{"id":"https://openalex.org/W4409315720","doi":"https://doi.org/10.1007/s10994-025-06763-8","title":"Data-efficient reinforcement learning by generalized value estimation","display_name":"Data-efficient reinforcement learning by generalized value estimation","publication_year":2025,"publication_date":"2025-04-10","ids":{"openalex":"https://openalex.org/W4409315720","doi":"https://doi.org/10.1007/s10994-025-06763-8"},"language":"en","primary_location":{"id":"doi:10.1007/s10994-025-06763-8","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s10994-025-06763-8","pdf_url":null,"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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5013696178","display_name":"Junjie Zhou","orcid":"https://orcid.org/0000-0003-4134-5382"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Junjie Zhou","raw_affiliation_strings":["School of management, Hefei University of Technology, Hefei, 230009, China"],"affiliations":[{"raw_affiliation_string":"School of management, Hefei University of Technology, Hefei, 230009, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073116946","display_name":"Ying Tian","orcid":"https://orcid.org/0000-0001-8065-7042"},"institutions":[{"id":"https://openalex.org/I115592961","display_name":"Jiangsu University","ror":"https://ror.org/03jc41j30","country_code":"CN","type":"education","lineage":["https://openalex.org/I115592961"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Tian","raw_affiliation_strings":["Modern Equipment Manufacturing Department, Zhenjiang College, Zhenjiang, 212000, China"],"affiliations":[{"raw_affiliation_string":"Modern Equipment Manufacturing Department, Zhenjiang College, Zhenjiang, 212000, China","institution_ids":["https://openalex.org/I115592961"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043281628","display_name":"Minglun Ren","orcid":"https://orcid.org/0000-0001-5107-2133"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Minglun Ren","raw_affiliation_strings":["School of management, Hefei University of Technology, Hefei, 230009, China"],"affiliations":[{"raw_affiliation_string":"School of management, Hefei University of Technology, Hefei, 230009, China","institution_ids":["https://openalex.org/I16365422"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5013696178"],"corresponding_institution_ids":["https://openalex.org/I16365422"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":null,"fwci":2.6995,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.89665205,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"114","issue":"6","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":0.9991999864578247,"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":0.9991999864578247,"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":0.9857000112533569,"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/T10524","display_name":"Traffic control and management","score":0.9807000160217285,"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":0.746194064617157},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5175065994262695},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5038473010063171},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.4669930040836334},{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.4228825867176056},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4209280014038086},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4195422828197479},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3868616223335266},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.10449877381324768},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0705907940864563}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.746194064617157},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5175065994262695},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5038473010063171},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.4669930040836334},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.4228825867176056},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4209280014038086},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4195422828197479},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3868616223335266},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.10449877381324768},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0705907940864563},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s10994-025-06763-8","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s10994-025-06763-8","pdf_url":null,"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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W2110485445","https://openalex.org/W2145339207","https://openalex.org/W2157331557","https://openalex.org/W2158782408","https://openalex.org/W2173248099","https://openalex.org/W2593237273","https://openalex.org/W2596758708","https://openalex.org/W2739473244","https://openalex.org/W2746553466","https://openalex.org/W2761873684","https://openalex.org/W2765302304","https://openalex.org/W2781726626","https://openalex.org/W2787938642","https://openalex.org/W2789824229","https://openalex.org/W2805762288","https://openalex.org/W2810754397","https://openalex.org/W2859967432","https://openalex.org/W2902907165","https://openalex.org/W2950624398","https://openalex.org/W2995509794","https://openalex.org/W2996449210","https://openalex.org/W3004029932","https://openalex.org/W3009660502","https://openalex.org/W3094125909","https://openalex.org/W3121786643","https://openalex.org/W3162450516","https://openalex.org/W3178845376","https://openalex.org/W3215181478","https://openalex.org/W3216283008","https://openalex.org/W4214717370","https://openalex.org/W4306632396","https://openalex.org/W4387171816","https://openalex.org/W4388184601","https://openalex.org/W4393160261","https://openalex.org/W4399116257","https://openalex.org/W6638018090","https://openalex.org/W6677916085","https://openalex.org/W6741002519","https://openalex.org/W6754479021"],"related_works":["https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2145821588","https://openalex.org/W2086122291","https://openalex.org/W1987513656"],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
