{"id":"https://openalex.org/W2754526012","doi":"https://doi.org/10.1007/s10586-017-1165-0","title":"An off-policy least square algorithms with eligibility trace based on importance reweighting","display_name":"An off-policy least square algorithms with eligibility trace based on importance reweighting","publication_year":2017,"publication_date":"2017-09-12","ids":{"openalex":"https://openalex.org/W2754526012","doi":"https://doi.org/10.1007/s10586-017-1165-0","mag":"2754526012"},"language":"en","primary_location":{"id":"doi:10.1007/s10586-017-1165-0","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s10586-017-1165-0","pdf_url":null,"source":{"id":"https://openalex.org/S106148199","display_name":"Cluster Computing","issn_l":"1386-7857","issn":["1386-7857","1573-7543"],"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":"Cluster Computing","raw_type":"journal-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/A5101927223","display_name":"Haifei Zhang","orcid":"https://orcid.org/0000-0003-4488-1631"},"institutions":[{"id":"https://openalex.org/I199305430","display_name":"Nantong University","ror":"https://ror.org/02afcvw97","country_code":"CN","type":"education","lineage":["https://openalex.org/I199305430"]},{"id":"https://openalex.org/I163340411","display_name":"Hohai University","ror":"https://ror.org/01wd4xt90","country_code":"CN","type":"education","lineage":["https://openalex.org/I163340411"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Haifei Zhang","raw_affiliation_strings":["School of Computer and Information Engineering, Hohai University, Nanjing, China","School of Computer and Information Engineering, Nantong Institute of Technology, Nantong, China"],"affiliations":[{"raw_affiliation_string":"School of Computer and Information Engineering, Hohai University, Nanjing, China","institution_ids":["https://openalex.org/I163340411"]},{"raw_affiliation_string":"School of Computer and Information Engineering, Nantong Institute of Technology, Nantong, China","institution_ids":["https://openalex.org/I199305430"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101196007","display_name":"Ying Hong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ying Hong","raw_affiliation_strings":["Center of International Education and Exchange, Jiangsu College of Engineering and Technology, Nantong, China"],"affiliations":[{"raw_affiliation_string":"Center of International Education and Exchange, Jiangsu College of Engineering and Technology, Nantong, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112780689","display_name":"Jianlin Qiu","orcid":"https://orcid.org/0009-0004-7835-7621"},"institutions":[{"id":"https://openalex.org/I199305430","display_name":"Nantong University","ror":"https://ror.org/02afcvw97","country_code":"CN","type":"education","lineage":["https://openalex.org/I199305430"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianlin Qiu","raw_affiliation_strings":["School of Computer Science and Technology, Nantong University, Nantong, China","School of Computer and Information Engineering, Nantong Institute of Technology, Nantong, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Nantong University, Nantong, China","institution_ids":["https://openalex.org/I199305430"]},{"raw_affiliation_string":"School of Computer and Information Engineering, Nantong Institute of Technology, Nantong, China","institution_ids":["https://openalex.org/I199305430"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101927223"],"corresponding_institution_ids":["https://openalex.org/I163340411","https://openalex.org/I199305430"],"apc_list":{"value":2190,"currency":"EUR","value_usd":2790},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.13584802,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"20","issue":"4","first_page":"3475","last_page":"3487"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9988999962806702,"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":0.9988999962806702,"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":0.9936000108718872,"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"}},{"id":"https://openalex.org/T14011","display_name":"Elevator Systems and Control","score":0.9804999828338623,"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":0.9291775822639465},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8203645944595337},{"id":"https://openalex.org/keywords/trace","display_name":"TRACE (psycholinguistics)","score":0.7367525100708008},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.6931947469711304},{"id":"https://openalex.org/keywords/square","display_name":"Square (algebra)","score":0.6691607236862183},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.6022148728370667},{"id":"https://openalex.org/keywords/rate-of-convergence","display_name":"Rate of convergence","score":0.4770766496658325},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"Temporal difference learning","score":0.4731346666812897},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.46707087755203247},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.4461013972759247},{"id":"https://openalex.org/keywords/function-approximation","display_name":"Function approximation","score":0.44189244508743286},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4164707660675049},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2836054265499115},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12970265746116638},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.07131394743919373},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.059317171573638916}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9291775822639465},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8203645944595337},{"id":"https://openalex.org/C75291252","wikidata":"https://www.wikidata.org/wiki/Q1315756","display_name":"TRACE (psycholinguistics)","level":2,"score":0.7367525100708008},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6931947469711304},{"id":"https://openalex.org/C135692309","wikidata":"https://www.wikidata.org/wiki/Q111124","display_name":"Square (algebra)","level":2,"score":0.6691607236862183},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.6022148728370667},{"id":"https://openalex.org/C57869625","wikidata":"https://www.wikidata.org/wiki/Q1783502","display_name":"Rate of convergence","level":3,"score":0.4770766496658325},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.4731346666812897},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.46707087755203247},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.4461013972759247},{"id":"https://openalex.org/C91873725","wikidata":"https://www.wikidata.org/wiki/Q3445816","display_name":"Function approximation","level":3,"score":0.44189244508743286},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4164707660675049},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2836054265499115},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12970265746116638},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.07131394743919373},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.059317171573638916},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s10586-017-1165-0","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s10586-017-1165-0","pdf_url":null,"source":{"id":"https://openalex.org/S106148199","display_name":"Cluster Computing","issn_l":"1386-7857","issn":["1386-7857","1573-7543"],"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":"Cluster Computing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.6700000166893005}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W169981297","https://openalex.org/W1502893368","https://openalex.org/W1579026795","https://openalex.org/W1580425441","https://openalex.org/W1980241579","https://openalex.org/W1981276685","https://openalex.org/W1995515585","https://openalex.org/W2072931156","https://openalex.org/W2075268401","https://openalex.org/W2084202551","https://openalex.org/W2099833070","https://openalex.org/W2100677568","https://openalex.org/W2104753538","https://openalex.org/W2107726111","https://openalex.org/W2109330238","https://openalex.org/W2132351269","https://openalex.org/W2139418546","https://openalex.org/W2147839652","https://openalex.org/W2150923691","https://openalex.org/W2165905123","https://openalex.org/W2166282269","https://openalex.org/W2415292238","https://openalex.org/W2610686804","https://openalex.org/W2914656440","https://openalex.org/W2963705262","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2341346307","https://openalex.org/W3096874164","https://openalex.org/W2154399718","https://openalex.org/W2166117066","https://openalex.org/W2357975469","https://openalex.org/W2136202932","https://openalex.org/W2145363145","https://openalex.org/W2152445738","https://openalex.org/W3148138296","https://openalex.org/W4388937744"],"abstract_inverted_index":null,"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}