{"id":"https://openalex.org/W2963302418","doi":"https://doi.org/10.1109/icra.2018.8463211","title":"Intent-Aware Multi-Agent Reinforcement Learning","display_name":"Intent-Aware Multi-Agent Reinforcement Learning","publication_year":2018,"publication_date":"2018-05-01","ids":{"openalex":"https://openalex.org/W2963302418","doi":"https://doi.org/10.1109/icra.2018.8463211","mag":"2963302418"},"language":"en","primary_location":{"id":"doi:10.1109/icra.2018.8463211","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra.2018.8463211","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},"type":"preprint","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/A5043510420","display_name":"Siyuan Qi","orcid":"https://orcid.org/0000-0002-4070-733X"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Siyuan Qi","raw_affiliation_strings":["University of California, Los Angeles"],"affiliations":[{"raw_affiliation_string":"University of California, Los Angeles","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034228010","display_name":"Song\u2010Chun Zhu","orcid":"https://orcid.org/0009-0008-0876-8117"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Song-Chun Zhu","raw_affiliation_strings":["University of California, Los Angeles"],"affiliations":[{"raw_affiliation_string":"University of California, Los Angeles","institution_ids":["https://openalex.org/I161318765"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5043510420"],"corresponding_institution_ids":["https://openalex.org/I161318765"],"apc_list":null,"apc_paid":null,"fwci":2.8688,"has_fulltext":false,"cited_by_count":35,"citation_normalized_percentile":{"value":0.92961198,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"7533","last_page":"7540"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9987000226974487,"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":0.9987000226974487,"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/T10656","display_name":"Child and Animal Learning Development","score":0.9837999939918518,"subfield":{"id":"https://openalex.org/subfields/3204","display_name":"Developmental and Educational Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11252","display_name":"Evolutionary Game Theory and Cooperation","score":0.9771000146865845,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"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/partially-observable-markov-decision-process","display_name":"Partially observable Markov decision process","score":0.8062107563018799},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8062037825584412},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7487143278121948},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7124181985855103},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.665269136428833},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5749003887176514},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5658676624298096},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5327439904212952},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5307433605194092},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4859146177768707},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4794172942638397},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.41580620408058167},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3471946716308594},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.31999439001083374},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.20855045318603516},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10645830631256104}],"concepts":[{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.8062107563018799},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8062037825584412},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7487143278121948},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7124181985855103},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.665269136428833},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5749003887176514},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5658676624298096},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5327439904212952},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5307433605194092},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4859146177768707},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4794172942638397},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.41580620408058167},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3471946716308594},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.31999439001083374},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.20855045318603516},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10645830631256104},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra.2018.8463211","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra.2018.8463211","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.7400000095367432}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":63,"referenced_works":["https://openalex.org/W155097506","https://openalex.org/W1513468570","https://openalex.org/W1519840480","https://openalex.org/W1531590217","https://openalex.org/W1560074431","https://openalex.org/W1605929701","https://openalex.org/W1641379095","https://openalex.org/W1973039793","https://openalex.org/W1974955132","https://openalex.org/W1976056313","https://openalex.org/W1992461594","https://openalex.org/W2025338721","https://openalex.org/W2078993594","https://openalex.org/W2082511574","https://openalex.org/W2085366587","https://openalex.org/W2099618002","https://openalex.org/W2101915445","https://openalex.org/W2104602264","https://openalex.org/W2110762409","https://openalex.org/W2120327309","https://openalex.org/W2128643385","https://openalex.org/W2137096508","https://openalex.org/W2149551746","https://openalex.org/W2151516755","https://openalex.org/W2188746823","https://openalex.org/W2210428523","https://openalex.org/W2415953079","https://openalex.org/W2561428047","https://openalex.org/W2592798481","https://openalex.org/W2738701519","https://openalex.org/W2771075179","https://openalex.org/W2901136733","https://openalex.org/W2962731062","https://openalex.org/W2963037989","https://openalex.org/W2963150791","https://openalex.org/W2963658727","https://openalex.org/W2966896140","https://openalex.org/W3041202696","https://openalex.org/W4210786910","https://openalex.org/W4299802797","https://openalex.org/W6628973269","https://openalex.org/W6630520071","https://openalex.org/W6631197528","https://openalex.org/W6633472260","https://openalex.org/W6636376383","https://openalex.org/W6637033378","https://openalex.org/W6648315218","https://openalex.org/W6670693114","https://openalex.org/W6671000503","https://openalex.org/W6672070530","https://openalex.org/W6675811377","https://openalex.org/W6688266214","https://openalex.org/W6715959869","https://openalex.org/W6730961451","https://openalex.org/W6734678876","https://openalex.org/W6737943933","https://openalex.org/W6738796088","https://openalex.org/W6740017579","https://openalex.org/W6741546182","https://openalex.org/W6742687009","https://openalex.org/W6746454999","https://openalex.org/W6756486208","https://openalex.org/W6766854325"],"related_works":["https://openalex.org/W2096013579","https://openalex.org/W1589140671","https://openalex.org/W1760611253","https://openalex.org/W52153049","https://openalex.org/W3096874164","https://openalex.org/W2951545791","https://openalex.org/W1515117609","https://openalex.org/W2294884454","https://openalex.org/W2937181779","https://openalex.org/W2386410636"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"an":[3,17,82],"intent-aware":[4],"multi-agent":[5],"planning":[6,30,116],"framework":[7,92],"as":[8,10,47],"well":[9],"a":[11,48,57,88,135,157,169,173],"learning":[12,45],"algorithm.":[13],"Under":[14],"this":[15],"framework,":[16],"agent":[18],"plans":[19],"in":[20,126,134,156,159,168],"the":[21,26,33,44,65,72,127,142,183,191],"goal":[22],"space":[23],"to":[24,104],"maximize":[25],"expected":[27],"utility.":[28],"The":[29,90],"process":[31,53],"takes":[32],"belief":[34],"of":[35,42,64,144],"other":[36,77],"agents'":[37],"intents":[38,79],"into":[39],"consideration.":[40],"Instead":[41],"formulating":[43],"problem":[46,137],"partially":[49],"observable":[50],"Markov":[51],"decision":[52],"(POMDP),":[54],"we":[55],"propose":[56],"simple":[58],"but":[59],"effective":[60],"linear":[61],"function":[62],"approximation":[63],"utility":[66,86],"function.":[67],"It":[68,107,119],"is":[69,99,139,154],"based":[70],"on":[71,84],"observation":[73],"that":[74,138,179],"for":[75,87],"humans,":[76],"people's":[78],"will":[80],"pose":[81],"influence":[83],"our":[85,132,180],"goal.":[89],"proposed":[91],"has":[93],"several":[94],"major":[95],"advantages:":[96],"i)":[97],"it":[98],"computationally":[100],"feasible":[101],"and":[102,114,141,146,163,166,186],"guaranteed":[103],"converge.":[105],"ii)":[106],"can":[108,148],"easily":[109],"integrate":[110],"existing":[111],"intent":[112],"prediction":[113],"low-level":[115],"algorithms.":[117],"iii)":[118],"does":[120],"not":[121],"suffer":[122],"from":[123],"sparse":[124],"feedbacks":[125],"action":[128],"space.":[129],"We":[130],"experiment":[131],"algorithm":[133,153,181],"real-world":[136],"non-episodic,":[140],"number":[143],"agents":[145],"goals":[147],"vary":[149],"over":[150],"time.":[151],"Our":[152],"trained":[155],"scene":[158,171],"which":[160],"aerial":[161],"robots":[162],"humans":[164],"interact,":[165],"tested":[167],"novel":[170],"with":[172],"different":[174],"environment.":[175],"Experimental":[176],"results":[177],"show":[178],"achieves":[182],"best":[184],"performance":[185],"human-like":[187],"behaviors":[188],"emerge":[189],"during":[190],"dynamic":[192],"process.":[193]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":4}],"updated_date":"2026-03-12T08:34:05.389933","created_date":"2025-10-10T00:00:00"}