{"id":"https://openalex.org/W4200342431","doi":"https://doi.org/10.1109/iros51168.2021.9636349","title":"Centralizing State-Values in Dueling Networks for Multi-Robot Reinforcement Learning Mapless Navigation","display_name":"Centralizing State-Values in Dueling Networks for Multi-Robot Reinforcement Learning Mapless Navigation","publication_year":2021,"publication_date":"2021-09-27","ids":{"openalex":"https://openalex.org/W4200342431","doi":"https://doi.org/10.1109/iros51168.2021.9636349"},"language":"en","primary_location":{"id":"doi:10.1109/iros51168.2021.9636349","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros51168.2021.9636349","pdf_url":null,"source":{"id":"https://openalex.org/S4363607734","display_name":"2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-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/A5058298540","display_name":"Enrico Marchesini","orcid":"https://orcid.org/0000-0003-1858-7279"},"institutions":[{"id":"https://openalex.org/I119439378","display_name":"University of Verona","ror":"https://ror.org/039bp8j42","country_code":"IT","type":"education","lineage":["https://openalex.org/I119439378"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Enrico Marchesini","raw_affiliation_strings":["University of Verona, Verona, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Verona, Verona, Italy","institution_ids":["https://openalex.org/I119439378"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045922629","display_name":"Alessandro Farinelli","orcid":"https://orcid.org/0000-0002-2592-5814"},"institutions":[{"id":"https://openalex.org/I119439378","display_name":"University of Verona","ror":"https://ror.org/039bp8j42","country_code":"IT","type":"education","lineage":["https://openalex.org/I119439378"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Alessandro Farinelli","raw_affiliation_strings":["University of Verona, Verona, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Verona, Verona, Italy","institution_ids":["https://openalex.org/I119439378"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.0147,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.80277264,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"4583","last_page":"4588"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":1.0,"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":1.0,"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/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9940999746322632,"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"}},{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9904000163078308,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8133866786956787},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.7210380434989929},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7125499248504639},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5940552949905396},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.5216048955917358},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.46439769864082336},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3395320177078247},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3255184590816498},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.32152843475341797},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12004846334457397},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11792948842048645},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.11005061864852905}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8133866786956787},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.7210380434989929},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7125499248504639},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5940552949905396},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5216048955917358},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.46439769864082336},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3395320177078247},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3255184590816498},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.32152843475341797},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12004846334457397},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11792948842048645},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.11005061864852905},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros51168.2021.9636349","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros51168.2021.9636349","pdf_url":null,"source":{"id":"https://openalex.org/S4363607734","display_name":"2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.47999998927116394,"id":"https://metadata.un.org/sdg/17","display_name":"Partnerships for the goals"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1518858799","https://openalex.org/W1542670833","https://openalex.org/W2158782408","https://openalex.org/W2201581102","https://openalex.org/W2215378786","https://openalex.org/W2602275733","https://openalex.org/W2617547828","https://openalex.org/W2626637010","https://openalex.org/W2746553466","https://openalex.org/W2747213132","https://openalex.org/W2754517384","https://openalex.org/W2761873684","https://openalex.org/W2769883686","https://openalex.org/W2949963774","https://openalex.org/W2951799221","https://openalex.org/W2963019567","https://openalex.org/W2963322416","https://openalex.org/W2963821308","https://openalex.org/W3002855444","https://openalex.org/W3037430760","https://openalex.org/W3089695338","https://openalex.org/W3119977777","https://openalex.org/W3120345700","https://openalex.org/W3185656037","https://openalex.org/W4288091739","https://openalex.org/W4295252942","https://openalex.org/W4295598622","https://openalex.org/W4299802797","https://openalex.org/W6685444567","https://openalex.org/W6687681856","https://openalex.org/W6735650757","https://openalex.org/W6738796088","https://openalex.org/W6739516088","https://openalex.org/W6749304979","https://openalex.org/W6762491519","https://openalex.org/W6767327128","https://openalex.org/W6779884726","https://openalex.org/W6788085919","https://openalex.org/W6798969013","https://openalex.org/W6864424756"],"related_works":["https://openalex.org/W4362501864","https://openalex.org/W4306904969","https://openalex.org/W4380318855","https://openalex.org/W2138720691","https://openalex.org/W2031695474","https://openalex.org/W2586732548","https://openalex.org/W3049728571","https://openalex.org/W20361778","https://openalex.org/W2110944602","https://openalex.org/W3213722473"],"abstract_inverted_index":{"We":[0],"study":[1],"the":[2,9,51,73,120,124,134,137,141,146,156,161,173,194],"problem":[3,19],"of":[4,75,123,140,148,155,163,197],"multi-robot":[5],"mapless":[6],"navigation":[7,185],"in":[8,41,78,119,182],"popular":[10],"Centralized":[11],"Training":[12],"and":[13,35,61,190],"Decentralized":[14],"Execution":[15],"(CTDE)":[16],"paradigm.":[17],"This":[18],"is":[20,84,112,176,178],"challenging":[21],"when":[22],"each":[23,82,127,169],"robot":[24,170],"considers":[25],"its":[26,130],"path":[27],"without":[28],"explicitly":[29],"sharing":[30],"observations":[31],"with":[32,187],"other":[33],"robots":[34],"can":[36],"lead":[37],"to":[38,58,106,114],"non-stationary":[39],"issues":[40],"Deep":[42],"Reinforcement":[43],"Learning":[44],"(DRL).":[45],"The":[46],"typical":[47],"CTDE":[48,99,202],"algorithm":[49],"factorizes":[50],"joint":[52,89,109,157],"action-value":[53],"function":[54],"into":[55],"individual":[56,80],"ones,":[57],"favor":[59],"cooperation":[60],"achieve":[62],"decentralized":[63],"execution.":[64],"Such":[65],"factorization":[66],"involves":[67],"constraints":[68],"(e.g.,":[69,204],"monotonicity)":[70],"that":[71,100],"limit":[72],"emergence":[74],"novel":[76,96],"behaviors":[77],"an":[79],"as":[81,151],"agent":[83],"trained":[85],"starting":[86],"from":[87],"a":[88,95,102,108,152,183],"action-value.":[90],"In":[91],"contrast,":[92],"we":[93],"propose":[94],"architecture":[97],"for":[98,133],"uses":[101],"centralized":[103],"state-value":[104,158],"network":[105],"compute":[107],"state-value,":[110],"which":[111],"used":[113],"inject":[115],"global":[116,174],"state":[117,139,175],"information":[118,171],"value-based":[121],"updates":[122],"agents.":[125],"Consequently,":[126],"model":[128],"computes":[129],"gradient":[131],"update":[132],"weights,":[135],"considering":[136],"overall":[138],"environment.":[142],"Our":[143],"idea":[144],"follows":[145],"insights":[147],"Dueling":[149],"Networks":[150],"separate":[153],"estimation":[154],"has":[159],"both":[160],"advantage":[162],"improving":[164],"sample":[165],"efficiency,":[166],"while":[167],"providing":[168],"whether":[172],"(or":[177],"not)":[179],"valuable.":[180],"Experiments":[181],"robotic":[184],"task":[186],"2":[188],"4,":[189],"8":[191],"robots,":[192],"confirm":[193],"superior":[195],"performance":[196],"our":[198],"approach":[199],"over":[200],"prior":[201],"methods":[203],"VDN,":[205],"QMIX).":[206]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}