{"id":"https://openalex.org/W4401611240","doi":"https://doi.org/10.1109/icasspw62465.2024.10627769","title":"QMARL: A Quantum Multi-Agent Reinforcement Learning Framework for Swarm Robots Navigation","display_name":"QMARL: A Quantum Multi-Agent Reinforcement Learning Framework for Swarm Robots Navigation","publication_year":2024,"publication_date":"2024-04-14","ids":{"openalex":"https://openalex.org/W4401611240","doi":"https://doi.org/10.1109/icasspw62465.2024.10627769"},"language":"en","primary_location":{"id":"doi:10.1109/icasspw62465.2024.10627769","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icasspw62465.2024.10627769","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","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/A5045347651","display_name":"Weizhao Chen","orcid":"https://orcid.org/0000-0003-2482-1906"},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Weizhao Chen","raw_affiliation_strings":["University of Science and Technology,School of Computer and Communication Engineering,Beijing"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology,School of Computer and Communication Engineering,Beijing","institution_ids":["https://openalex.org/I92403157"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088370265","display_name":"Jiawang Wan","orcid":"https://orcid.org/0000-0001-7688-7347"},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiawang Wan","raw_affiliation_strings":["University of Science and Technology,School of Computer and Communication Engineering,Beijing"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology,School of Computer and Communication Engineering,Beijing","institution_ids":["https://openalex.org/I92403157"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083360604","display_name":"Fangwen Ye","orcid":"https://orcid.org/0000-0002-6521-2261"},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fangwen Ye","raw_affiliation_strings":["University of Science and Technology,School of Computer and Communication Engineering,Beijing"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology,School of Computer and Communication Engineering,Beijing","institution_ids":["https://openalex.org/I92403157"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087067755","display_name":"Ran Wang","orcid":"https://orcid.org/0000-0002-9530-8838"},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ran Wang","raw_affiliation_strings":["University of Science and Technology,School of Computer and Communication Engineering,Beijing"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology,School of Computer and Communication Engineering,Beijing","institution_ids":["https://openalex.org/I92403157"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066602150","display_name":"Cheng Xu","orcid":"https://orcid.org/0000-0003-1624-5494"},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cheng Xu","raw_affiliation_strings":["University of Science and Technology,School of Computer and Communication Engineering,Beijing"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology,School of Computer and Communication Engineering,Beijing","institution_ids":["https://openalex.org/I92403157"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5045347651"],"corresponding_institution_ids":["https://openalex.org/I92403157"],"apc_list":null,"apc_paid":null,"fwci":0.3862,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.65957167,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"388","last_page":"392"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10100","display_name":"Metaheuristic Optimization Algorithms Research","score":0.8442999720573425,"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/T10100","display_name":"Metaheuristic Optimization Algorithms Research","score":0.8442999720573425,"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":0.8281999826431274,"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/T12784","display_name":"Modular Robots and Swarm Intelligence","score":0.8183000087738037,"subfield":{"id":"https://openalex.org/subfields/2210","display_name":"Mechanical 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":0.8553804159164429},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.691770076751709},{"id":"https://openalex.org/keywords/swarm-behaviour","display_name":"Swarm behaviour","score":0.67097008228302},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6691262722015381},{"id":"https://openalex.org/keywords/swarm-robotics","display_name":"Swarm robotics","score":0.5521277189254761},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.5261863470077515},{"id":"https://openalex.org/keywords/quantum","display_name":"Quantum","score":0.45707637071609497},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.4176263213157654},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.41403257846832275},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39330971240997314},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3501507341861725},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.1024588942527771},{"id":"https://openalex.org/keywords/quantum-mechanics","display_name":"Quantum mechanics","score":0.04651099443435669}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8553804159164429},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.691770076751709},{"id":"https://openalex.org/C181335050","wikidata":"https://www.wikidata.org/wiki/Q14915018","display_name":"Swarm behaviour","level":2,"score":0.67097008228302},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6691262722015381},{"id":"https://openalex.org/C169337768","wikidata":"https://www.wikidata.org/wiki/Q2446723","display_name":"Swarm robotics","level":3,"score":0.5521277189254761},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.5261863470077515},{"id":"https://openalex.org/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"score":0.45707637071609497},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.4176263213157654},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.41403257846832275},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39330971240997314},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3501507341861725},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.1024588942527771},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.04651099443435669}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icasspw62465.2024.10627769","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icasspw62465.2024.10627769","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322725","display_name":"China Scholarship Council","ror":"https://ror.org/04atp4p48"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W2117941808","https://openalex.org/W2145339207","https://openalex.org/W2521267242","https://openalex.org/W2617547828","https://openalex.org/W2773252567","https://openalex.org/W2813428123","https://openalex.org/W3102731313","https://openalex.org/W3111162498","https://openalex.org/W3156295478"],"related_works":["https://openalex.org/W1871202614","https://openalex.org/W4233987368","https://openalex.org/W1988876749","https://openalex.org/W65954170","https://openalex.org/W2518382144","https://openalex.org/W2350154411","https://openalex.org/W4229451618","https://openalex.org/W617387166","https://openalex.org/W2787547275","https://openalex.org/W1966857494"],"abstract_inverted_index":{"In":[0],"the":[1,4,20,31,76,83,89,92,119,149,155],"last":[2],"decade,":[3],"field":[5],"of":[6,22,33,78,91,151],"reinforcement":[7,85,152],"learning":[8,35,86,134],"has":[9,111],"evolved":[10],"from":[11],"single-agent":[12],"paradigms":[13],"to":[14,38,131],"embrace":[15],"multi-agent":[16,46,84,133,164],"settings.":[17,137],"However,":[18],"as":[19,66],"number":[21],"agents":[23],"increases,":[24],"especially":[25],"in":[26,45,118,135,148,163],"intricate":[27],"or":[28],"stochastic":[29],"environments,":[30],"efficacy":[32],"individual":[34],"models":[36],"tends":[37],"diminish.":[39],"Moreover,":[40],"applying":[41],"experience":[42,105],"replay":[43,106],"techniques":[44,147],"scenarios":[47],"presents":[48],"considerable":[49],"challenges.":[50],"To":[51],"address":[52],"these":[53],"pressing":[54],"issues,":[55],"this":[56],"paper":[57],"introduces":[58],"a":[59,101],"straightforward":[60],"yet":[61],"highly":[62],"effective":[63],"approach":[64,73,110],"known":[65],"Quantum-Based":[67],"Multi-Agent":[68],"Reinforcement":[69],"Learning":[70],"(QMARL).":[71],"This":[72,138],"revolves":[74],"around":[75],"quantization":[77],"states":[79],"and":[80,160],"actions":[81],"within":[82],"system.":[87],"Leveraging":[88],"power":[90],"Grover":[93],"algorithm":[94],"for":[95,143,157],"action":[96],"decision-making,":[97],"we":[98],"also":[99],"introduce":[100],"novel":[102],"quantum-based":[103],"prioritized":[104],"method.":[107],"Our":[108],"proposed":[109],"been":[112],"rigorously":[113],"validated":[114],"through":[115],"experiments":[116],"conducted":[117],"cooperative":[120],"navigation":[121],"environment":[122],"provided":[123],"by":[124],"OpenAI.":[125],"The":[126],"results":[127],"demonstrate":[128],"its":[129],"capacity":[130],"enhance":[132],"complex":[136],"research":[139],"opens":[140],"promising":[141],"avenues":[142],"harnessing":[144],"quantum":[145],"computing":[146],"realm":[150],"learning,":[153],"paving":[154],"way":[156],"more":[158],"robust":[159],"scalable":[161],"solutions":[162],"systems.":[165]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-22T23:10:17.713674","created_date":"2025-10-10T00:00:00"}
