{"id":"https://openalex.org/W2154152229","doi":null,"title":"IMPROVING THE PERFORMANCE OF Q-LEARNING WITH LOCALLY WEIGHTED REGRESSION","display_name":"IMPROVING THE PERFORMANCE OF Q-LEARNING WITH LOCALLY WEIGHTED REGRESSION","publication_year":2001,"publication_date":"2001-01-01","ids":{"openalex":"https://openalex.org/W2154152229","mag":"2154152229"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.21.5009","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.21.5009","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://mil.ufl.edu/~luck/thesis.pdf","raw_type":"text"},"volume":null,"type":"article","is_traditional":true,"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/A5005600521","display_name":"Halim Aljibury","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Halim Aljibury","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5005600521"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.0,"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/T12072","display_name":"Machine Learning and Algorithms","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"}}],"keywords":[{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.9919999837875366},{"id":"https://openalex.org/keywords/locally-weighted-regression","display_name":"locally weighted regression","score":0.9940000176429749},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"curse of dimensionality","score":0.7820000052452087},{"id":"https://openalex.org/keywords/function-approximation","display_name":"function approximation","score":0.8709999918937683},{"id":"https://openalex.org/keywords/value-function-learning","display_name":"value function learning","score":0.765999972820282},{"id":"https://openalex.org/keywords/robot-control","display_name":"robot control","score":0.5649999976158142}],"concepts":[{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.502192497253418},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4358586072921753},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4009660482406616},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.327297180891037},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.30325767397880554}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.21.5009","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.21.5009","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://mil.ufl.edu/~luck/thesis.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.217.3116","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.217.3116","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.mil.ufl.edu/publications/thes_diss/Hal_Aljibury_thesis.pdf","raw_type":"text"},{"id":"mag:2154152229","doi":null,"is_oa":false,"landing_page_url":"https://www.mil.ufl.edu/publications/thes_diss/Hal_Aljibury_thesis.pdf","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W6242441","https://openalex.org/W32403112","https://openalex.org/W98997153","https://openalex.org/W1502001434","https://openalex.org/W1506832649","https://openalex.org/W1540502646","https://openalex.org/W1541084404","https://openalex.org/W1552148478","https://openalex.org/W1597173708","https://openalex.org/W1657674574","https://openalex.org/W1667009210","https://openalex.org/W1689445748","https://openalex.org/W1997255626","https://openalex.org/W2009533501","https://openalex.org/W2052117683","https://openalex.org/W2089415692","https://openalex.org/W2103626435","https://openalex.org/W2107726111","https://openalex.org/W2109952767","https://openalex.org/W2122701159","https://openalex.org/W2125074935","https://openalex.org/W2125510930","https://openalex.org/W2139418546","https://openalex.org/W2150339816","https://openalex.org/W2165131254","https://openalex.org/W2341171179","https://openalex.org/W2912185451","https://openalex.org/W3011120880","https://openalex.org/W3139377883"],"related_works":["https://openalex.org/W7098649383","https://openalex.org/W2155337959","https://openalex.org/W7098200929","https://openalex.org/W1857080389","https://openalex.org/W7099815579","https://openalex.org/W213783005","https://openalex.org/W7135732392","https://openalex.org/W2123955331","https://openalex.org/W6903604908","https://openalex.org/W2108049979"],"abstract_inverted_index":{"Oftentimes,":[0],"the":[1,20,36,43,46,55,88,103],"problem":[2,13,28,69],"faced":[3],"by":[4,53],"researchers":[5,31],"applying":[6],"reinforcement":[7],"learning":[8,87],"to":[9,66,106,112],"a":[10,26,51,58,67,73,92,113],"nontrivial":[11],"robotics":[12],"is":[14,25],"that":[15],"they":[16],"run":[17],"head-on":[18],"into":[19],"curse":[21],"of":[22,38,45,57,79,86,95],"dimensionality.":[23],"This":[24,48],"particular":[27],"for":[29],"those":[30,109],"using":[32,102],"discrete-state":[33,59],"algorithms,":[34],"as":[35],"number":[37,94],"states":[39,111],"exponentially":[40],"increase":[41],"with":[42,72],"complexity":[44],"problem.":[47],"thesis":[49],"provides":[50],"method":[52,77],"which":[54],"performance":[56],"algorithm":[60],"can":[61],"be":[62],"improved":[63],"when":[64],"applied":[65],"continuous-state":[68],"in":[70],"combination":[71],"function":[74,90,104],"approximator.":[75],"The":[76,82,98],"consists":[78,85],"two":[80],"steps.":[81],"first":[83],"step":[84,100],"value":[89],"over":[91],"small":[93],"discrete":[96,110],"states.":[97],"second":[99],"involves":[101],"approximator":[105],"generalize":[107],"from":[108],"continuous":[114],"state":[115],"space.":[116]},"counts_by_year":[],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2016-06-24T00:00:00"}