{"id":"https://openalex.org/W2095722088","doi":"https://doi.org/10.1109/tpami.1986.4767793","title":"An Algorithm for Learning Without External Supervision and Its Application to Learning Control Systems","display_name":"An Algorithm for Learning Without External Supervision and Its Application to Learning Control Systems","publication_year":1986,"publication_date":"1986-05-01","ids":{"openalex":"https://openalex.org/W2095722088","doi":"https://doi.org/10.1109/tpami.1986.4767793","mag":"2095722088","pmid":"https://pubmed.ncbi.nlm.nih.gov/21869349"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.1986.4767793","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.1986.4767793","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","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/A5058916231","display_name":"Z. J. Nikolic","orcid":null},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Z. J. Nikolic","raw_affiliation_strings":["Purdue University, Lafayette, Ind","Purdue University, Lafayette, IN, USA"],"affiliations":[{"raw_affiliation_string":"Purdue University, Lafayette, Ind","institution_ids":[]},{"raw_affiliation_string":"Purdue University, Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103574733","display_name":"Kuan-Yu Fu","orcid":null},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"K. S. Fu","raw_affiliation_strings":["Purdue University, Lafayette, IN, USA"],"affiliations":[{"raw_affiliation_string":"Purdue University, Lafayette, IN, USA","institution_ids":["https://openalex.org/I219193219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5058916231"],"corresponding_institution_ids":["https://openalex.org/I219193219"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.26400981,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"PAMI-8","issue":"3","first_page":"304","last_page":"312"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.9995999932289124,"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"}},"topics":[{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.9995999932289124,"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/T11236","display_name":"Control Systems and Identification","score":0.9936000108718872,"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/T10876","display_name":"Fault Detection and Control Systems","score":0.9908000230789185,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.6580439805984497},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.6224456429481506},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6005862355232239},{"id":"https://openalex.org/keywords/conditional-probability","display_name":"Conditional probability","score":0.5994070172309875},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5979124307632446},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5807359218597412},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5659182667732239},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.5441251397132874},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4835371971130371},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4684838056564331},{"id":"https://openalex.org/keywords/random-variable","display_name":"Random variable","score":0.42786216735839844},{"id":"https://openalex.org/keywords/conditional-expectation","display_name":"Conditional expectation","score":0.42278972268104553},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4188454747200012},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3205808997154236},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2899283766746521},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.095635324716568}],"concepts":[{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.6580439805984497},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.6224456429481506},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6005862355232239},{"id":"https://openalex.org/C44492722","wikidata":"https://www.wikidata.org/wiki/Q327069","display_name":"Conditional probability","level":2,"score":0.5994070172309875},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5979124307632446},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5807359218597412},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5659182667732239},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.5441251397132874},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4835371971130371},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4684838056564331},{"id":"https://openalex.org/C122123141","wikidata":"https://www.wikidata.org/wiki/Q176623","display_name":"Random variable","level":2,"score":0.42786216735839844},{"id":"https://openalex.org/C186215838","wikidata":"https://www.wikidata.org/wiki/Q772232","display_name":"Conditional expectation","level":2,"score":0.42278972268104553},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4188454747200012},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3205808997154236},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2899283766746521},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.095635324716568},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.1986.4767793","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.1986.4767793","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:21869349","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/21869349","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":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1526146785","https://openalex.org/W1527117384","https://openalex.org/W1575017126","https://openalex.org/W2009220676","https://openalex.org/W2103116581","https://openalex.org/W2111195237","https://openalex.org/W2138618395","https://openalex.org/W2157867149","https://openalex.org/W2547990408","https://openalex.org/W2570723800","https://openalex.org/W2795622704","https://openalex.org/W2799137445","https://openalex.org/W3009086382","https://openalex.org/W3216858661","https://openalex.org/W4237171445","https://openalex.org/W6634506789"],"related_works":["https://openalex.org/W2575822034","https://openalex.org/W2365248444","https://openalex.org/W2064864137","https://openalex.org/W2694207508","https://openalex.org/W4239087487","https://openalex.org/W4384376816","https://openalex.org/W4250630220","https://openalex.org/W4210738546","https://openalex.org/W4233361406","https://openalex.org/W4285709146"],"abstract_inverted_index":{"An":[0],"algorithm":[1,91,145],"is":[2,41,55,71,92,105,142,146],"proposed":[3],"for":[4,51,63],"the":[5,46,52,72,76,83,87,101,108,111,115,118,123,136,138],"design":[6],"of":[7,20,28,75,110,114,128],"``on-line''":[8],"learning":[9],"controllers":[10],"to":[11,57,82],"control":[12,22],"a":[13,25,149],"discrete":[14,129],"stochastic":[15],"plant.":[16],"The":[17,48,67,90,126,144],"subjective":[18,49,124],"probabilities":[19],"applying":[21],"actions":[23,30],"from":[24],"finite":[26],"set":[27],"allowable":[29,88,116],"using":[31],"random":[32],"strategy,":[33],"after":[34],"any":[35,64],"plant-environment":[36],"situation":[37],"(called":[38],"an":[39],"``event'')":[40],"observed,":[42],"are":[43,133,157],"modified":[44],"through":[45,94],"algorithm.":[47],"probability":[50,61],"optimal":[53],"action":[54],"proved":[56],"approach":[58],"one":[59,62],"with":[60,80,148],"observed":[65,84],"event.":[66],"optimized":[68],"performance":[69,78,112],"index":[70],"conditional":[73],"expectation":[74],"instantaneous":[77],"evaluations":[79],"respect":[81],"events":[85],"and":[86,98,130,153],"actions.":[89],"described":[93],"two":[95],"transformations,":[96],"T1,":[97],"T2.":[99],"After":[100],"``ordering":[102],"transformation''":[103,120],"T1":[104],"applied":[106],"on":[107],"estimates":[109],"indexes":[113],"actions,":[117],"``learning":[119],"T2":[121],"modifies":[122],"probabilities.":[125],"cases":[127],"continuous":[131],"features":[132],"considered.":[134],"In":[135],"latter,":[137],"Potential":[139],"Function":[140],"Method":[141],"employed.":[143],"compared":[147],"linear":[150],"reinforcement":[151],"schenme":[152],"computer":[154],"simulation":[155],"results":[156],"presented.":[158]},"counts_by_year":[{"year":2015,"cited_by_count":1}],"updated_date":"2026-01-13T01:12:25.745995","created_date":"2025-10-10T00:00:00"}