{"id":"https://openalex.org/W3201419494","doi":"https://doi.org/10.1109/ijcnn52387.2021.9533975","title":"Domain-Aware Multiagent Reinforcement Learning in Navigation","display_name":"Domain-Aware Multiagent Reinforcement Learning in Navigation","publication_year":2021,"publication_date":"2021-07-18","ids":{"openalex":"https://openalex.org/W3201419494","doi":"https://doi.org/10.1109/ijcnn52387.2021.9533975","mag":"3201419494"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn52387.2021.9533975","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn52387.2021.9533975","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Joint Conference on Neural Networks (IJCNN)","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/A5110803897","display_name":"Ifrah Saeed","orcid":"https://orcid.org/0000-0002-0556-1080"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Ifrah Saeed","raw_affiliation_strings":["The University of Melbourne,Department of Electrical and Electronic Engineering,Australia"],"affiliations":[{"raw_affiliation_string":"The University of Melbourne,Department of Electrical and Electronic Engineering,Australia","institution_ids":["https://openalex.org/I165779595"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080710876","display_name":"Andrew C. Cullen","orcid":"https://orcid.org/0000-0001-8243-6470"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Andrew C. Cullen","raw_affiliation_strings":["The University of Melbourne,School of Computing and Information Systems,Australia","School of Computing and Information Systems, The University of Melbourne, Australia"],"affiliations":[{"raw_affiliation_string":"The University of Melbourne,School of Computing and Information Systems,Australia","institution_ids":["https://openalex.org/I165779595"]},{"raw_affiliation_string":"School of Computing and Information Systems, The University of Melbourne, Australia","institution_ids":["https://openalex.org/I165779595"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070030398","display_name":"Sarah Erfani","orcid":"https://orcid.org/0000-0003-0885-0643"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Sarah Erfani","raw_affiliation_strings":["The University of Melbourne,School of Computing and Information Systems,Australia","School of Computing and Information Systems, The University of Melbourne, Australia"],"affiliations":[{"raw_affiliation_string":"The University of Melbourne,School of Computing and Information Systems,Australia","institution_ids":["https://openalex.org/I165779595"]},{"raw_affiliation_string":"School of Computing and Information Systems, The University of Melbourne, Australia","institution_ids":["https://openalex.org/I165779595"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060997326","display_name":"Tansu Alpcan","orcid":"https://orcid.org/0000-0002-7434-3239"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Tansu Alpcan","raw_affiliation_strings":["The University of Melbourne,Department of Electrical and Electronic Engineering,Australia"],"affiliations":[{"raw_affiliation_string":"The University of Melbourne,Department of Electrical and Electronic Engineering,Australia","institution_ids":["https://openalex.org/I165779595"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5110803897"],"corresponding_institution_ids":["https://openalex.org/I165779595"],"apc_list":null,"apc_paid":null,"fwci":0.136,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.55267159,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"97","issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9901999831199646,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.98580002784729,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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":0.9339255094528198},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7958885431289673},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.6886346936225891},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5619459748268127},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.5451759696006775},{"id":"https://openalex.org/keywords/a-priori-and-a-posteriori","display_name":"A priori and a posteriori","score":0.5082647204399109},{"id":"https://openalex.org/keywords/domain-knowledge","display_name":"Domain knowledge","score":0.4716108441352844},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.41182610392570496}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9339255094528198},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7958885431289673},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.6886346936225891},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5619459748268127},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.5451759696006775},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.5082647204399109},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.4716108441352844},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41182610392570496},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn52387.2021.9533975","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn52387.2021.9533975","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4959948828","display_name":null,"funder_award_id":"DP190102828","funder_id":"https://openalex.org/F4320334704","funder_display_name":"Australian Research Council"}],"funders":[{"id":"https://openalex.org/F4320315885","display_name":"Australian Government","ror":"https://ror.org/0314h5y94"},{"id":"https://openalex.org/F4320334704","display_name":"Australian Research Council","ror":"https://ror.org/05mmh0f86"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":62,"referenced_works":["https://openalex.org/W119236796","https://openalex.org/W1542941925","https://openalex.org/W1777239053","https://openalex.org/W2097381042","https://openalex.org/W2121863487","https://openalex.org/W2156737235","https://openalex.org/W2168148394","https://openalex.org/W2507578125","https://openalex.org/W2602275733","https://openalex.org/W2604382266","https://openalex.org/W2617547828","https://openalex.org/W2781726626","https://openalex.org/W2798511001","https://openalex.org/W2894976951","https://openalex.org/W2910851905","https://openalex.org/W2921955147","https://openalex.org/W2953708620","https://openalex.org/W2962938168","https://openalex.org/W2962966033","https://openalex.org/W2963407617","https://openalex.org/W2963881016","https://openalex.org/W2964095117","https://openalex.org/W2964096423","https://openalex.org/W2965307502","https://openalex.org/W2973203378","https://openalex.org/W2981038142","https://openalex.org/W2991046523","https://openalex.org/W2995559018","https://openalex.org/W3001618744","https://openalex.org/W3034769194","https://openalex.org/W3034971464","https://openalex.org/W3037881682","https://openalex.org/W3037917444","https://openalex.org/W3038822267","https://openalex.org/W3041148953","https://openalex.org/W3089418186","https://openalex.org/W4214717370","https://openalex.org/W4287750003","https://openalex.org/W4287904064","https://openalex.org/W4288796004","https://openalex.org/W4297627396","https://openalex.org/W4299802797","https://openalex.org/W6604948569","https://openalex.org/W6638088447","https://openalex.org/W6674600207","https://openalex.org/W6683195989","https://openalex.org/W6735650757","https://openalex.org/W6737849119","https://openalex.org/W6738796088","https://openalex.org/W6747473740","https://openalex.org/W6749859622","https://openalex.org/W6750393176","https://openalex.org/W6755069753","https://openalex.org/W6771101658","https://openalex.org/W6771274123","https://openalex.org/W6772070198","https://openalex.org/W6773222559","https://openalex.org/W6775529125","https://openalex.org/W6780041639","https://openalex.org/W6780856455","https://openalex.org/W6781016291","https://openalex.org/W6783566100"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W4388311650","https://openalex.org/W5922282","https://openalex.org/W1974056099","https://openalex.org/W4245343541","https://openalex.org/W2386077341","https://openalex.org/W1583422155","https://openalex.org/W1649619740","https://openalex.org/W3213252596","https://openalex.org/W1534006406"],"abstract_inverted_index":{"Multiagent":[0,84],"reinforcement":[1,52,100,131],"learning":[2,53,95,101,132],"has":[3],"shown":[4],"success":[5],"in":[6,11,142],"guiding":[7],"the":[8,26,36,77,93,118,136],"agents'":[9],"behaviour":[10],"systems":[12],"that":[13,109],"have":[14],"realworld":[15,41],"significance.":[16],"In":[17,73],"these":[18],"frameworks,":[19],"agents":[20,30],"learn":[21],"how":[22],"to":[23,57,128],"interact":[24],"with":[25,92],"environment":[27],"and":[28,96,116],"other":[29,129],"while":[31],"satisfying":[32],"their":[33],"objectives.":[34],"Unfortunately,":[35],"level":[37],"of":[38,40,47,124,138],"complexity":[39],"problems":[42],"requires":[43],"a":[44,63,82],"significant":[45],"investment":[46],"computational":[48],"resources":[49],"before":[50],"multiagent":[51,99,130],"methods":[54],"are":[55],"able":[56],"deliver":[58],"results.":[59],"However,":[60],"by":[61,121],"incorporating":[62],"priori":[64],"domain":[65,90],"knowledge,":[66],"more":[67,143],"computationally-efficient":[68],"algorithms":[69],"can":[70],"be":[71],"developed.":[72],"this":[74,139],"paper,":[75],"for":[76],"first":[78],"time,":[79],"we":[80],"present":[81],"Domain-Aware":[83],"Actor-Critic":[85],"(DAMAC)":[86],"algorithm,":[87],"which":[88],"integrates":[89],"knowledge":[91],"centralised":[94],"decentralised":[97],"execution":[98],"approach":[102],"using":[103],"domain-specific":[104],"solvers.":[105],"Our":[106],"experiments":[107],"show":[108],"our":[110],"algorithm":[111],"achieves":[112],"substantial":[113],"high":[114],"reward":[115],"reduces":[117],"training":[119],"time":[120],"two":[122],"orders":[123],"magnitude":[125],"as":[126],"compared":[127],"algorithms.":[133],"This":[134],"enables":[135],"adoption":[137],"powerful":[140],"framework":[141],"resource-constrained":[144],"scenarios.":[145]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}