{"id":"https://openalex.org/W2103303252","doi":"https://doi.org/10.1109/ijcnn.2003.1224032","title":"An enhanced least-squares approach for reinforcement learning","display_name":"An enhanced least-squares approach for reinforcement learning","publication_year":2004,"publication_date":"2004-06-22","ids":{"openalex":"https://openalex.org/W2103303252","doi":"https://doi.org/10.1109/ijcnn.2003.1224032","mag":"2103303252"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn.2003.1224032","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2003.1224032","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Joint Conference on Neural Networks, 2003.","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"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/A5031118344","display_name":"Hailin Li","orcid":"https://orcid.org/0000-0001-6924-9689"},"institutions":[{"id":"https://openalex.org/I4210116219","display_name":"Engineering Systems (United States)","ror":"https://ror.org/02qg60849","country_code":"US","type":"company","lineage":["https://openalex.org/I4210116219"]},{"id":"https://openalex.org/I20382870","display_name":"Missouri University of Science and Technology","ror":"https://ror.org/00scwqd12","country_code":"US","type":"education","lineage":["https://openalex.org/I20382870"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Hailin Li","raw_affiliation_strings":["Department of Engineering Management, Smart Engineering Systems Laboratory,  229 Engineering Management, University of Missouri, Rolla, Rolla, MO, USA","Dept. of Eng. Manage., Missouri Univ., Rolla, MO, USA"],"affiliations":[{"raw_affiliation_string":"Department of Engineering Management, Smart Engineering Systems Laboratory,  229 Engineering Management, University of Missouri, Rolla, Rolla, MO, USA","institution_ids":["https://openalex.org/I20382870","https://openalex.org/I4210116219"]},{"raw_affiliation_string":"Dept. of Eng. Manage., Missouri Univ., Rolla, MO, USA","institution_ids":["https://openalex.org/I20382870"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5096811505","display_name":"C.H. Dagh","orcid":null},"institutions":[{"id":"https://openalex.org/I20382870","display_name":"Missouri University of Science and Technology","ror":"https://ror.org/00scwqd12","country_code":"US","type":"education","lineage":["https://openalex.org/I20382870"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"C.H. Dagh","raw_affiliation_strings":["Dept. of Eng. Manage., Missouri Univ., Rolla, MO, USA"],"affiliations":[{"raw_affiliation_string":"Dept. of Eng. Manage., Missouri Univ., Rolla, MO, USA","institution_ids":["https://openalex.org/I20382870"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5031118344"],"corresponding_institution_ids":["https://openalex.org/I20382870","https://openalex.org/I4210116219"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.10480239,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"4","issue":null,"first_page":"2905","last_page":"2909"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11749","display_name":"Iterative Learning Control Systems","score":0.9986000061035156,"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/T11749","display_name":"Iterative Learning Control Systems","score":0.9986000061035156,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9962000250816345,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8242959380149841},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7384556531906128},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6598049402236938},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5228520035743713},{"id":"https://openalex.org/keywords/least-squares-function-approximation","display_name":"Least-squares function approximation","score":0.4301237463951111},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4148196876049042},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.39038029313087463},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1589052677154541}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8242959380149841},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7384556531906128},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6598049402236938},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5228520035743713},{"id":"https://openalex.org/C9936470","wikidata":"https://www.wikidata.org/wiki/Q6510405","display_name":"Least-squares function approximation","level":3,"score":0.4301237463951111},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4148196876049042},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.39038029313087463},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1589052677154541},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn.2003.1224032","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2003.1224032","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Joint Conference on Neural Networks, 2003.","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1492936035","https://openalex.org/W1502893368","https://openalex.org/W2072931156","https://openalex.org/W2099833070","https://openalex.org/W2100677568","https://openalex.org/W2107726111","https://openalex.org/W3011120880","https://openalex.org/W3041202696","https://openalex.org/W4246906609","https://openalex.org/W6629236817","https://openalex.org/W6630339688","https://openalex.org/W6675086535","https://openalex.org/W6775686901"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W2031695474","https://openalex.org/W2024136090","https://openalex.org/W2586732548","https://openalex.org/W3049728571","https://openalex.org/W2964765435","https://openalex.org/W2585069576"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"an":[3],"enhanced":[4],"least-squares":[5,14,65],"approach":[6,86],"for":[7,23,69],"solving":[8],"reinforcement":[9],"learning":[10,25,82,109],"control":[11,110],"problems.":[12],"Model-free":[13],"policy":[15,40],"iteration":[16],"(LSPI)":[17],"method":[18,68],"has":[19],"been":[20],"successfully":[21],"used":[22],"this":[24],"domain.":[26],"Although":[27],"LSPI":[28,88],"is":[29],"a":[30,79,97],"promising":[31],"algorithm":[32,89],"that":[33],"uses":[34,94],"linear":[35],"approximator":[36],"architecture":[37],"to":[38,99],"achieve":[39],"optimization":[41],"in":[42,51],"the":[43,54,71,101,108,115,118],"spirit":[44],"of":[45,53,56,73,111,117],"Q-learning,":[46],"it":[47],"faces":[48],"challenging":[49],"issues":[50],"terms":[52],"selection":[55],"basis":[57],"functions":[58],"and":[59,93],"training":[60],"samples.":[61],"Inspired":[62],"by":[63],"orthogonal":[64],"regression":[66],"(OLSR)":[67],"selecting":[70],"centers":[72],"RBF":[74],"neural":[75],"network,":[76],"we":[77],"propose":[78],"new":[80],"hybrid":[81],"method.":[83],"The":[84,105],"suggested":[85],"combines":[87],"with":[90],"OLSR":[91],"strategy":[92],"simulation":[95],"as":[96],"tool":[98],"guide":[100],"\"feature":[102],"processing\"":[103],"procedure.":[104],"results":[106],"on":[107],"cart-pole":[112],"system":[113],"illustrate":[114],"effectiveness":[116],"presented":[119],"scheme.":[120]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}