{"id":"https://openalex.org/W4416366467","doi":"https://doi.org/10.1109/tpami.2025.3634378","title":"Dynamic Deep Factor Graph for Multi-Agent Reinforcement Learning","display_name":"Dynamic Deep Factor Graph for Multi-Agent Reinforcement Learning","publication_year":2025,"publication_date":"2025-11-19","ids":{"openalex":"https://openalex.org/W4416366467","doi":"https://doi.org/10.1109/tpami.2025.3634378","pmid":"https://pubmed.ncbi.nlm.nih.gov/41259158"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2025.3634378","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3634378","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5060868822","display_name":"Yuchen Shi","orcid":"https://orcid.org/0009-0007-2790-9678"},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yuchen Shi","raw_affiliation_strings":["School of Computer and Communication Engineering, Shunde Innovation School, University of Science and Technology Beijing, Beijing, China","School of Computer and Communication Engineering and the Shunde Innovation School, University of Science and Technology Beijing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Computer and Communication Engineering, Shunde Innovation School, University of Science and Technology Beijing, Beijing, China","institution_ids":["https://openalex.org/I92403157"]},{"raw_affiliation_string":"School of Computer and Communication Engineering and the Shunde Innovation School, University of Science and Technology Beijing, Beijing, China","institution_ids":["https://openalex.org/I92403157"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035752099","display_name":"Shihong Duan","orcid":"https://orcid.org/0000-0001-8162-4269"},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shihong Duan","raw_affiliation_strings":["School of Computer and Communication Engineering, Shunde Innovation School, University of Science and Technology Beijing, Beijing, China","School of Computer and Communication Engineering and the Shunde Innovation School, University of Science and Technology Beijing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Computer and Communication Engineering, Shunde Innovation School, University of Science and Technology Beijing, Beijing, China","institution_ids":["https://openalex.org/I92403157"]},{"raw_affiliation_string":"School of Computer and Communication Engineering and the Shunde Innovation School, University of Science and Technology Beijing, Beijing, China","institution_ids":["https://openalex.org/I92403157"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066602150","display_name":"Cheng Xu","orcid":"https://orcid.org/0000-0003-1624-5494"},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cheng Xu","raw_affiliation_strings":["School of Computer and Communication Engineering, Shunde Innovation School, University of Science and Technology Beijing, Beijing, China","School of Computer and Communication Engineering and the Shunde Innovation School, University of Science and Technology Beijing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Computer and Communication Engineering, Shunde Innovation School, University of Science and Technology Beijing, Beijing, China","institution_ids":["https://openalex.org/I92403157"]},{"raw_affiliation_string":"School of Computer and Communication Engineering and the Shunde Innovation School, University of Science and Technology Beijing, Beijing, China","institution_ids":["https://openalex.org/I92403157"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087067755","display_name":"Ran Wang","orcid":"https://orcid.org/0000-0002-9530-8838"},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ran Wang","raw_affiliation_strings":["School of Computer and Communication Engineering, Shunde Innovation School, University of Science and Technology Beijing, Beijing, China","School of Computer and Communication Engineering and the Shunde Innovation School, University of Science and Technology Beijing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Computer and Communication Engineering, Shunde Innovation School, University of Science and Technology Beijing, Beijing, China","institution_ids":["https://openalex.org/I92403157"]},{"raw_affiliation_string":"School of Computer and Communication Engineering and the Shunde Innovation School, University of Science and Technology Beijing, Beijing, China","institution_ids":["https://openalex.org/I92403157"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083360604","display_name":"Fangwen Ye","orcid":"https://orcid.org/0000-0002-6521-2261"},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fangwen Ye","raw_affiliation_strings":["School of Computer and Communication Engineering, Shunde Innovation School, University of Science and Technology Beijing, Beijing, China","School of Computer and Communication Engineering and the Shunde Innovation School, University of Science and Technology Beijing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Computer and Communication Engineering, Shunde Innovation School, University of Science and Technology Beijing, Beijing, China","institution_ids":["https://openalex.org/I92403157"]},{"raw_affiliation_string":"School of Computer and Communication Engineering and the Shunde Innovation School, University of Science and Technology Beijing, Beijing, China","institution_ids":["https://openalex.org/I92403157"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060020877","display_name":"Chau Yuen","orcid":"https://orcid.org/0000-0002-9307-2120"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Chau Yuen","raw_affiliation_strings":["School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5060868822"],"corresponding_institution_ids":["https://openalex.org/I92403157"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19783624,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"48","issue":"3","first_page":"3417","last_page":"3431"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9557999968528748,"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":0.9557999968528748,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.0038999998942017555,"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":0.0031999999191612005,"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":0.6682999730110168},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5895000100135803},{"id":"https://openalex.org/keywords/factor-graph","display_name":"Factor graph","score":0.5134999752044678},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.46860000491142273},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.46389999985694885},{"id":"https://openalex.org/keywords/upper-and-lower-bounds","display_name":"Upper and lower bounds","score":0.36500000953674316},{"id":"https://openalex.org/keywords/on-the-fly","display_name":"On the fly","score":0.35989999771118164},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.3499999940395355},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.3440999984741211}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.718500018119812},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6682999730110168},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5895000100135803},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.526199996471405},{"id":"https://openalex.org/C159246509","wikidata":"https://www.wikidata.org/wiki/Q5428725","display_name":"Factor graph","level":3,"score":0.5134999752044678},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.46860000491142273},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.46389999985694885},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41119998693466187},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.36500000953674316},{"id":"https://openalex.org/C2781020372","wikidata":"https://www.wikidata.org/wiki/Q533093","display_name":"On the fly","level":2,"score":0.35989999771118164},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.3499999940395355},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.3440999984741211},{"id":"https://openalex.org/C91873725","wikidata":"https://www.wikidata.org/wiki/Q3445816","display_name":"Function approximation","level":3,"score":0.33889999985694885},{"id":"https://openalex.org/C2781039887","wikidata":"https://www.wikidata.org/wiki/Q1391724","display_name":"Factor (programming language)","level":2,"score":0.3249000012874603},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.32179999351501465},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.32120001316070557},{"id":"https://openalex.org/C148764684","wikidata":"https://www.wikidata.org/wiki/Q621751","display_name":"Approximation algorithm","level":2,"score":0.3068000078201294},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.30649998784065247},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3046000003814697},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.29510000348091125},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.2928999960422516},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.2815000116825104},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.27489998936653137},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.2662000060081482},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.25999999046325684},{"id":"https://openalex.org/C88230418","wikidata":"https://www.wikidata.org/wiki/Q131476","display_name":"Graph theory","level":2,"score":0.25839999318122864},{"id":"https://openalex.org/C201236551","wikidata":"https://www.wikidata.org/wiki/Q7310809","display_name":"Relative value","level":2,"score":0.2581000030040741},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.2567000091075897},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.25619998574256897},{"id":"https://openalex.org/C147297375","wikidata":"https://www.wikidata.org/wiki/Q6674930","display_name":"Look-ahead","level":2,"score":0.2524000108242035}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2025.3634378","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3634378","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:41259158","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41259158","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1543115993","https://openalex.org/W1552825266","https://openalex.org/W2018375997","https://openalex.org/W2121845348","https://openalex.org/W2128251417","https://openalex.org/W2137813581","https://openalex.org/W2145339207","https://openalex.org/W2150859678","https://openalex.org/W2746553466","https://openalex.org/W2747213132","https://openalex.org/W2807741983","https://openalex.org/W2913662073","https://openalex.org/W2968526727","https://openalex.org/W2987046690","https://openalex.org/W2996525917","https://openalex.org/W3160434116","https://openalex.org/W3173782550","https://openalex.org/W4245295309","https://openalex.org/W4321611535","https://openalex.org/W4392125445"],"related_works":[],"abstract_inverted_index":{"Multi-agent":[0],"reinforcement":[1],"learning":[2],"(MARL)":[3],"requires":[4],"effective":[5],"coordination":[6],"among":[7],"multiple":[8],"decision-making":[9],"agents":[10],"to":[11,50,93],"achieve":[12],"joint":[13,136],"goals.":[14],"Approaches":[15],"based":[16],"on":[17,85,103,139],"a":[18,69,89,99],"global":[19,76],"value":[20,70,77],"function":[21],"face":[22],"the":[23,75,86,104,113],"curse":[24],"of":[25,107],"dimensionality,":[26],"while":[27],"fully":[28],"decomposed":[29],"centralized":[30],"training":[31],"with":[32],"decentralized":[33],"execution":[34],"(CTDE)":[35],"methods":[36],"often":[37],"suffer":[38],"from":[39],"relative":[40],"overgeneralization.":[41],"Coordination":[42],"graphs":[43,80],"mitigate":[44],"this":[45],"issue":[46],"but":[47],"typically":[48],"fail":[49],"capture":[51],"dynamic":[52],"collaboration":[53],"patterns":[54],"that":[55,73],"evolve":[56],"over":[57,147],"time":[58],"and":[59,81,110,127,142,155],"across":[60],"tasks.":[61],"We":[62,97],"propose":[63],"Dynamic":[64],"Deep":[65],"Factor":[66],"Graphs":[67],"(DDFG),":[68],"decomposition":[71],"algorithm":[72],"represents":[74],"via":[78],"factor":[79],"learns":[82],"graph":[83],"structures":[84],"fly":[87],"through":[88],"graph-generation":[90],"policy,":[91],"adapting":[92],"evolving":[94],"inter-agent":[95],"relations.":[96],"provide":[98],"theoretical":[100],"upper":[101],"bound":[102],"approximation":[105],"error":[106],"high-order":[108],"decompositions":[109],"reveal":[111],"how":[112],"maximum":[114],"order":[115],"$D$D":[116],"trades":[117],"off":[118],"accuracy":[119],"against":[120],"computation,":[121],"offering":[122],"guidance":[123],"for":[124,131],"balancing":[125],"performance":[126],"cost.":[128],"Using":[129],"max-sum":[130],"inference,":[132],"DDFG":[133],"efficiently":[134],"derives":[135],"policies.":[137],"Experiments":[138],"higher-order":[140],"predator-prey":[141],"SMAC":[143],"show":[144],"consistent":[145],"gains":[146],"strong":[148],"value-decomposition":[149],"baselines,":[150],"demonstrating":[151],"improved":[152],"sample":[153],"efficiency":[154],"robustness":[156],"in":[157],"complex":[158],"settings.":[159]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-19T00:00:00"}