{"id":"https://openalex.org/W246777829","doi":null,"title":"Q-Learning with a growing RBF network for behavior learning in mobile robotics","display_name":"Q-Learning with a growing RBF network for behavior learning in mobile robotics","publication_year":2005,"publication_date":"2005-01-01","ids":{"openalex":"https://openalex.org/W246777829","mag":"246777829"},"language":"en","primary_location":{"id":"mag:246777829","doi":null,"is_oa":false,"landing_page_url":"http://www.diva-portal.org/smash/record.jsf?pid=diva2:138297","pdf_url":null,"source":{"id":"https://openalex.org/S4306420800","display_name":"Robotics and Applications","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Robotics and Applications","raw_type":null},"volume":null,"type":"article","indexed_in":[],"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/A5100678956","display_name":"Jun Li","orcid":"https://orcid.org/0000-0002-5978-2049","observed_orcids":["https://orcid.org/0000-0002-5978-2049"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jun Li","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-5978-2049","affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5088202291","display_name":"Tom Duckett","orcid":"https://orcid.org/0000-0003-2971-7905","observed_orcids":["https://orcid.org/0000-0003-2971-7905"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tom Duckett","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-2971-7905","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.0541,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.79748062,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":1.0,"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":1.0,"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/T10320","display_name":"Neural Networks and Applications","score":0.0,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.0,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/q-learning","display_name":"Q-learning","score":1.0},{"id":"https://openalex.org/keywords/resource-allocating-network","display_name":"resource allocating network","score":0.8610000014305115},{"id":"https://openalex.org/keywords/radial-basis-function-neural-network","display_name":"radial basis function neural network","score":0.8330000042915344},{"id":"https://openalex.org/keywords/function-approximation","display_name":"function approximation","score":0.7129999995231628},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.5860000252723694},{"id":"https://openalex.org/keywords/sensorimotor-mapping","display_name":"sensorimotor mapping","score":0.9039999842643738},{"id":"https://openalex.org/keywords/off-policy-learning","display_name":"off-policy learning","score":0.8849999904632568},{"id":"https://openalex.org/keywords/wall-following-behavior","display_name":"wall-following behavior","score":0.7889999747276306},{"id":"https://openalex.org/keywords/online-training","display_name":"online training","score":0.7009999752044678},{"id":"https://openalex.org/keywords/convergence","display_name":"convergence","score":0.5410000085830688}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8454766273498535},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7269739508628845},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6703222990036011},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6256071925163269},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.6019996404647827},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.5714637041091919},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.5424436330795288},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5269092917442322},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.5177239775657654},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5089569091796875},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5030397772789001},{"id":"https://openalex.org/C120822770","wikidata":"https://www.wikidata.org/wiki/Q5156355","display_name":"Competitive learning","level":3,"score":0.497074156999588},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.4891338646411896},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.41228151321411133},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4112175405025482},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.3879987299442291},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.08530184626579285},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0791333019733429},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.07791376113891602},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:246777829","doi":null,"is_oa":false,"landing_page_url":"http://www.diva-portal.org/smash/record.jsf?pid=diva2:138297","pdf_url":null,"source":{"id":"https://openalex.org/S4306420800","display_name":"Robotics and Applications","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Robotics and Applications","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2159642572","https://openalex.org/W2007645104","https://openalex.org/W162682169","https://openalex.org/W2343224045","https://openalex.org/W1986998777","https://openalex.org/W2375194930","https://openalex.org/W2360919083","https://openalex.org/W7099452318","https://openalex.org/W2772908574","https://openalex.org/W2140085786"],"abstract_inverted_index":{"The":[0,58],"use":[1],"of":[2,29,136],"arti\ufb01cial":[3],"neural":[4],"networks":[5],"for":[6,52,80],"approximating":[7],"value":[8],"functions":[9],"in":[10,55,91,140],"reinforcement":[11,109],"learning":[12,41,54,103,138],"is":[13,62,84],"a":[14,39,47,65,117,122],"common":[15],"practice,":[16],"but":[17],"usually":[18],"requires":[19],"much":[20],"work":[21],"on":[22,130],"designing":[23],"the":[24,30,71,77,88,96,101,108,131,141],"network":[25,31,50,61],"architecture":[26],"and":[27,82,125,133],"re\ufb01ning":[28],"parame":[32],"ters.":[33],"In":[34],"this":[35],"paper":[36],"we":[37],"present":[38],"simple":[40],"system":[42],"that":[43,94],"uses":[44],"Q-learning":[45,83],"with":[46],"resource":[48,59],"allocating":[49,60],"(RAN)":[51],"behaviour":[53],"mobile":[56],"robotics.":[57],"used":[63,85],"as":[64],"function":[66],"approximator":[67],"to":[68,86,99,120],"dynamically":[69],"represent":[70],"continuous":[72],"sensory":[73],"space,":[74],"thus":[75,105],"acquiring":[76],"sensorimotor":[78],"mapping":[79],"generalization;":[81],"learn":[87,110],"control":[89],"policy":[90],"\u2018off-policy\u2019":[92],"fashion":[93],"enables":[95],"human":[97],"operator":[98],"guide":[100],"initial":[102],"process,":[104],"speeding":[106],"up":[107],"ing.":[111],"We":[112],"illustrate":[113],"our":[114,137],"approach":[115],"using":[116],"PeopleBot":[118],"robot":[119],"acquire":[121],"wall-following":[123],"behaviour,":[124],"discuss":[126],"some":[127],"ob":[128],"servations":[129],"convergence":[132],"online":[134],"training":[135],"algorithm":[139],"experiments.":[142]},"counts_by_year":[{"year":2015,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-10-30T12:39:25.321706","created_date":"2016-06-24T00:00:00"}