{"id":"https://openalex.org/W2141559645","doi":"https://doi.org/10.1007/bf00992699","title":"Self-improving reactive agents based on reinforcement learning, planning and teaching","display_name":"Self-improving reactive agents based on reinforcement learning, planning and teaching","publication_year":1992,"publication_date":"1992-05-01","ids":{"openalex":"https://openalex.org/W2141559645","doi":"https://doi.org/10.1007/bf00992699","mag":"2141559645"},"language":"en","primary_location":{"id":"doi:10.1007/bf00992699","is_oa":true,"landing_page_url":"https://doi.org/10.1007/bf00992699","pdf_url":"https://link.springer.com/content/pdf/10.1007/BF00992699.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://link.springer.com/content/pdf/10.1007/BF00992699.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5107841673","display_name":"Long-Ji Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Long-Ji Lin","raw_affiliation_strings":["School of Computer Science, Carnegie Mellon University, 15213, Pittsburgh, Pennsylvania","School of Computer Science, Carnegie Mellon University, Pittsburgh, Pennsylvania 15213. [email\u00a0protected]#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Carnegie Mellon University, 15213, Pittsburgh, Pennsylvania","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"School of Computer Science, Carnegie Mellon University, Pittsburgh, Pennsylvania 15213. [email\u00a0protected]#TAB#","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5107841673"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":null,"fwci":27.3426,"has_fulltext":true,"cited_by_count":1649,"citation_normalized_percentile":{"value":0.99673885,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"8","issue":"3-4","first_page":"293","last_page":"321"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9965000152587891,"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":0.9965000152587891,"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":0.9697999954223633,"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":0.9666000008583069,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8232548832893372},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7178032398223877},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.534294068813324},{"id":"https://openalex.org/keywords/testbed","display_name":"Testbed","score":0.4863794147968292},{"id":"https://openalex.org/keywords/nondeterministic-algorithm","display_name":"Nondeterministic algorithm","score":0.48279011249542236},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.4513678550720215},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4368458688259125},{"id":"https://openalex.org/keywords/learning-classifier-system","display_name":"Learning classifier system","score":0.43606919050216675},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3755074143409729},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.07724055647850037},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06887543201446533}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8232548832893372},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7178032398223877},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.534294068813324},{"id":"https://openalex.org/C31395832","wikidata":"https://www.wikidata.org/wiki/Q1318674","display_name":"Testbed","level":2,"score":0.4863794147968292},{"id":"https://openalex.org/C176181172","wikidata":"https://www.wikidata.org/wiki/Q3490301","display_name":"Nondeterministic algorithm","level":2,"score":0.48279011249542236},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.4513678550720215},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4368458688259125},{"id":"https://openalex.org/C199190896","wikidata":"https://www.wikidata.org/wiki/Q3509276","display_name":"Learning classifier system","level":3,"score":0.43606919050216675},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3755074143409729},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.07724055647850037},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06887543201446533},{"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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/bf00992699","is_oa":true,"landing_page_url":"https://doi.org/10.1007/bf00992699","pdf_url":"https://link.springer.com/content/pdf/10.1007/BF00992699.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.75.7884","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.75.7884","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www-anw.cs.umass.edu/~rich/lin-92.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.1007/bf00992699","is_oa":true,"landing_page_url":"https://doi.org/10.1007/bf00992699","pdf_url":"https://link.springer.com/content/pdf/10.1007/BF00992699.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11","score":0.6700000166893005}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306101","display_name":"National Aeronautics and Space Administration","ror":"https://ror.org/027ka1x80"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2141559645.pdf","grobid_xml":"https://content.openalex.org/works/W2141559645.grobid-xml"},"referenced_works_count":42,"referenced_works":["https://openalex.org/W3185548","https://openalex.org/W50296447","https://openalex.org/W111328409","https://openalex.org/W1491843047","https://openalex.org/W1505156375","https://openalex.org/W1522632257","https://openalex.org/W1529303739","https://openalex.org/W1530666108","https://openalex.org/W1551329771","https://openalex.org/W1565134770","https://openalex.org/W1569296262","https://openalex.org/W1586504939","https://openalex.org/W1588388339","https://openalex.org/W1610678877","https://openalex.org/W1640646391","https://openalex.org/W1652505363","https://openalex.org/W1931792391","https://openalex.org/W2009207944","https://openalex.org/W2016589492","https://openalex.org/W2028145673","https://openalex.org/W2051945694","https://openalex.org/W2052117683","https://openalex.org/W2078226168","https://openalex.org/W2100677568","https://openalex.org/W2106639887","https://openalex.org/W2154642048","https://openalex.org/W2157445228","https://openalex.org/W2158091072","https://openalex.org/W2167224731","https://openalex.org/W2766736793","https://openalex.org/W2912225506","https://openalex.org/W3011120880","https://openalex.org/W3207342693","https://openalex.org/W4235411351","https://openalex.org/W6636530465","https://openalex.org/W6640629700","https://openalex.org/W6675901991","https://openalex.org/W6682886336","https://openalex.org/W6683182819","https://openalex.org/W6758710848","https://openalex.org/W6780394890","https://openalex.org/W6834815581"],"related_works":["https://openalex.org/W1966456942","https://openalex.org/W2754028433","https://openalex.org/W3148138296","https://openalex.org/W1882507001","https://openalex.org/W2367922714","https://openalex.org/W2352650970","https://openalex.org/W2534140487","https://openalex.org/W4383501708","https://openalex.org/W2041126907","https://openalex.org/W2130711276"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":13},{"year":2025,"cited_by_count":84},{"year":2024,"cited_by_count":99},{"year":2023,"cited_by_count":129},{"year":2022,"cited_by_count":112},{"year":2021,"cited_by_count":194},{"year":2020,"cited_by_count":207},{"year":2019,"cited_by_count":143},{"year":2018,"cited_by_count":90},{"year":2017,"cited_by_count":51},{"year":2016,"cited_by_count":41},{"year":2015,"cited_by_count":22},{"year":2014,"cited_by_count":14},{"year":2013,"cited_by_count":19},{"year":2012,"cited_by_count":18}],"updated_date":"2026-05-08T15:41:06.802602","created_date":"2025-10-10T00:00:00"}
