{"id":"https://openalex.org/W4410358146","doi":"https://doi.org/10.1007/s00521-025-11272-9","title":"Communication with factorized policy gradients in multi-agent deep reinforcement learning","display_name":"Communication with factorized policy gradients in multi-agent deep reinforcement learning","publication_year":2025,"publication_date":"2025-05-14","ids":{"openalex":"https://openalex.org/W4410358146","doi":"https://doi.org/10.1007/s00521-025-11272-9"},"language":"en","primary_location":{"id":"doi:10.1007/s00521-025-11272-9","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00521-025-11272-9","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00521-025-11272-9.pdf","source":{"id":"https://openalex.org/S147897268","display_name":"Neural Computing and Applications","issn_l":"0941-0643","issn":["0941-0643","1433-3058"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Computing and Applications","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s00521-025-11272-9.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5053438680","display_name":"Changxi Zhu","orcid":"https://orcid.org/0000-0002-2910-5506"},"institutions":[{"id":"https://openalex.org/I193662353","display_name":"Utrecht University","ror":"https://ror.org/04pp8hn57","country_code":"NL","type":"education","lineage":["https://openalex.org/I193662353"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Changxi Zhu","raw_affiliation_strings":["Department of Information and Computing Sciences, Utrecht University, Utrecht, The Netherlands"],"raw_orcid":"https://orcid.org/0000-0002-2910-5506","affiliations":[{"raw_affiliation_string":"Department of Information and Computing Sciences, Utrecht University, Utrecht, The Netherlands","institution_ids":["https://openalex.org/I193662353"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028760842","display_name":"Mehdi Dastani","orcid":"https://orcid.org/0000-0002-4641-4087"},"institutions":[{"id":"https://openalex.org/I193662353","display_name":"Utrecht University","ror":"https://ror.org/04pp8hn57","country_code":"NL","type":"education","lineage":["https://openalex.org/I193662353"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Mehdi Dastani","raw_affiliation_strings":["Department of Information and Computing Sciences, Utrecht University, Utrecht, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information and Computing Sciences, Utrecht University, Utrecht, The Netherlands","institution_ids":["https://openalex.org/I193662353"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5107808323","display_name":"Shihan Wang","orcid":"https://orcid.org/0000-0001-5971-7522"},"institutions":[{"id":"https://openalex.org/I193662353","display_name":"Utrecht University","ror":"https://ror.org/04pp8hn57","country_code":"NL","type":"education","lineage":["https://openalex.org/I193662353"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Shihan Wang","raw_affiliation_strings":["Department of Information and Computing Sciences, Utrecht University, Utrecht, The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information and Computing Sciences, Utrecht University, Utrecht, The Netherlands","institution_ids":["https://openalex.org/I193662353"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5053438680"],"corresponding_institution_ids":["https://openalex.org/I193662353"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":{"value":2390,"currency":"EUR","value_usd":2990},"fwci":1.7312,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.86304323,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"37","issue":"23","first_page":"18933","last_page":"18956"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9948999881744385,"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/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9927999973297119,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/computational-science-and-engineering","display_name":"Computational Science and Engineering","score":0.9265275001525879},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7937992811203003},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6527678966522217},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.6270337104797363},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4434361457824707},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2982422411441803},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.12337026000022888},{"id":"https://openalex.org/keywords/composite-material","display_name":"Composite material","score":0.07804453372955322}],"concepts":[{"id":"https://openalex.org/C68597687","wikidata":"https://www.wikidata.org/wiki/Q362601","display_name":"Computational Science and Engineering","level":2,"score":0.9265275001525879},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7937992811203003},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6527678966522217},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.6270337104797363},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4434361457824707},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2982422411441803},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.12337026000022888},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.07804453372955322}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s00521-025-11272-9","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00521-025-11272-9","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00521-025-11272-9.pdf","source":{"id":"https://openalex.org/S147897268","display_name":"Neural Computing and Applications","issn_l":"0941-0643","issn":["0941-0643","1433-3058"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Computing and Applications","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s00521-025-11272-9","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00521-025-11272-9","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00521-025-11272-9.pdf","source":{"id":"https://openalex.org/S147897268","display_name":"Neural Computing and Applications","issn_l":"0941-0643","issn":["0941-0643","1433-3058"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Computing and Applications","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4410358146.pdf","grobid_xml":"https://content.openalex.org/works/W4410358146.grobid-xml"},"referenced_works_count":15,"referenced_works":["https://openalex.org/W1977655452","https://openalex.org/W2064675550","https://openalex.org/W2141017267","https://openalex.org/W2560674852","https://openalex.org/W2617547828","https://openalex.org/W2747213132","https://openalex.org/W2747329762","https://openalex.org/W2766447205","https://openalex.org/W2960876848","https://openalex.org/W2998367975","https://openalex.org/W2998489261","https://openalex.org/W4283789768","https://openalex.org/W4319984167","https://openalex.org/W4385767399","https://openalex.org/W4393147227"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856"],"abstract_inverted_index":{"Abstract":[0],"In":[1,69],"multi-agent":[2,169],"deep":[3],"reinforcement":[4],"learning":[5,39,52,94,163,175],"(MADRL),":[6],"agents":[7,46,79],"can":[8,158],"learn":[9],"to":[10,12,49,87,93,102,122,150,173],"communicate":[11],"broaden":[13],"their":[14,22],"view":[15],"and":[16,21,80,161,168],"understanding":[17],"of":[18,113],"the":[19,50,104,111],"environment":[20],"teammates.":[23],"Previous":[24],"works":[25],"on":[26,32],"communication":[27,137,176],"in":[28,66,164],"MADRL":[29],"mainly":[30],"rely":[31],"centralized":[33,82],"or":[34],"independent":[35],"value":[36,85,148],"functions":[37,86,149],"for":[38,77],"communication,":[40,96,108],"which":[41],"cannot":[42],"differentiate":[43,88],"how":[44,89],"communicating":[45,78,151],"individually":[47],"contribute":[48],"overall":[51],"process.":[53],"Moreover,":[54],"continuous":[55,59,165],"environments":[56],"that":[57,117,156],"incorporate":[58],"state/action":[60],"spaces":[61],"have":[62],"received":[63],"limited":[64],"attention":[65,115],"previous":[67],"research.":[68],"this":[70],"paper,":[71],"we":[72,109],"propose":[73],"a":[74,124,131],"novel":[75],"architecture":[76],"apply":[81],"but":[83],"factorized":[84,139,147],"each":[90],"agent":[91],"contributes":[92],"during":[95],"along":[97],"with":[98,138],"gradient":[99,134],"backpropagation.":[100],"Additionally,":[101],"address":[103],"complexity":[105],"introduced":[106],"by":[107],"investigate":[110],"use":[112],"an":[114],"mechanism":[116],"aggregates":[118],"messages,":[119],"enabling":[120],"policies":[121],"maintain":[123],"fixed":[125],"input":[126],"length.":[127],"We":[128,154],"then":[129],"present":[130],"new":[132],"policy":[133,140],"method":[135],"termed":[136],"gradients":[141],"(CFPG),":[142],"featuring":[143],"full":[144],"backpropagation":[145],"from":[146],"agents\u2019":[152],"architecture.":[153],"demonstrate":[155],"CFPG":[157],"enhance":[159],"performance":[160],"accelerate":[162],"predator\u2013prey":[166],"scenarios":[167],"MuJoCo,":[170],"when":[171],"compared":[172],"other":[174],"methods.":[177]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-13T06:13:01.061226","created_date":"2025-10-10T00:00:00"}