{"id":"https://openalex.org/W2018236549","doi":"https://doi.org/10.1109/smc.2014.6974464","title":"Multi-agent path planning in unknown environment with reinforcement learning and neural network","display_name":"Multi-agent path planning in unknown environment with reinforcement learning and neural network","publication_year":2014,"publication_date":"2014-10-01","ids":{"openalex":"https://openalex.org/W2018236549","doi":"https://doi.org/10.1109/smc.2014.6974464","mag":"2018236549"},"language":"en","primary_location":{"id":"doi:10.1109/smc.2014.6974464","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc.2014.6974464","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","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/A5019055832","display_name":"David Luviano\u2010Cruz","orcid":"https://orcid.org/0000-0002-4778-8873"},"institutions":[{"id":"https://openalex.org/I68368234","display_name":"Center for Research and Advanced Studies of the National Polytechnic Institute","ror":"https://ror.org/009eqmr18","country_code":"MX","type":"facility","lineage":["https://openalex.org/I59361560","https://openalex.org/I68368234"]},{"id":"https://openalex.org/I59361560","display_name":"Instituto Polit\u00e9cnico Nacional","ror":"https://ror.org/059sp8j34","country_code":"MX","type":"education","lineage":["https://openalex.org/I59361560"]}],"countries":["MX"],"is_corresponding":true,"raw_author_name":"David Luviano Cruz","raw_affiliation_strings":["Departamento de Control Automatico, Centro de Investigacion y de Estudios Avanzados del Instituto Politecnico Nacional, Ciudad de Mexico, Ciudad de M\u00c3\u00a9xico, MX","Departamento de Control Autom\u00e1tico, CINVESTAV-IPN, Mexico City, Mexico#TAB#"],"affiliations":[{"raw_affiliation_string":"Departamento de Control Automatico, Centro de Investigacion y de Estudios Avanzados del Instituto Politecnico Nacional, Ciudad de Mexico, Ciudad de M\u00c3\u00a9xico, MX","institution_ids":["https://openalex.org/I59361560","https://openalex.org/I68368234"]},{"raw_affiliation_string":"Departamento de Control Autom\u00e1tico, CINVESTAV-IPN, Mexico City, Mexico#TAB#","institution_ids":["https://openalex.org/I68368234"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008201587","display_name":"Wen Yu","orcid":"https://orcid.org/0000-0002-9540-7924"},"institutions":[{"id":"https://openalex.org/I68368234","display_name":"Center for Research and Advanced Studies of the National Polytechnic Institute","ror":"https://ror.org/009eqmr18","country_code":"MX","type":"facility","lineage":["https://openalex.org/I59361560","https://openalex.org/I68368234"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"Wen Yu","raw_affiliation_strings":["Departamento de Control Automatico, CINVESTAV-IPN, Mexico City, Mexico","Departamento de Control Autom\u00e1tico, CINVESTAV-IPN, Mexico City, Mexico#TAB#"],"affiliations":[{"raw_affiliation_string":"Departamento de Control Automatico, CINVESTAV-IPN, Mexico City, Mexico","institution_ids":["https://openalex.org/I68368234"]},{"raw_affiliation_string":"Departamento de Control Autom\u00e1tico, CINVESTAV-IPN, Mexico City, Mexico#TAB#","institution_ids":["https://openalex.org/I68368234"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5019055832"],"corresponding_institution_ids":["https://openalex.org/I59361560","https://openalex.org/I68368234"],"apc_list":null,"apc_paid":null,"fwci":1.227,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.84244463,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"a","issue":null,"first_page":"3458","last_page":"3463"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994000196456909,"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":0.9994000196456909,"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9939000010490417,"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":0.9315108060836792},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7761144638061523},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.7020986080169678},{"id":"https://openalex.org/keywords/motion-planning","display_name":"Motion planning","score":0.6646555066108704},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.6541559100151062},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5803928971290588},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.46853867173194885},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4422720670700073},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.43301984667778015},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3356319069862366},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.19695031642913818},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.1257549226284027},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12465760111808777}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9315108060836792},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7761144638061523},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.7020986080169678},{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.6646555066108704},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.6541559100151062},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5803928971290588},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.46853867173194885},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4422720670700073},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.43301984667778015},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3356319069862366},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.19695031642913818},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.1257549226284027},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12465760111808777},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/smc.2014.6974464","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc.2014.6974464","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5400000214576721,"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W94523489","https://openalex.org/W1525325904","https://openalex.org/W1553407966","https://openalex.org/W1965765347","https://openalex.org/W1980278669","https://openalex.org/W2021702776","https://openalex.org/W2046431055","https://openalex.org/W2074500080","https://openalex.org/W2092324280","https://openalex.org/W2099618002","https://openalex.org/W2100695938","https://openalex.org/W2107726111","https://openalex.org/W2108886361","https://openalex.org/W2120327309","https://openalex.org/W2129479396","https://openalex.org/W2137840335","https://openalex.org/W2139285094","https://openalex.org/W2145790759","https://openalex.org/W2147492008","https://openalex.org/W2611243847","https://openalex.org/W4210369895","https://openalex.org/W4214717370","https://openalex.org/W6673518375","https://openalex.org/W6675090247","https://openalex.org/W6676020571"],"related_works":["https://openalex.org/W4225571923","https://openalex.org/W2359600231","https://openalex.org/W3212257828","https://openalex.org/W2380019117","https://openalex.org/W3138952546","https://openalex.org/W1987886368","https://openalex.org/W1660309994","https://openalex.org/W2369187583","https://openalex.org/W3197207153","https://openalex.org/W3154539612"],"abstract_inverted_index":{"Path":[0],"planning":[1,24,56],"of":[2,57,85],"multi-agent":[3,45],"is":[4,12,36,48,88],"much":[5],"harder":[6],"than":[7],"single-agent.":[8],"Reinforcement":[9],"learning":[10,47],"(RL)":[11],"a":[13],"popular":[14],"method":[15,87],"for":[16,71,96,114],"it.":[17],"However,":[18],"it":[19],"cannot":[20],"solve":[21],"the":[22,40,51,74,97,103,111],"path":[23,55],"problem":[25],"directly":[26],"in":[27,110],"unknown":[28,112],"environment.":[29],"In":[30],"this":[31,58,86],"paper,":[32],"neural":[33,52],"network":[34],"(NN)":[35],"applied":[37],"to":[38,67,81,93],"estimate":[39],"unvisited":[41,98],"space.":[42],"The":[43,54,83],"traditional":[44],"reinforcement":[46],"modified":[49],"by":[50],"approximation.":[53],"paper":[59],"includes":[60],"two":[61],"stages:":[62],"we":[63,89],"first":[64],"use":[65],"RL":[66,95],"generate":[68,107],"training":[69],"samples":[70],"NN;":[72],"then":[73],"trained":[75],"NN":[76],"gives":[77],"an":[78],"approximate":[79],"action":[80],"agents.":[82,116],"advantage":[84],"do":[90],"not":[91],"need":[92],"repeat":[94],"state.":[99],"Experiment":[100],"results":[101],"show":[102],"proposed":[104],"algorithm":[105],"can":[106],"suboptimal":[108],"paths":[109],"environment":[113],"multiple":[115]},"counts_by_year":[{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}