{"id":"https://openalex.org/W2149738224","doi":"https://doi.org/10.1142/s0129065799000241","title":"Autonomous Learning Based on Cost Assumptions: Theoretical Studies And Experiments in Robot Control","display_name":"Autonomous Learning Based on Cost Assumptions: Theoretical Studies And Experiments in Robot Control","publication_year":1999,"publication_date":"1999-06-01","ids":{"openalex":"https://openalex.org/W2149738224","doi":"https://doi.org/10.1142/s0129065799000241","mag":"2149738224","pmid":"https://pubmed.ncbi.nlm.nih.gov/10560764"},"language":"en","primary_location":{"id":"doi:10.1142/s0129065799000241","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0129065799000241","pdf_url":null,"source":{"id":"https://openalex.org/S197665576","display_name":"International Journal of Neural Systems","issn_l":"0129-0657","issn":["0129-0657","1793-6462"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Neural Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5068086847","display_name":"Carlos H. C. Ribeiro","orcid":"https://orcid.org/0000-0002-5760-8426"},"institutions":[{"id":"https://openalex.org/I4210123805","display_name":"Instituto de Aeron\u00e1utica e Espa\u00e7o","ror":"https://ror.org/025n1fp68","country_code":"BR","type":"other","lineage":["https://openalex.org/I4210123805"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"CARLOS H.C. RIBEIRO","raw_affiliation_strings":["Technological Institute of Aeronautics, Pra\u00e7a Mal. Eduardo Gomes, 50,  12228\u2013900 S\u00e3o Jos\u00e9 dos Campos \u2013 SP, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technological Institute of Aeronautics, Pra\u00e7a Mal. Eduardo Gomes, 50,  12228\u2013900 S\u00e3o Jos\u00e9 dos Campos \u2013 SP, Brazil","institution_ids":["https://openalex.org/I4210123805"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077562062","display_name":"ELDER M. HEMERLY","orcid":null},"institutions":[{"id":"https://openalex.org/I4210123805","display_name":"Instituto de Aeron\u00e1utica e Espa\u00e7o","ror":"https://ror.org/025n1fp68","country_code":"BR","type":"other","lineage":["https://openalex.org/I4210123805"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"ELDER M. HEMERLY","raw_affiliation_strings":["Technological Institute of Aeronautics, Pra\u00e7a Mal. Eduardo Gomes, 50,  12228\u2013900 S\u00e3o Jos\u00e9 dos Campos \u2013 SP, Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technological Institute of Aeronautics, Pra\u00e7a Mal. Eduardo Gomes, 50,  12228\u2013900 S\u00e3o Jos\u00e9 dos Campos \u2013 SP, Brazil","institution_ids":["https://openalex.org/I4210123805"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210123805"],"apc_list":null,"apc_paid":null,"fwci":1.0317,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.82948806,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"09","issue":"03","first_page":"243","last_page":"249"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.998199999332428,"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":0.998199999332428,"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.9925000071525574,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9878000020980835,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7791974544525146},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7098074555397034},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5803613066673279},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5434182286262512},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5313053131103516},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4720422029495239},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4703626334667206},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.46187734603881836},{"id":"https://openalex.org/keywords/robot-learning","display_name":"Robot learning","score":0.4525167942047119},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4384641945362091},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3948260545730591},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.20714643597602844},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.20570963621139526},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10395976901054382}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7791974544525146},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7098074555397034},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5803613066673279},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5434182286262512},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5313053131103516},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4720422029495239},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4703626334667206},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.46187734603881836},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.4525167942047119},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4384641945362091},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3948260545730591},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.20714643597602844},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.20570963621139526},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10395976901054382},{"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D008962","descriptor_name":"Models, Theoretical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008962","descriptor_name":"Models, Theoretical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008962","descriptor_name":"Models, Theoretical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012054","descriptor_name":"Reinforcement, Psychology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012054","descriptor_name":"Reinforcement, Psychology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012054","descriptor_name":"Reinforcement, Psychology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012201","descriptor_name":"Reward","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012201","descriptor_name":"Reward","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012201","descriptor_name":"Reward","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012371","descriptor_name":"Robotics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012371","descriptor_name":"Robotics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012371","descriptor_name":"Robotics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.1142/s0129065799000241","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0129065799000241","pdf_url":null,"source":{"id":"https://openalex.org/S197665576","display_name":"International Journal of Neural Systems","issn_l":"0129-0657","issn":["0129-0657","1793-6462"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Neural Systems","raw_type":"journal-article"},{"id":"pmid:10560764","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/10560764","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International journal of neural systems","raw_type":null},{"id":"pmid:10798711","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/10798711","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International journal of neural systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8500000238418579,"display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320997","display_name":"Funda\u00e7\u00e3o de Amparo \u00e0 Pesquisa do Estado de S\u00e3o Paulo","ror":"https://ror.org/02ddkpn78"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W1979071892","https://openalex.org/W2127290018","https://openalex.org/W2165131254","https://openalex.org/W2169982856"],"related_works":["https://openalex.org/W2044123706","https://openalex.org/W3213722473","https://openalex.org/W4225571923","https://openalex.org/W3212257828","https://openalex.org/W2999580272","https://openalex.org/W2930863966","https://openalex.org/W4297873223","https://openalex.org/W2350784623","https://openalex.org/W3009457412","https://openalex.org/W2126211886"],"abstract_inverted_index":{"Autonomous":[0],"learning":[1,27,36,52,143],"techniques":[2],"are":[3,71],"based":[4],"on":[5],"experience":[6,12],"acquisition.":[7],"In":[8],"most":[9],"realistic":[10],"applications,":[11],"is":[13],"time-consuming:":[14],"it":[15,135],"implies":[16],"sensor":[17],"reading,":[18],"actuator":[19],"control":[20],"and":[21,44,105,133],"algorithmic":[22],"update,":[23],"constrained":[24],"by":[25],"the":[26,51,63,83,101,127,130],"system":[28],"dynamics.":[29],"The":[30],"information":[31,48,92],"crudeness":[32],"upon":[33],"which":[34],"classical":[35],"algorithms":[37,70],"operate":[38],"make":[39],"such":[40,59],"problems":[41],"too":[42],"difficult":[43],"unrealistic.":[45],"Nonetheless,":[46],"additional":[47],"for":[49,88],"facilitating":[50],"process":[53],"ideally":[54],"should":[55],"be":[56,116],"embedded":[57],"in":[58,75,136,145],"a":[60,78,89,98,119,137,141,146],"way":[61],"that":[62,86],"structural,":[64],"well-studied":[65],"characteristics":[66],"of":[67,82,91,100,129,140],"these":[68],"fundamental":[69],"maintained.":[72],"We":[73,109],"investigate":[74],"this":[76,112],"article":[77],"more":[79],"general":[80],"formulation":[81,114],"Q-learning":[84],"method":[85],"allows":[87],"spreading":[90],"derived":[93],"from":[94],"single":[95],"updates":[96],"towards":[97],"neighbourhood":[99],"instantly":[102],"visited":[103],"state":[104,131],"converges":[106],"to":[107,121],"optimality.":[108],"show":[110],"how":[111],"new":[113],"can":[115],"used":[117],"as":[118],"mechanism":[120],"safely":[122],"embed":[123],"prior":[124],"knowledge":[125],"about":[126],"structure":[128],"space,":[132],"demonstrate":[134],"modified":[138],"implementation":[139],"reinforcement":[142],"algorithm":[144],"real":[147],"robot":[148],"navigation":[149],"task.":[150]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2016-06-24T00:00:00"}