{"id":"https://openalex.org/W2045167219","doi":"https://doi.org/10.1080/095400999116250","title":"Dynamic Update of the Reinforcement Function During Learning","display_name":"Dynamic Update of the Reinforcement Function During Learning","publication_year":1999,"publication_date":"1999-12-01","ids":{"openalex":"https://openalex.org/W2045167219","doi":"https://doi.org/10.1080/095400999116250","mag":"2045167219"},"language":"en","primary_location":{"id":"doi:10.1080/095400999116250","is_oa":true,"landing_page_url":"https://doi.org/10.1080/095400999116250","pdf_url":"https://www.tandfonline.com/doi/pdf/10.1080/095400999116250?needAccess=true","source":{"id":"https://openalex.org/S4210188800","display_name":"Connection Science","issn_l":"0954-0091","issn":["0954-0091","1360-0494"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Connection Science","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://www.tandfonline.com/doi/pdf/10.1080/095400999116250?needAccess=true","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101095848","display_name":"Juan Miguel Santos","orcid":"https://orcid.org/0009-0005-6967-3603"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Juan Miguel Santos","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5090918769","display_name":"Claude Touzet","orcid":"https://orcid.org/0000-0003-4991-0382"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Claude Touzet","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1270,"currency":"USD","value_usd":1270},"apc_paid":null,"fwci":0.5207,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.75377811,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"11","issue":"3-4","first_page":"267","last_page":"289"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9900000095367432,"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":0.9900000095367432,"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":0.9635999798774719,"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":0.8653008937835693},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7805525660514832},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6295652985572815},{"id":"https://openalex.org/keywords/obstacle-avoidance","display_name":"Obstacle avoidance","score":0.6092851161956787},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5812074542045593},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5674980282783508},{"id":"https://openalex.org/keywords/memorization","display_name":"Memorization","score":0.5624478459358215},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5400046110153198},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.47445663809776306},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.4487898051738739},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.4103805422782898},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3913957178592682}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8653008937835693},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7805525660514832},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6295652985572815},{"id":"https://openalex.org/C6683253","wikidata":"https://www.wikidata.org/wiki/Q7075535","display_name":"Obstacle avoidance","level":4,"score":0.6092851161956787},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5812074542045593},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5674980282783508},{"id":"https://openalex.org/C30038468","wikidata":"https://www.wikidata.org/wiki/Q4354775","display_name":"Memorization","level":2,"score":0.5624478459358215},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5400046110153198},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.47445663809776306},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4487898051738739},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.4103805422782898},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3913957178592682},{"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1080/095400999116250","is_oa":true,"landing_page_url":"https://doi.org/10.1080/095400999116250","pdf_url":"https://www.tandfonline.com/doi/pdf/10.1080/095400999116250?needAccess=true","source":{"id":"https://openalex.org/S4210188800","display_name":"Connection Science","issn_l":"0954-0091","issn":["0954-0091","1360-0494"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Connection Science","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1080/095400999116250","is_oa":true,"landing_page_url":"https://doi.org/10.1080/095400999116250","pdf_url":"https://www.tandfonline.com/doi/pdf/10.1080/095400999116250?needAccess=true","source":{"id":"https://openalex.org/S4210188800","display_name":"Connection Science","issn_l":"0954-0091","issn":["0954-0091","1360-0494"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Connection Science","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2045167219.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2906946336","https://openalex.org/W2938416672","https://openalex.org/W2146611987","https://openalex.org/W4289599435","https://openalex.org/W2155757393","https://openalex.org/W2098534227","https://openalex.org/W3126153333","https://openalex.org/W1995204376","https://openalex.org/W2046187727","https://openalex.org/W1528255171"],"abstract_inverted_index":{"During":[0],"the":[1,10,16,25,42,50,53,86,112,116,128,138,144,155],"last":[2],"decade,":[3],"numerous":[4],"contributions":[5],"have":[6,21],"been":[7],"made":[8,64],"to":[9,48,93,95,110,126],"use":[11],"of":[12,52,99,137,161,163],"reinforcement":[13,54,150],"learning":[14,18,118],"in":[15,60,76,159],"robot":[17,157],"field.":[19],"They":[20],"focused":[22],"mainly":[23],"on":[24],"generalization,":[26],"memorization":[27],"and":[28,121,148,166],"exploration":[29,87,130],"issues-mandatory":[30],"for":[31],"dealing":[32],"with":[33,154],"real":[34],"robots.":[35],"However,":[36],"it":[37,81],"is":[38,47,92],"our":[39,170],"opinion":[40],"that":[41,80],"most":[43],"difficult":[44],"task":[45],"today":[46],"obtain":[49],"definition":[51],"function":[55],"(RF).":[56],"A":[57],"first":[58],"attempt":[59],"this":[61,102],"direction":[62],"was":[63],"by":[65,142],"introducing":[66],"a":[67,74,78,96],"method-the":[68],"update":[69],"parameters":[70,114],"algorithm":[71,108],"(UPA)-for":[72],"tuning":[73],"RF":[75,113,139],"such":[77],"way":[79],"would":[82],"be":[83],"optimal":[84],"during":[85,115,151],"phase.":[88],"The":[89],"only":[90],"requirement":[91],"conform":[94],"particular":[97],"expression":[98],"RF.":[100],"In":[101],"article,":[103],"we":[104],"propose":[105],"Dynamic-UPA,":[106],"an":[107],"able":[109],"tune":[111],"whole":[117],"phase":[119],"(exploration":[120],"exploitation).":[122],"It":[123],"allows":[124],"one":[125],"undertake":[127],"so-called":[129],"versus":[131],"exploitation":[132],"dilemma":[133],"through":[134],"careful":[135],"computation":[136],"parameter":[140],"values":[141],"controlling":[143],"ratio":[145],"between":[146],"positive":[147],"negative":[149],"learning.":[152],"Experiments":[153],"mobile":[156],"Khepera":[158],"tasks":[160],"synthesis":[162],"obstacle":[164],"avoidance":[165],"wall-following":[167],"behaviors":[168],"validate":[169],"proposals.":[171]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}