{"id":"https://openalex.org/W2900553726","doi":"https://doi.org/10.1109/ictc.2018.8539424","title":"Multiagent Reinforcement Learning in Escape Scenario","display_name":"Multiagent Reinforcement Learning in Escape Scenario","publication_year":2018,"publication_date":"2018-10-01","ids":{"openalex":"https://openalex.org/W2900553726","doi":"https://doi.org/10.1109/ictc.2018.8539424","mag":"2900553726"},"language":"en","primary_location":{"id":"doi:10.1109/ictc.2018.8539424","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ictc.2018.8539424","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 International Conference on Information and Communication Technology Convergence (ICTC)","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/A5100348868","display_name":"Donghun Lee","orcid":"https://orcid.org/0000-0002-7941-2395"},"institutions":[{"id":"https://openalex.org/I142401562","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10","country_code":"KR","type":"facility","lineage":["https://openalex.org/I142401562","https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Donghun Lee","raw_affiliation_strings":["Electronics and Telecommunications Research Institute, Daejeon, Korea"],"affiliations":[{"raw_affiliation_string":"Electronics and Telecommunications Research Institute, Daejeon, Korea","institution_ids":["https://openalex.org/I142401562"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101430464","display_name":"Seonghyun Kim","orcid":"https://orcid.org/0000-0001-8080-8963"},"institutions":[{"id":"https://openalex.org/I142401562","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10","country_code":"KR","type":"facility","lineage":["https://openalex.org/I142401562","https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seonghyun Kim","raw_affiliation_strings":["Electronics and Telecommunications Research Institute, Daejeon, Korea"],"affiliations":[{"raw_affiliation_string":"Electronics and Telecommunications Research Institute, Daejeon, Korea","institution_ids":["https://openalex.org/I142401562"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005267663","display_name":"Young-Sung Son","orcid":null},"institutions":[{"id":"https://openalex.org/I142401562","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10","country_code":"KR","type":"facility","lineage":["https://openalex.org/I142401562","https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Young-Sung Son","raw_affiliation_strings":["Electronics and Telecommunications Research Institute, Daejeon, Korea"],"affiliations":[{"raw_affiliation_string":"Electronics and Telecommunications Research Institute, Daejeon, Korea","institution_ids":["https://openalex.org/I142401562"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100348868"],"corresponding_institution_ids":["https://openalex.org/I142401562"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.13017698,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"529","issue":null,"first_page":"1031","last_page":"1033"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9997000098228455,"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":0.9997000098228455,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.9837999939918518,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.982200026512146,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.9420349597930908},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.702878475189209},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.6818151473999023},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5575213432312012},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4661138653755188},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.4293254017829895},{"id":"https://openalex.org/keywords/error-driven-learning","display_name":"Error-driven learning","score":0.41119998693466187},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11892783641815186}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9420349597930908},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.702878475189209},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.6818151473999023},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5575213432312012},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4661138653755188},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.4293254017829895},{"id":"https://openalex.org/C47932503","wikidata":"https://www.wikidata.org/wiki/Q5395689","display_name":"Error-driven learning","level":3,"score":0.41119998693466187},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11892783641815186},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ictc.2018.8539424","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ictc.2018.8539424","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 International Conference on Information and Communication Technology Convergence (ICTC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1515851193","https://openalex.org/W2142924305","https://openalex.org/W2257979135","https://openalex.org/W2594794854","https://openalex.org/W2601465345","https://openalex.org/W2602275733","https://openalex.org/W2604283518","https://openalex.org/W2810602713","https://openalex.org/W2949886883","https://openalex.org/W2963407617","https://openalex.org/W2963934958","https://openalex.org/W2964043796","https://openalex.org/W2964345382","https://openalex.org/W4298857966","https://openalex.org/W4299802797","https://openalex.org/W6692846177","https://openalex.org/W6735011893","https://openalex.org/W6735650757","https://openalex.org/W6735698609","https://openalex.org/W6736622323","https://openalex.org/W6738796088","https://openalex.org/W6746513637","https://openalex.org/W6947956204"],"related_works":["https://openalex.org/W2371091044","https://openalex.org/W87513465","https://openalex.org/W2786230833","https://openalex.org/W2391666574","https://openalex.org/W2352650970","https://openalex.org/W1493952344","https://openalex.org/W4312372616","https://openalex.org/W8539471","https://openalex.org/W1544514152","https://openalex.org/W3203256658"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,33],"let":[2],"agents":[3,45,59,78],"perform":[4],"repeated":[5],"actions":[6],"in":[7,15,48],"given":[8,17],"environments":[9],"and":[10,79,82,99],"identify":[11],"how":[12,103],"to":[13,40,46,66,85,104],"behave":[14],"the":[16],"environments.":[18],"In":[19],"this":[20],"paper,":[21],"we":[22],"showed":[23,37],"possibilities":[24],"of":[25,58,76],"solutions":[26],"for":[27,44,89],"real-world":[28,97],"scenarios":[29],"on":[30,102],"multiagent":[31,53],"reinforcement":[32,54],"environment.":[34],"Our":[35],"experiment":[36],"an":[38,49,68],"approach":[39],"investigate":[41],"a":[42,73],"way":[43],"escape":[47,50],"scenario":[51],"using":[52],"learning.":[55],"Two":[56],"types":[57],"are":[60],"trained.":[61],"We":[62],"trained":[63],"Escaper":[64],"Agent":[65,84],"find":[67,86],"optimal":[69,87],"exit":[70],"which":[71],"increases":[72],"total":[74],"number":[75],"escaped":[77],"decreases":[80],"congestion":[81],"Exit":[83],"locations":[88],"exits.":[90],"Thoroughly":[91],"setting":[92],"reward":[93],"function":[94],"could":[95],"simulate":[96],"problems":[98],"get":[100],"insights":[101],"break":[105],"down":[106],"challenging":[107],"questions.":[108]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}