{"id":"https://openalex.org/W7125427339","doi":"https://doi.org/10.3390/robotics15010028","title":"Relaxed Monotonic QMIX (R-QMIX): A Regularized Value Factorization Approach to Decentralized Multi-Agent Reinforcement Learning","display_name":"Relaxed Monotonic QMIX (R-QMIX): A Regularized Value Factorization Approach to Decentralized Multi-Agent Reinforcement Learning","publication_year":2026,"publication_date":"2026-01-21","ids":{"openalex":"https://openalex.org/W7125427339","doi":"https://doi.org/10.3390/robotics15010028"},"language":"en","primary_location":{"id":"doi:10.3390/robotics15010028","is_oa":true,"landing_page_url":"https://doi.org/10.3390/robotics15010028","pdf_url":"https://www.mdpi.com/2218-6581/15/1/28/pdf?version=1769004334","source":{"id":"https://openalex.org/S4210232487","display_name":"Robotics","issn_l":"2218-6581","issn":["2218-6581"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Robotics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2218-6581/15/1/28/pdf?version=1769004334","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5123625939","display_name":"Liam O\u2019Brien","orcid":null},"institutions":[{"id":"https://openalex.org/I134113660","display_name":"University of Nevada, Reno","ror":"https://ror.org/01keh0577","country_code":"US","type":"education","lineage":["https://openalex.org/I134113660"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Liam O\u2019Brien","raw_affiliation_strings":["Department of Electrical and Biomedical Engineering, University of Nevada, Reno, NV 89557, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Biomedical Engineering, University of Nevada, Reno, NV 89557, USA","institution_ids":["https://openalex.org/I134113660"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5123615427","display_name":"Hao Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I134113660","display_name":"University of Nevada, Reno","ror":"https://ror.org/01keh0577","country_code":"US","type":"education","lineage":["https://openalex.org/I134113660"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Hao Xu","raw_affiliation_strings":["Department of Electrical and Biomedical Engineering, University of Nevada, Reno, NV 89557, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Biomedical Engineering, University of Nevada, Reno, NV 89557, USA","institution_ids":["https://openalex.org/I134113660"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5123615427","https://openalex.org/A5123625939"],"corresponding_institution_ids":["https://openalex.org/I134113660"],"apc_list":{"value":1600,"currency":"CHF","value_usd":1782},"apc_paid":{"value":1600,"currency":"CHF","value_usd":1782},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.08513118,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"15","issue":"1","first_page":"28","last_page":"28"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9164999723434448,"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":0.9164999723434448,"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":0.007600000128149986,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.00430000014603138,"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/monotonic-function","display_name":"Monotonic function","score":0.8802000284194946},{"id":"https://openalex.org/keywords/factorization","display_name":"Factorization","score":0.57669997215271},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.5691999793052673},{"id":"https://openalex.org/keywords/differentiable-function","display_name":"Differentiable function","score":0.5551999807357788},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.49880000948905945},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.4909999966621399},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.439300000667572},{"id":"https://openalex.org/keywords/sign","display_name":"Sign (mathematics)","score":0.37950000166893005}],"concepts":[{"id":"https://openalex.org/C72169020","wikidata":"https://www.wikidata.org/wiki/Q194404","display_name":"Monotonic function","level":2,"score":0.8802000284194946},{"id":"https://openalex.org/C187834632","wikidata":"https://www.wikidata.org/wiki/Q188804","display_name":"Factorization","level":2,"score":0.57669997215271},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.5691999793052673},{"id":"https://openalex.org/C202615002","wikidata":"https://www.wikidata.org/wiki/Q783507","display_name":"Differentiable function","level":2,"score":0.5551999807357788},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5199000239372253},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.49880000948905945},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.4909999966621399},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.439300000667572},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4187000095844269},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4129999876022339},{"id":"https://openalex.org/C139676723","wikidata":"https://www.wikidata.org/wiki/Q1193832","display_name":"Sign (mathematics)","level":2,"score":0.37950000166893005},{"id":"https://openalex.org/C138777275","wikidata":"https://www.wikidata.org/wiki/Q6884054","display_name":"Mixing (physics)","level":2,"score":0.3788999915122986},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.3456999957561493},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.3314000070095062},{"id":"https://openalex.org/C72134830","wikidata":"https://www.wikidata.org/wiki/Q5166524","display_name":"Convexity","level":2,"score":0.3255000114440918},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.32089999318122864},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.29840001463890076},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.28029999136924744},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.2700999975204468},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.2614000141620636},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.25049999356269836}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3390/robotics15010028","is_oa":true,"landing_page_url":"https://doi.org/10.3390/robotics15010028","pdf_url":"https://www.mdpi.com/2218-6581/15/1/28/pdf?version=1769004334","source":{"id":"https://openalex.org/S4210232487","display_name":"Robotics","issn_l":"2218-6581","issn":["2218-6581"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Robotics","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:8439f4fbd7aa4ad5899c46dc34737e0d","is_oa":true,"landing_page_url":"https://doaj.org/article/8439f4fbd7aa4ad5899c46dc34737e0d","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Robotics, Vol 15, Iss 1, p 28 (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/robotics15010028","is_oa":true,"landing_page_url":"https://doi.org/10.3390/robotics15010028","pdf_url":"https://www.mdpi.com/2218-6581/15/1/28/pdf?version=1769004334","source":{"id":"https://openalex.org/S4210232487","display_name":"Robotics","issn_l":"2218-6581","issn":["2218-6581"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Robotics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G266287223","display_name":"CAREER: Toward Hierarchical Game Theory and Hybrid Learning Framework for Safe, Efficient Large-scale Multi-agent Systems","funder_award_id":"2144646","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3294896131","display_name":null,"funder_award_id":"W911NF-24-2-0133","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"},{"id":"https://openalex.org/G7452299184","display_name":null,"funder_award_id":"W911NF","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320312725","display_name":"University of Nevada, Reno","ror":"https://ror.org/01keh0577"},{"id":"https://openalex.org/F4320338281","display_name":"Army Research Office","ror":"https://ror.org/05epdh915"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7125427339.pdf","grobid_xml":"https://content.openalex.org/works/W7125427339.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Value":[0],"factorization":[1,125,246,264],"methods":[2],"have":[3],"become":[4],"a":[5,37,73,101,142,158,235,260],"standard":[6,143],"tool":[7],"for":[8,25,196],"cooperative":[9],"multi-agent":[10],"reinforcement":[11],"learning":[12,170],"(MARL)":[13],"in":[14,28,141],"the":[15,31,86,91,95,109,120,128,152,164,199,240,278],"centralized-training,":[16],"decentralized-execution":[17],"(CTDE)":[18],"setting.":[19],"QMIX":[20,71,78,168],"(a":[21],"monotonic":[22,38,244],"mixing":[23,39,96],"network":[24,97],"value":[26,111,124,130,245,251,263],"factorization),":[27],"particular,":[29],"constrains":[30],"joint":[32,110,129,250],"action\u2013value":[33],"function":[34],"to":[35,114,131,206,212,221,238],"be":[36],"of":[40,77,108,123,167],"per-agent":[41],"utilities,":[42],"which":[43],"guarantees":[44],"consistency":[45],"with":[46,57,112],"individual":[47],"greedy":[48],"policies":[49],"but":[50,81],"can":[51],"severely":[52],"limit":[53],"expressiveness":[54],"on":[55,94,104,151,208,214,223,277],"tasks":[56],"non-monotonic":[58],"agent":[59],"interactions.":[60],"This":[61,118],"work":[62],"revisits":[63],"this":[64],"design":[65],"choice":[66],"and":[67,99,149,181,191,218,247,271],"proposes":[68],"Relaxed":[69],"Monotonic":[70],"(R-QMIX),":[72],"simple":[74,159],"regularized":[75],"variant":[76],"that":[79,230,267],"encourages":[80],"does":[82],"not":[83],"strictly":[84,243],"enforce":[85],"monotonicity":[87,135,232],"constraint.":[88],"R-QMIX":[89,138,162,185,268],"removes":[90],"sign":[92],"constraints":[93],"weights":[98],"introduces":[100],"differentiable":[102],"penalty":[103],"negative":[105],"partial":[106],"derivatives":[107],"respect":[113],"each":[115],"agent\u2019s":[116],"utility.":[117],"preserves":[119],"computational":[121],"benefits":[122],"while":[126,169],"allowing":[127],"deviate":[132],"from":[133,204,210,219],"strict":[134],"when":[136],"beneficial.":[137],"is":[139,234],"implemented":[140],"PyMARL":[144],"(an":[145],"open-source":[146],"MARL":[147],"codebase)":[148],"evaluated":[150],"StarCraft":[153],"Multi-Agent":[154],"Challenge":[155],"(SMAC).":[156],"On":[157,173],"map":[160],"(3m),":[161],"matches":[163],"asymptotic":[165],"performance":[166],"substantially":[171],"faster.":[172],"more":[174,261,272],"challenging":[175,279],"maps":[176,281],"(MMM2,":[177],"6h":[178,215],"vs.":[179,183,216,225],"8z,":[180,217],"27m":[182,224],"30m),":[184],"significantly":[186],"improves":[187],"both":[188],"sample":[189],"efficiency":[190],"final":[192],"win":[193,202,275],"rate":[194,203],"(WR),":[195],"example":[197],"increasing":[198],"final-quarter":[200],"mean":[201],"42.3%":[205],"97.1%":[207],"MMM2,":[209],"0.0%":[211],"57.5%":[213],"58.0%":[220],"96.6%":[222],"30m.":[226],"These":[227],"results":[228],"suggest":[229],"soft":[231],"regularization":[233],"practical":[236],"way":[237],"bridge":[239],"gap":[241],"between":[242],"fully":[248],"unconstrained":[249],"functions.":[252],"A":[253],"further":[254],"comparison":[255],"against":[256],"QTRAN":[257],"(Q-value":[258],"transformation),":[259],"expressive":[262],"method,":[265],"shows":[266],"achieves":[269],"higher":[270],"reliably":[273],"convergent":[274],"rates":[276],"SMAC":[280],"considered.":[282]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2026-01-23T00:00:00"}