{"id":"https://openalex.org/W2147852745","doi":"https://doi.org/10.1109/iros.2003.1250668","title":"A reinforcement learning approach involving a shortest path finding algorithm","display_name":"A reinforcement learning approach involving a shortest path finding algorithm","publication_year":2004,"publication_date":"2004-07-08","ids":{"openalex":"https://openalex.org/W2147852745","doi":"https://doi.org/10.1109/iros.2003.1250668","mag":"2147852745"},"language":"en","primary_location":{"id":"doi:10.1109/iros.2003.1250668","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2003.1250668","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings 2003 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2003) (Cat. No.03CH37453)","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/A5070848861","display_name":"Woo Young Kwon","orcid":"https://orcid.org/0000-0003-0922-9832"},"institutions":[{"id":"https://openalex.org/I880766802","display_name":"Graduate School USA","ror":"https://ror.org/04n835f38","country_code":"US","type":"education","lineage":["https://openalex.org/I880766802"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Woo Young Kwon","raw_affiliation_strings":["The Graduate School of Information and Communications"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Graduate School of Information and Communications","institution_ids":["https://openalex.org/I880766802"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102158239","display_name":"Sangboon Lee","orcid":null},"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"]},{"id":"https://openalex.org/I93906172","display_name":"Anyang University","ror":"https://ror.org/018pdh902","country_code":"KR","type":"education","lineage":["https://openalex.org/I93906172"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sangboon Lee","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science, Hauyang University, Seoul, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, Hauyang University, Seoul, South Korea","institution_ids":["https://openalex.org/I4575257","https://openalex.org/I93906172"]}]},{"author_position":"last","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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":", Hanyang University","institution_ids":["https://openalex.org/I4575257"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.1026,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.78037357,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"1","issue":null,"first_page":"436","last_page":"441"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9936000108718872,"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/T10581","display_name":"Neural dynamics and brain function","score":0.9872999787330627,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7731813788414001},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7006164193153381},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.618091344833374},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.5972498655319214},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.5869612693786621},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47419387102127075},{"id":"https://openalex.org/keywords/learning-classifier-system","display_name":"Learning classifier system","score":0.4698666036128998},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.46405354142189026},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.463588684797287},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.45150670409202576},{"id":"https://openalex.org/keywords/shortest-path-problem","display_name":"Shortest path problem","score":0.4349375069141388},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.43064090609550476},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.42426711320877075},{"id":"https://openalex.org/keywords/sequence-learning","display_name":"Sequence learning","score":0.4232729375362396},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.4154210090637207},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.28419172763824463},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19732192158699036},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.18509238958358765},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.07313939929008484}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7731813788414001},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7006164193153381},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.618091344833374},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.5972498655319214},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.5869612693786621},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47419387102127075},{"id":"https://openalex.org/C199190896","wikidata":"https://www.wikidata.org/wiki/Q3509276","display_name":"Learning classifier system","level":3,"score":0.4698666036128998},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.46405354142189026},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.463588684797287},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.45150670409202576},{"id":"https://openalex.org/C22590252","wikidata":"https://www.wikidata.org/wiki/Q1058754","display_name":"Shortest path problem","level":3,"score":0.4349375069141388},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.43064090609550476},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.42426711320877075},{"id":"https://openalex.org/C40506919","wikidata":"https://www.wikidata.org/wiki/Q7452469","display_name":"Sequence learning","level":2,"score":0.4232729375362396},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.4154210090637207},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28419172763824463},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19732192158699036},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.18509238958358765},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.07313939929008484},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/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/iros.2003.1250668","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2003.1250668","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings 2003 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2003) (Cat. No.03CH37453)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Responsible consumption and production","id":"https://metadata.un.org/sdg/12","score":0.5400000214576721}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1563045389","https://openalex.org/W1583380718","https://openalex.org/W1669275715","https://openalex.org/W2005967666","https://openalex.org/W2045031658","https://openalex.org/W2065482164","https://openalex.org/W2107726111","https://openalex.org/W2126566174","https://openalex.org/W2142192587","https://openalex.org/W2911283634","https://openalex.org/W2914656440","https://openalex.org/W3011120880","https://openalex.org/W3184534114","https://openalex.org/W4206975602","https://openalex.org/W4253632718","https://openalex.org/W4301630257","https://openalex.org/W6635158338","https://openalex.org/W6676007687","https://openalex.org/W6680539579","https://openalex.org/W6775686901"],"related_works":["https://openalex.org/W2808418668","https://openalex.org/W2101748387","https://openalex.org/W2357975469","https://openalex.org/W4380550992","https://openalex.org/W4322760752","https://openalex.org/W3096874164","https://openalex.org/W2970347269","https://openalex.org/W2146763310","https://openalex.org/W3167472281","https://openalex.org/W2937181779"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,9,94,150],"(RL)":[2],"has":[3],"been":[4],"widely":[5],"used":[6],"as":[7,58,116,138],"a":[8,29,79,103,109,117,121,127,131,140],"mechanism":[10],"of":[11,31,147],"an":[12,92],"artificial":[13],"life":[14],"system.":[15],"However,":[16],"RL":[17],"usually":[18],"suffers":[19],"from":[20],"slow":[21],"convergence":[22],"to":[23,47,66,87,97],"the":[24,89,112,145],"optimum":[25,61],"state-action":[26,54],"sequence":[27,30],"or":[28],"stimulus-response":[32],"(SR)":[33],"behaviors,":[34],"and":[35],"may":[36],"not":[37],"correctly":[38],"work":[39],"in":[40,69,108,139],"non-Markov":[41,100,122,132],"processes.":[42],"In":[43],"this":[44],"paper,":[45],"first,":[46],"cope":[48],"with":[49],"slow-convergence":[50],"problem,":[51,101],"if":[52,102],"some":[53],"pairs":[55],"are":[56,65,76,155],"considered":[57],"disturbance":[59],"for":[60,120,130],"sequence,":[62],"then":[63,111],"they":[64],"be":[67,136],"eliminated":[68],"long-term":[70],"memory":[71],"(LTM),":[72],"where":[73],"such":[74],"disturbances":[75],"found":[77],"by":[78],"shortest":[80],"path-finding":[81],"algorithm.":[82],"This":[83],"process":[84],"is":[85,105,114],"shown":[86],"let":[88],"system":[90],"get":[91],"enhanced":[93],"speed.":[95],"Second,":[96],"partly":[98],"solve":[99],"stimulus":[104,113],"frequently":[106],"met":[107],"searching-process,":[110],"classified":[115],"sequential":[118],"percept":[119],"hidden":[123,133],"state.":[124],"And":[125],"thus,":[126],"correct":[128],"behavior":[129],"state":[134],"can":[135],"learned":[137],"Markov":[141],"environment.":[142],"To":[143],"show":[144],"validity":[146],"our":[148],"proposed":[149],"technologies,":[151],"several":[152],"simulation":[153],"results":[154],"illustrated.":[156]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}