{"id":"https://openalex.org/W4221145105","doi":"https://doi.org/10.1109/iros47612.2022.9981441","title":"DARL1N: Distributed multi-Agent Reinforcement Learning with One-hop Neighbors","display_name":"DARL1N: Distributed multi-Agent Reinforcement Learning with One-hop Neighbors","publication_year":2022,"publication_date":"2022-10-23","ids":{"openalex":"https://openalex.org/W4221145105","doi":"https://doi.org/10.1109/iros47612.2022.9981441"},"language":"en","primary_location":{"id":"doi:10.1109/iros47612.2022.9981441","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros47612.2022.9981441","pdf_url":null,"source":{"id":"https://openalex.org/S4363607704","display_name":"2022 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":"2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5017869089","display_name":"Baoqian Wang","orcid":"https://orcid.org/0000-0002-1977-5100"},"institutions":[{"id":"https://openalex.org/I26538001","display_name":"San Diego State University","ror":"https://ror.org/0264fdx42","country_code":"US","type":"education","lineage":["https://openalex.org/I26538001"]},{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Baoqian Wang","raw_affiliation_strings":["University of California San Diego and San Diego State University,Department of Electrical and Computer Engineering,La Jolla,CA,92093"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California San Diego and San Diego State University,Department of Electrical and Computer Engineering,La Jolla,CA,92093","institution_ids":["https://openalex.org/I26538001","https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063416695","display_name":"Junfei Xie","orcid":"https://orcid.org/0000-0001-7406-3221"},"institutions":[{"id":"https://openalex.org/I26538001","display_name":"San Diego State University","ror":"https://ror.org/0264fdx42","country_code":"US","type":"education","lineage":["https://openalex.org/I26538001"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Junfei Xie","raw_affiliation_strings":["San Diego State University,Department of Electrical and Computer Engineering,San Diego,CA,92182"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"San Diego State University,Department of Electrical and Computer Engineering,San Diego,CA,92182","institution_ids":["https://openalex.org/I26538001"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066400889","display_name":"Nikolay Atanasov","orcid":"https://orcid.org/0000-0003-0272-7580"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nikolay Atanasov","raw_affiliation_strings":["University of California San Diego,Department of Electrical and Computer Engineering,La Jolla,CA,92093"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California San Diego,Department of Electrical and Computer Engineering,La Jolla,CA,92093","institution_ids":["https://openalex.org/I36258959"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"9003","last_page":"9010"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9649999737739563,"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/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9535999894142151,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8854817748069763},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.7579751014709473},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6838843822479248},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.5790375471115112},{"id":"https://openalex.org/keywords/hop","display_name":"Hop (telecommunications)","score":0.45734405517578125},{"id":"https://openalex.org/keywords/curse","display_name":"Curse","score":0.4433248043060303},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.4300636649131775},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39723923802375793},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3870369493961334},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.25306445360183716},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11861789226531982},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.07879588007926941}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8854817748069763},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.7579751014709473},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6838843822479248},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.5790375471115112},{"id":"https://openalex.org/C25906391","wikidata":"https://www.wikidata.org/wiki/Q1432381","display_name":"Hop (telecommunications)","level":2,"score":0.45734405517578125},{"id":"https://openalex.org/C2780273121","wikidata":"https://www.wikidata.org/wiki/Q109411","display_name":"Curse","level":2,"score":0.4433248043060303},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.4300636649131775},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39723923802375793},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3870369493961334},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.25306445360183716},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11861789226531982},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.07879588007926941},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros47612.2022.9981441","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros47612.2022.9981441","pdf_url":null,"source":{"id":"https://openalex.org/S4363607704","display_name":"2022 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":"2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.6100000143051147,"id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G7046165531","display_name":null,"funder_award_id":"CAREER-2048266,CRI-1953048","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W206679605","https://openalex.org/W569478347","https://openalex.org/W1583837637","https://openalex.org/W1639167632","https://openalex.org/W1788292158","https://openalex.org/W2110906765","https://openalex.org/W2617547828","https://openalex.org/W2915117209","https://openalex.org/W2993990522","https://openalex.org/W3002395438","https://openalex.org/W3034741641","https://openalex.org/W3163894240","https://openalex.org/W3168414797","https://openalex.org/W4214717370","https://openalex.org/W4286748781","https://openalex.org/W4299802797","https://openalex.org/W6600255050","https://openalex.org/W6676769901","https://openalex.org/W6677834374","https://openalex.org/W6738796088","https://openalex.org/W6747941106","https://openalex.org/W6749304979","https://openalex.org/W6752380930","https://openalex.org/W6755069753","https://openalex.org/W6762491519","https://openalex.org/W6768531814","https://openalex.org/W6771232374","https://openalex.org/W6771904302"],"related_works":["https://openalex.org/W2561617217","https://openalex.org/W3158353707","https://openalex.org/W3088621770","https://openalex.org/W4287662386","https://openalex.org/W2115449043","https://openalex.org/W2808418668","https://openalex.org/W3149091143","https://openalex.org/W4287865573","https://openalex.org/W2025663273","https://openalex.org/W3007324819"],"abstract_inverted_index":{"Multi-agent":[0],"reinforcement":[1],"learning":[2],"(MARL)":[3],"meth-ods":[4],"face":[5],"a":[6,91,118,133],"curse":[7,67],"of":[8,20,25,68,108,116,131,136,143,166],"dimensionality":[9,69],"in":[10,122],"the":[11,18,35,39,66,76,95,113,128,137,141,164],"policy":[12,88,161],"and":[13,70,87,106],"value":[14,86],"function":[15],"representations":[16],"as":[17,163],"number":[19,165],"agents":[21,167],"increases.":[22,168],"The":[23],"development":[24],"distributed":[26,72,119],"or":[27],"parallel":[28],"training":[29,73,102,120,142,157],"techniques":[30],"is":[31,58],"also":[32],"hindered":[33],"by":[34,74,101],"global":[36],"coupling":[37],"among":[38],"agent":[40,77,83],"dynamics,":[41],"requiring":[42],"simultaneous":[43],"state":[44,129],"transitions.":[45],"This":[46,110],"paper":[47],"introduces":[48],"Distributed":[49],"multi-Agent":[50],"Reinforcement":[51],"Learning":[52],"with":[53,103,148],"One-hop":[54],"Neighbors":[55],"(DARLIN).":[56],"DARLIN":[57,154],"an":[59],"off-policy":[60],"actor-critic":[61],"MARL":[62,145,150],"method":[63],"that":[64,153],"breaks":[65],"achieves":[71],"restricting":[75],"interactions":[78],"to":[79],"one-hop":[80,92],"neighborhoods.":[81],"Each":[82],"optimizes":[84],"its":[85],"functions":[89],"over":[90],"neighborhood,":[93],"reducing":[94],"representation":[96],"complexity,":[97],"yet":[98],"maintaining":[99],"expressiveness":[100],"varying":[104],"numbers":[105],"states":[107],"neighbors.":[109],"structure":[111],"enables":[112],"key":[114],"contribution":[115],"DARLIN:":[117],"procedure":[121],"which":[123],"each":[124],"compute":[125],"node":[126],"simulates":[127],"transitions":[130],"only":[132],"small":[134],"subset":[135],"agents,":[138],"greatly":[139],"accelerating":[140],"large-scale":[144],"policies.":[146],"Comparisons":[147],"state-of-the-art":[149],"methods":[151],"show":[152],"significantly":[155],"reduces":[156],"time":[158],"without":[159],"sacrificing":[160],"quality":[162]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}