{"id":"https://openalex.org/W2124597436","doi":"https://doi.org/10.1109/iros.2007.4399040","title":"Fast reinforcement learning using stochastic shortest paths for a mobile robot","display_name":"Fast reinforcement learning using stochastic shortest paths for a mobile robot","publication_year":2007,"publication_date":"2007-10-01","ids":{"openalex":"https://openalex.org/W2124597436","doi":"https://doi.org/10.1109/iros.2007.4399040","mag":"2124597436"},"language":"en","primary_location":{"id":"doi:10.1109/iros.2007.4399040","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2007.4399040","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2007 IEEE/RSJ International Conference on Intelligent Robots and Systems","raw_type":"proceedings-article"},"type":"conference-paper","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/A5032568326","display_name":"Woo-Young Kwon","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":"Wooyoung Kwon","raw_affiliation_strings":["Electron. & Telecommun. Res. Inst., Daejeon"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electron. & Telecommun. Res. Inst., Daejeon","institution_ids":["https://openalex.org/I142401562"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030410269","display_name":"Il Hong Suh","orcid":"https://orcid.org/0000-0002-0981-329X"},"institutions":[{"id":"https://openalex.org/I4575257","display_name":"Hanyang University","ror":"https://ror.org/046865y68","country_code":"KR","type":"education","lineage":["https://openalex.org/I4575257"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Il Hong Suh","raw_affiliation_strings":["Hanyang University Seoul Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hanyang University Seoul Korea","institution_ids":["https://openalex.org/I4575257"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100320202","display_name":"Sanghoon Lee","orcid":"https://orcid.org/0000-0002-6986-9930"},"institutions":[{"id":"https://openalex.org/I4575257","display_name":"Hanyang University","ror":"https://ror.org/046865y68","country_code":"KR","type":"education","lineage":["https://openalex.org/I4575257"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sanghoon Lee","raw_affiliation_strings":["Hanyang University Seoul Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hanyang University Seoul Korea","institution_ids":["https://openalex.org/I4575257"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030073688","display_name":"Young-Jo Cho","orcid":"https://orcid.org/0000-0003-0886-7592"},"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-Jo Cho","raw_affiliation_strings":["Intelligent Robotics Division, Electronics and Telecommunications Research Institute, Daejon, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intelligent Robotics Division, Electronics and Telecommunications Research Institute, Daejon, Korea","institution_ids":["https://openalex.org/I142401562"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2231,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.48774317,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"82","last_page":"87"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9986000061035156,"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":0.9986000061035156,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.996999979019165,"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/T12423","display_name":"Software Reliability and Analysis Research","score":0.9829000234603882,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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":0.8167483806610107},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6925150752067566},{"id":"https://openalex.org/keywords/shortest-path-problem","display_name":"Shortest path problem","score":0.6356786489486694},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5879319906234741},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5718536972999573},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.5019280910491943},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4831227958202362},{"id":"https://openalex.org/keywords/action-selection","display_name":"Action selection","score":0.48235267400741577},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.4782637357711792},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4509834051132202},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.43227213621139526},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.43207111954689026},{"id":"https://openalex.org/keywords/a-priori-and-a-posteriori","display_name":"A priori and a posteriori","score":0.42347222566604614},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4154689610004425},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3851320743560791},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.37138131260871887},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.26583749055862427},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2122870683670044},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.2033950686454773}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8167483806610107},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6925150752067566},{"id":"https://openalex.org/C22590252","wikidata":"https://www.wikidata.org/wiki/Q1058754","display_name":"Shortest path problem","level":3,"score":0.6356786489486694},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5879319906234741},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5718536972999573},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.5019280910491943},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4831227958202362},{"id":"https://openalex.org/C166109690","wikidata":"https://www.wikidata.org/wiki/Q4677422","display_name":"Action selection","level":3,"score":0.48235267400741577},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.4782637357711792},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4509834051132202},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.43227213621139526},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.43207111954689026},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.42347222566604614},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4154689610004425},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3851320743560791},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.37138131260871887},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.26583749055862427},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2122870683670044},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2033950686454773},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"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},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/iros.2007.4399040","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2007.4399040","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2007 IEEE/RSJ International Conference on Intelligent Robots and Systems","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.615.2203","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.615.2203","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://incorl.hanyang.ac.kr/xe/paper/ic/ic2007-4.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth","score":0.6800000071525574}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W139877375","https://openalex.org/W1480676279","https://openalex.org/W1483307070","https://openalex.org/W1491843047","https://openalex.org/W1557517019","https://openalex.org/W1569930087","https://openalex.org/W1992969624","https://openalex.org/W2048226872","https://openalex.org/W2110178871","https://openalex.org/W2124748769","https://openalex.org/W2147852745","https://openalex.org/W2149665096","https://openalex.org/W2911283634","https://openalex.org/W2914656440","https://openalex.org/W3011120880","https://openalex.org/W4245108548","https://openalex.org/W4253023493","https://openalex.org/W4285719527","https://openalex.org/W4301630257","https://openalex.org/W6634043515","https://openalex.org/W6648466938","https://openalex.org/W6676388466","https://openalex.org/W6678823476","https://openalex.org/W6681698302","https://openalex.org/W6681793319","https://openalex.org/W6775686901"],"related_works":["https://openalex.org/W2015051472","https://openalex.org/W2168501056","https://openalex.org/W2742483371","https://openalex.org/W2120009678","https://openalex.org/W3096874164","https://openalex.org/W2166117066","https://openalex.org/W2357975469","https://openalex.org/W2037601570","https://openalex.org/W2136202932","https://openalex.org/W3087814763"],"abstract_inverted_index":{"Abstract":[0],"\u2014":[1],"Reinforcement":[2],"learning":[3,10,50,127,130,148],"(RL)":[4],"has":[5],"been":[6],"used":[7,78],"as":[8,118],"a":[9,13,21,49,59,73,81,85,89,93,96,98],"mechanism":[11],"for":[12],"mobile":[14],"robot":[15,94],"to":[16,36,47,79],"learn":[17,37],"state-action":[18,39],"relations":[19],"without":[20],"priori":[22],"knowledge":[23],"of":[24,145],"working":[25],"environment.":[26],"However,":[27],"most":[28],"RL":[29,139],"methods":[30],"usually":[31],"suffer":[32],"from":[33,105],"slow":[34],"conver-gence":[35],"optimum":[38],"sequence.":[40],"In":[41],"this":[42,126],"paper,":[43],"it":[44],"is":[45,77],"intended":[46],"improve":[48],"speed":[51,131],"by":[52],"compounding":[53],"an":[54],"existing":[55],"Q-learning":[56,71],"method":[57],"with":[58,70,137],"shortest":[60,67],"path":[61,68],"finding":[62],"algorithm.":[63],"To":[64,141],"integrate":[65],"the":[66,106,113,122,129,143],"algorithm":[69],"method,":[72,128],"stochastic":[74,107],"state-transition":[75,108],"model":[76],"store":[80],"previous":[82,86],"observed":[83],"state,":[84],"action":[87,123],"and":[88,152],"current":[90],"state.":[91],"Whenever":[92],"reaches":[95],"goal,":[97],"Stochastic":[99],"Shortest":[100],"Path(SSP)":[101],"will":[102,115,132,155],"be":[103,116,133,156],"found":[104],"model.":[109],"State-action":[110],"pairs":[111],"on":[112],"SSP":[114],"counted":[117],"more":[119],"significant":[120],"in":[121],"selection.":[124],"Using":[125],"boosted":[134],"when":[135],"compared":[136],"classical":[138],"methods.":[140],"show":[142],"validity":[144],"our":[146],"proposed":[147],"technology,":[149],"several":[150],"simulations":[151],"experimental":[153],"results":[154],"illustrated.":[157],"I.":[158]},"counts_by_year":[{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-10-10T00:00:00"}