{"id":"https://openalex.org/W4411758851","doi":"https://doi.org/10.1093/comjnl/bxaf063","title":"Improving value factorization for multi-agent deep reinforcement learning via individual contribution","display_name":"Improving value factorization for multi-agent deep reinforcement learning via individual contribution","publication_year":2025,"publication_date":"2025-06-05","ids":{"openalex":"https://openalex.org/W4411758851","doi":"https://doi.org/10.1093/comjnl/bxaf063"},"language":"en","primary_location":{"id":"doi:10.1093/comjnl/bxaf063","is_oa":false,"landing_page_url":"https://doi.org/10.1093/comjnl/bxaf063","pdf_url":null,"source":{"id":"https://openalex.org/S44643521","display_name":"The Computer Journal","issn_l":"0010-4620","issn":["0010-4620","1460-2067"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Computer Journal","raw_type":"journal-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/A5018602822","display_name":"Xiong Liqin","orcid":"https://orcid.org/0000-0001-5071-8844"},"institutions":[{"id":"https://openalex.org/I4210163363","display_name":"PLA Army Engineering University","ror":"https://ror.org/05mgp8x93","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210163363"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liqin Xiong","raw_affiliation_strings":["Command and Control Engineering Institute, Army Engineering University of PLA , Nanjing, 210007 ,"],"raw_orcid":"https://orcid.org/0000-0001-5071-8844","affiliations":[{"raw_affiliation_string":"Command and Control Engineering Institute, Army Engineering University of PLA , Nanjing, 210007 ,","institution_ids":["https://openalex.org/I4210163363"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026636864","display_name":"Lei Cao","orcid":"https://orcid.org/0000-0003-1137-6778"},"institutions":[{"id":"https://openalex.org/I4210163363","display_name":"PLA Army Engineering University","ror":"https://ror.org/05mgp8x93","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210163363"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Cao","raw_affiliation_strings":["Command and Control Engineering Institute, Army Engineering University of PLA , Nanjing, 210007 ,"],"raw_orcid":"https://orcid.org/0000-0003-1137-6778","affiliations":[{"raw_affiliation_string":"Command and Control Engineering Institute, Army Engineering University of PLA , Nanjing, 210007 ,","institution_ids":["https://openalex.org/I4210163363"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030992865","display_name":"Xiliang Chen","orcid":"https://orcid.org/0000-0001-5198-0932"},"institutions":[{"id":"https://openalex.org/I4210163363","display_name":"PLA Army Engineering University","ror":"https://ror.org/05mgp8x93","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210163363"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiliang Chen","raw_affiliation_strings":["Command and Control Engineering Institute, Army Engineering University of PLA , Nanjing, 210007 ,"],"raw_orcid":"https://orcid.org/0000-0001-5198-0932","affiliations":[{"raw_affiliation_string":"Command and Control Engineering Institute, Army Engineering University of PLA , Nanjing, 210007 ,","institution_ids":["https://openalex.org/I4210163363"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101900574","display_name":"Jun Lai","orcid":"https://orcid.org/0000-0002-3608-4985"},"institutions":[{"id":"https://openalex.org/I4210163363","display_name":"PLA Army Engineering University","ror":"https://ror.org/05mgp8x93","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210163363"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Lai","raw_affiliation_strings":["Command and Control Engineering Institute, Army Engineering University of PLA , Nanjing, 210007 ,"],"raw_orcid":"https://orcid.org/0000-0002-3608-4985","affiliations":[{"raw_affiliation_string":"Command and Control Engineering Institute, Army Engineering University of PLA , Nanjing, 210007 ,","institution_ids":["https://openalex.org/I4210163363"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024594636","display_name":"Xijian Luo","orcid":"https://orcid.org/0000-0002-4143-4521"},"institutions":[{"id":"https://openalex.org/I4210163363","display_name":"PLA Army Engineering University","ror":"https://ror.org/05mgp8x93","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210163363"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xijian Luo","raw_affiliation_strings":["Command and Control Engineering Institute, Army Engineering University of PLA , Nanjing, 210007 ,"],"raw_orcid":"https://orcid.org/0000-0002-4143-4521","affiliations":[{"raw_affiliation_string":"Command and Control Engineering Institute, Army Engineering University of PLA , Nanjing, 210007 ,","institution_ids":["https://openalex.org/I4210163363"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100381800","display_name":"Xiaoyan Wang","orcid":"https://orcid.org/0000-0002-8763-289X"},"institutions":[{"id":"https://openalex.org/I4210163363","display_name":"PLA Army Engineering University","ror":"https://ror.org/05mgp8x93","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210163363"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoyan Wang","raw_affiliation_strings":["Command and Control Engineering Institute, Army Engineering University of PLA , Nanjing, 210007 ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Command and Control Engineering Institute, Army Engineering University of PLA , Nanjing, 210007 ,","institution_ids":["https://openalex.org/I4210163363"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002294263","display_name":"Legui Zhang","orcid":"https://orcid.org/0000-0003-2768-7044"},"institutions":[{"id":"https://openalex.org/I4210163363","display_name":"PLA Army Engineering University","ror":"https://ror.org/05mgp8x93","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210163363"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Legui Zhang","raw_affiliation_strings":["Command and Control Engineering Institute, Army Engineering University of PLA , Nanjing, 210007 ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Command and Control Engineering Institute, Army Engineering University of PLA , Nanjing, 210007 ,","institution_ids":["https://openalex.org/I4210163363"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080136352","display_name":"Haoyang Dong","orcid":null},"institutions":[{"id":"https://openalex.org/I4210163363","display_name":"PLA Army Engineering University","ror":"https://ror.org/05mgp8x93","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210163363"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoyang Dong","raw_affiliation_strings":["Command and Control Engineering Institute, Army Engineering University of PLA , Nanjing, 210007 ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Command and Control Engineering Institute, Army Engineering University of PLA , Nanjing, 210007 ,","institution_ids":["https://openalex.org/I4210163363"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2635,"currency":"GBP","value_usd":3232},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0667297,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"68","issue":"11","first_page":"1628","last_page":"1640"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9937999844551086,"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":0.9937999844551086,"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/T10524","display_name":"Traffic control and management","score":0.9648000001907349,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.932699978351593,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8845786452293396},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6711385250091553},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5779697299003601},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.46292898058891296},{"id":"https://openalex.org/keywords/factorization","display_name":"Factorization","score":0.41346144676208496},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35030505061149597},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1025572121143341}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8845786452293396},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6711385250091553},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5779697299003601},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.46292898058891296},{"id":"https://openalex.org/C187834632","wikidata":"https://www.wikidata.org/wiki/Q188804","display_name":"Factorization","level":2,"score":0.41346144676208496},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35030505061149597},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1025572121143341}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1093/comjnl/bxaf063","is_oa":false,"landing_page_url":"https://doi.org/10.1093/comjnl/bxaf063","pdf_url":null,"source":{"id":"https://openalex.org/S44643521","display_name":"The Computer Journal","issn_l":"0010-4620","issn":["0010-4620","1460-2067"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Computer Journal","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W206679605","https://openalex.org/W2121092017","https://openalex.org/W2166533447","https://openalex.org/W2340985688","https://openalex.org/W2560674852","https://openalex.org/W2610466262","https://openalex.org/W2612288690","https://openalex.org/W2963658727","https://openalex.org/W2963762747","https://openalex.org/W3004640943","https://openalex.org/W3084233102","https://openalex.org/W3133862234","https://openalex.org/W3156295478","https://openalex.org/W3210096323","https://openalex.org/W4205746880","https://openalex.org/W4210806029","https://openalex.org/W4225547330","https://openalex.org/W4254300870","https://openalex.org/W4287755265","https://openalex.org/W4296471407","https://openalex.org/W4299296451","https://openalex.org/W4312985348","https://openalex.org/W4361802167","https://openalex.org/W4377141572","https://openalex.org/W4391042167","https://openalex.org/W4391753062","https://openalex.org/W6677939520","https://openalex.org/W6737849119","https://openalex.org/W6752380930","https://openalex.org/W6754964036","https://openalex.org/W6762491519","https://openalex.org/W6766805167","https://openalex.org/W6767151588","https://openalex.org/W6773620346","https://openalex.org/W6784046417","https://openalex.org/W6784152626","https://openalex.org/W6784197182","https://openalex.org/W6795154773","https://openalex.org/W6802503978","https://openalex.org/W6839077366","https://openalex.org/W6855664730","https://openalex.org/W6865063387","https://openalex.org/W7039202139"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W4387369504","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W3107602296","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347"],"abstract_inverted_index":{"Abstract":[0],"Multi-agent":[1],"credit":[2,95],"assignment":[3,96],"is":[4,19,64,178],"a":[5,79],"research":[6],"hotspot":[7],"in":[8,30,71,121,162,169,190],"the":[9,24,31,68,72,92,116,122,126,148,183],"field":[10],"of":[11,27,49,57,94,118,128,151,164,172,182],"cooperative":[12,149],"multi-agent":[13,35,85],"reinforcement":[14,87],"learning,":[15,88],"and":[16,55,167,175],"its":[17,52,176],"key":[18],"how":[20],"to":[21,33,146,180],"accurately":[22],"measure":[23],"individual":[25,107],"contribution":[26,108],"each":[28,48,112,119],"agent":[29,120],"system":[32,123],"promote":[34],"cooperation.":[36],"Existing":[37],"solutions":[38],"mainly":[39],"use":[40],"value":[41,81,130],"function":[42],"factorization":[43,82],"or":[44],"intrinsic":[45],"reward":[46],"mechanism,":[47],"which":[50,63,89,114],"has":[51],"own":[53],"limitations,":[54],"both":[56],"them":[58],"utilize":[59],"global":[60,99,187],"state":[61,100,188],"information,":[62],"not":[65],"consistent":[66],"with":[67],"information":[69,134,189],"conditions":[70],"actual":[73],"confrontation.":[74],"Therefore,":[75],"this":[76],"paper":[77],"proposes":[78],"novel":[80],"method":[83,103,158,184],"for":[84,111],"deep":[86],"can":[90],"solve":[91],"problem":[93],"without":[97],"using":[98],"information.":[101],"Our":[102],"establishes":[104],"an":[105],"explicit":[106],"evaluation":[109],"mechanism":[110],"agent,":[113],"portrays":[115],"role":[117],"by":[124],"comparing":[125],"differences":[127],"joint":[129],"functions":[131],"under":[132],"different":[133],"conditions,":[135],"so":[136,144],"that":[137,156,181],"more":[138,142],"important":[139],"agents":[140],"get":[141],"attention,":[143],"as":[145],"improve":[147],"ability":[150],"agents.":[152],"Experimental":[153],"results":[154],"show":[155],"our":[157],"outperforms":[159],"all":[160],"baselines":[161],"terms":[163],"learning":[165],"efficiency":[166],"stability":[168],"multiple":[170],"scenarios":[171],"StarCraft":[173],"II,":[174],"performance":[177],"comparable":[179],"based":[185],"on":[186],"easy":[191],"scenarios.":[192]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}