{"id":"https://openalex.org/W4394843610","doi":"https://doi.org/10.3389/frobt.2024.1229026","title":"Decentralized multi-agent reinforcement learning based on best-response policies","display_name":"Decentralized multi-agent reinforcement learning based on best-response policies","publication_year":2024,"publication_date":"2024-04-16","ids":{"openalex":"https://openalex.org/W4394843610","doi":"https://doi.org/10.3389/frobt.2024.1229026","pmid":"https://pubmed.ncbi.nlm.nih.gov/38690119"},"language":"en","primary_location":{"id":"doi:10.3389/frobt.2024.1229026","is_oa":true,"landing_page_url":"https://doi.org/10.3389/frobt.2024.1229026","pdf_url":"https://www.frontiersin.org/articles/10.3389/frobt.2024.1229026/pdf?isPublishedV2=False","source":{"id":"https://openalex.org/S2595095599","display_name":"Frontiers in Robotics and AI","issn_l":"2296-9144","issn":["2296-9144"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Robotics and AI","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.frontiersin.org/articles/10.3389/frobt.2024.1229026/pdf?isPublishedV2=False","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5078469731","display_name":"Volker Gabler","orcid":"https://orcid.org/0000-0002-9915-213X"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Volker Gabler","raw_affiliation_strings":["Chair of Automatic Control Engineering, TUM School of Computation, Information and Technology, Technical University of Munich, Munich, Germany","Chair of Automatic Control Engineering, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chair of Automatic Control Engineering, TUM School of Computation, Information and Technology, Technical University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Chair of Automatic Control Engineering, Germany","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061769472","display_name":"Dirk Wollherr","orcid":"https://orcid.org/0000-0003-2810-6790"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Dirk Wollherr","raw_affiliation_strings":["Chair of Automatic Control Engineering, TUM School of Computation, Information and Technology, Technical University of Munich, Munich, Germany","Chair of Automatic Control Engineering, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chair of Automatic Control Engineering, TUM School of Computation, Information and Technology, Technical University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Chair of Automatic Control Engineering, Germany","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I62916508"],"apc_list":{"value":2125,"currency":"USD","value_usd":2125},"apc_paid":{"value":2125,"currency":"USD","value_usd":2125},"fwci":3.1591,"has_fulltext":true,"cited_by_count":13,"citation_normalized_percentile":{"value":0.92243411,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"11","issue":null,"first_page":"1229026","last_page":"1229026"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9983000159263611,"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":0.9983000159263611,"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":0.9692000150680542,"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/T10646","display_name":"Experimental Behavioral Economics Studies","score":0.9603999853134155,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.9041844010353088},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8360629081726074},{"id":"https://openalex.org/keywords/stackelberg-competition","display_name":"Stackelberg competition","score":0.6517573595046997},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.509175717830658},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4989302158355713},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.49846744537353516},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.49770429730415344},{"id":"https://openalex.org/keywords/autonomous-agent","display_name":"Autonomous agent","score":0.4697090983390808},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.4581716060638428},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.34834936261177063}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9041844010353088},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8360629081726074},{"id":"https://openalex.org/C199510392","wikidata":"https://www.wikidata.org/wiki/Q1184602","display_name":"Stackelberg competition","level":2,"score":0.6517573595046997},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.509175717830658},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4989302158355713},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.49846744537353516},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.49770429730415344},{"id":"https://openalex.org/C13687954","wikidata":"https://www.wikidata.org/wiki/Q4826847","display_name":"Autonomous agent","level":2,"score":0.4697090983390808},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.4581716060638428},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.34834936261177063},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","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},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.3389/frobt.2024.1229026","is_oa":true,"landing_page_url":"https://doi.org/10.3389/frobt.2024.1229026","pdf_url":"https://www.frontiersin.org/articles/10.3389/frobt.2024.1229026/pdf?isPublishedV2=False","source":{"id":"https://openalex.org/S2595095599","display_name":"Frontiers in Robotics and AI","issn_l":"2296-9144","issn":["2296-9144"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Robotics and AI","raw_type":"journal-article"},{"id":"pmid:38690119","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38690119","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":"Frontiers in robotics and AI","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:11059992","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/11059992","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC11059992/pdf/frobt-11-1229026.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Front Robot AI","raw_type":"Text"},{"id":"pmh:oai:doaj.org/article:b4498e6898414c9fb850b713d7b40157","is_oa":true,"landing_page_url":"https://doaj.org/article/b4498e6898414c9fb850b713d7b40157","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":"Frontiers in Robotics and AI, Vol 11 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3389/frobt.2024.1229026","is_oa":true,"landing_page_url":"https://doi.org/10.3389/frobt.2024.1229026","pdf_url":"https://www.frontiersin.org/articles/10.3389/frobt.2024.1229026/pdf?isPublishedV2=False","source":{"id":"https://openalex.org/S2595095599","display_name":"Frontiers in Robotics and AI","issn_l":"2296-9144","issn":["2296-9144"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Robotics and AI","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4394843610.pdf"},"referenced_works_count":62,"referenced_works":["https://openalex.org/W398859631","https://openalex.org/W1542941925","https://openalex.org/W1579184372","https://openalex.org/W1682403713","https://openalex.org/W1949804828","https://openalex.org/W1977655452","https://openalex.org/W2067050450","https://openalex.org/W2076337359","https://openalex.org/W2107726111","https://openalex.org/W2109606373","https://openalex.org/W2109910161","https://openalex.org/W2145339207","https://openalex.org/W2257979135","https://openalex.org/W2474696542","https://openalex.org/W2525579820","https://openalex.org/W2575731723","https://openalex.org/W2593390416","https://openalex.org/W2798511001","https://openalex.org/W2904246096","https://openalex.org/W2904455790","https://openalex.org/W2908261578","https://openalex.org/W2920215304","https://openalex.org/W2945529113","https://openalex.org/W2963864421","https://openalex.org/W2975395546","https://openalex.org/W2981038142","https://openalex.org/W2982316857","https://openalex.org/W2991046523","https://openalex.org/W3003257820","https://openalex.org/W3045100301","https://openalex.org/W3089506933","https://openalex.org/W3100789280","https://openalex.org/W3103145119","https://openalex.org/W3133715761","https://openalex.org/W3170007158","https://openalex.org/W4200635426","https://openalex.org/W4206273864","https://openalex.org/W4252284432","https://openalex.org/W4254547512","https://openalex.org/W4299802797","https://openalex.org/W4301109798","https://openalex.org/W4302570325","https://openalex.org/W6631190155","https://openalex.org/W6632558091","https://openalex.org/W6638018090","https://openalex.org/W6640712829","https://openalex.org/W6683204974","https://openalex.org/W6684205842","https://openalex.org/W6684921986","https://openalex.org/W6697285542","https://openalex.org/W6737849119","https://openalex.org/W6738796088","https://openalex.org/W6750393176","https://openalex.org/W6755069753","https://openalex.org/W6757470271","https://openalex.org/W6758763022","https://openalex.org/W6759871227","https://openalex.org/W6762790178","https://openalex.org/W6768017362","https://openalex.org/W6775761296","https://openalex.org/W6780461016","https://openalex.org/W6783487004"],"related_works":["https://openalex.org/W4206233823","https://openalex.org/W2494202692","https://openalex.org/W2161520603","https://openalex.org/W2612836981","https://openalex.org/W2604958989","https://openalex.org/W2618716983","https://openalex.org/W2032491180","https://openalex.org/W2620638075","https://openalex.org/W1586030051","https://openalex.org/W2372480026"],"abstract_inverted_index":{"Introduction:":[0],"Multi-agent":[1],"systems":[2],"are":[3],"an":[4,87],"interdisciplinary":[5],"research":[6,43,281],"field":[7],"that":[8,67,131,279],"describes":[9],"the":[10,24,53,56,93,122,133,152,168,177,185,191,201,249,265],"concept":[11],"of":[12,99,128,204,276],"multiple":[13],"decisive":[14],"individuals":[15],"interacting":[16],"with":[17],"a":[18,46,68,83,96,105,126,217,222,254],"usually":[19],"partially":[20],"observable":[21],"environment.":[22,259],"Given":[23],"recent":[25,40],"advances":[26],"in":[27,39,76,115],"single-agent":[28,57],"reinforcement":[29,32],"learning,":[30],"multi-agent":[31,60,258],"learning":[33,49,70,84],"(RL)":[34],"has":[35],"gained":[36],"tremendous":[37],"interest":[38],"years.":[41],"Most":[42],"studies":[44],"apply":[45],"fully":[47,235],"centralized":[48],"scheme":[50,71],"to":[51,59,95,111,149,172,183],"ease":[52],"transfer":[54],"from":[55],"domain":[58],"systems.":[61],"Methods:":[62],"In":[63,139],"contrast,":[64],"we":[65,141,207,268],"claim":[66],"decentralized":[69,236],"is":[72],"preferable":[73],"for":[74],"applications":[75],"real-world":[77],"scenarios":[78],"as":[79,136,159],"this":[80,102,196,270],"allows":[81,234],"deploying":[82,92],"algorithm":[85,94,233,278],"on":[86,190,200,214],"individual":[88],"robot":[89],"rather":[90],"than":[91],"complete":[97],"fleet":[98],"robots.":[100],"Therefore,":[101],"article":[103,271],"outlines":[104],"novel":[106],"actor\u2013critic":[107],"(AC)":[108],"approach":[109,120,262],"tailored":[110],"cooperative":[112],"MARL":[113,123],"problems":[114],"sparsely":[116,255],"rewarded":[117,256],"domains.":[118],"Our":[119],"decouples":[121],"problem":[124],"into":[125],"set":[127],"distributed":[129],"agents":[130,135],"model":[132],"other":[134,178],"responsive":[137],"entities.":[138],"particular,":[140],"propose":[142],"using":[143,248],"two":[144,209],"separate":[145],"critics":[146],"per":[147],"agent":[148,181],"distinguish":[150],"between":[151],"joint":[153,186,192,202],"task":[154,193],"reward":[155,188],"and":[156,221,238,241],"agent-based":[157,169],"costs":[158],"commonly":[160],"applied":[161],"within":[162,253],"multi-robot":[163],"planning.":[164],"On":[165,176],"one":[166],"hand,":[167,179],"critic":[170,197],"intends":[171,182],"decrease":[173],"agent-specific":[174],"costs.":[175],"each":[180,226],"optimize":[184],"team":[187],"based":[189,213],"critic.":[194],"As":[195],"still":[198],"depends":[199],"action":[203],"all":[205],"agents,":[206],"outline":[208],"suitable":[210],"behavior":[211,230,251],"models":[212,252],"Stackelberg":[215],"games:":[216],"game":[218,224],"against":[219,225],"nature":[220],"dyadic":[223],"agent.":[227],"Following":[228],"these":[229],"models,":[231],"our":[232,245,261,277],"execution":[237],"training.":[239],"Results":[240],"Discussion:":[242],"We":[243],"evaluate":[244],"presented":[246],"method":[247],"proposed":[250],"simulated":[257],"Although":[260],"already":[263],"outperforms":[264],"state-of-the-art":[266],"learners,":[267],"conclude":[269],"by":[272],"outlining":[273],"possible":[274],"extensions":[275],"future":[280],"may":[282],"build":[283],"upon.":[284]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":11}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}