725"],"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/W2386410636","https://openalex.org/W3038962357","https://openalex.org/W2025663273","https://openalex.org/W3099153698","https://openalex.org/W2100349471"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1],"algorithms":[2],"require":[3],"a":[4,20,85,153],"large":[5],"amount":[6],"of":[7,31,49,112,129,136,201,210],"samples;":[8],"this":[9],"often":[10],"limits":[11],"their":[12,68,94],"real-world":[13],"applications":[14],"on":[15,164],"even":[16],"simple":[17],"tasks.":[18],"Such":[19],"challenge":[21],"is":[22,33,152],"more":[23,34],"outstanding":[24],"in":[25],"multi-agent":[26,50],"tasks,":[27],"as":[28],"each":[29,82],"step":[30],"operation":[32],"costly,":[35],"requiring":[36],"communications":[37],"or":[38,40],"shifting":[39],"resources.":[41],"This":[42],"work":[43],"aims":[44],"to":[45,88,156],"improve":[46],"data":[47,195],"efficiency":[48,196],"control":[51,176,185],"by":[52,96],"model-based":[53,74],"learning.":[54],"We":[55,160],"consider":[56],"networked":[57],"systems":[58],"where":[59],"agents":[60],"are":[61,102,172],"cooperative":[62],"and":[63,70,92,98,144,179,181,197,213],"communicate":[64],"only":[65],"locally":[66],"with":[67],"neighbors,":[69],"propose":[71],"the":[72,100,105,110,117,126,134,148,199],"decentralized":[73],"policy":[75,137,150,158],"optimization":[76],"framework":[77],"(DMPO).":[78],"In":[79],"our":[80,162,191,211],"method,":[81],"agent":[83],"learns":[84],"dynamic":[86],"model":[87,106,118,130],"predict":[89],"future":[90],"states":[91],"broadcast":[93],"predictions":[95],"communication,":[97],"then":[99],"policies":[101],"trained":[103],"under":[104],"rollouts.":[107],"To":[108,132],"alleviate":[109],"bias":[111],"model-generated":[113],"data,":[114],"we":[115,139],"restrain":[116],"usage":[119],"for":[120,167],"generating":[121],"myopic":[122],"rollouts,":[123],"thus":[124],"reducing":[125],"compounding":[127],"error":[128],"generation.":[131],"pertain":[133],"independence":[135],"update,":[138],"introduce":[140],"extended":[141],"value":[142],"function":[143],"theoretically":[145],"prove":[146],"that":[147,190],"resulting":[149],"gradient":[151],"close":[154],"approximation":[155],"true":[157,205],"gradients.":[159],"evaluate":[161],"algorithm":[163,212],"several":[165],"benchmarks":[166],"intelligent":[168],"transportation":[169],"systems,":[170],"which":[171],"connected":[173],"autonomous":[174],"vehicle":[175],"tasks":[177],"(Flow":[178],"CACC)":[180],"adaptive":[182],"traffic":[183],"signal":[184],"(ATSC).":[186],"Empirical":[187],"results":[188],"show":[189],"method":[192],"achieves":[193],"superior":[194],"matches":[198],"performance":[200],"model-free":[202],"methods":[203],"using":[204],"models.":[206],"The":[207],"source":[208],"code":[209],"baselines":[214],"can":[215],"be":[216],"found":[217],"at":[218],"https://github.com/PKU-MARL/Model-Based-MARL.":[219]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-09T08:58:05.943551","created_date":"2025-10-10T00:00:00"}