{"id":"https://openalex.org/W4402452682","doi":"https://doi.org/10.1007/s10489-024-05806-2","title":"An offline-to-online reinforcement learning approach based on multi-action evaluation with policy extension","display_name":"An offline-to-online reinforcement learning approach based on multi-action evaluation with policy extension","publication_year":2024,"publication_date":"2024-09-11","ids":{"openalex":"https://openalex.org/W4402452682","doi":"https://doi.org/10.1007/s10489-024-05806-2"},"language":"en","primary_location":{"id":"doi:10.1007/s10489-024-05806-2","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s10489-024-05806-2","pdf_url":null,"source":{"id":"https://openalex.org/S74726891","display_name":"Applied Intelligence","issn_l":"0924-669X","issn":["0924-669X","1573-7497"],"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":"Applied Intelligence","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/A5102533727","display_name":"Xuebo Cheng","orcid":null},"institutions":[{"id":"https://openalex.org/I13985625","display_name":"East China Jiaotong University","ror":"https://ror.org/05x2f1m38","country_code":"CN","type":"education","lineage":["https://openalex.org/I13985625"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuebo Cheng","raw_affiliation_strings":["School of Information and Engineering, East China Jiaotong University, Nanchang, 330000, Jiangxi, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information and Engineering, East China Jiaotong University, Nanchang, 330000, Jiangxi, China","institution_ids":["https://openalex.org/I13985625"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052480553","display_name":"Xiaohui Huang","orcid":"https://orcid.org/0000-0001-7269-4484"},"institutions":[{"id":"https://openalex.org/I13985625","display_name":"East China Jiaotong University","ror":"https://ror.org/05x2f1m38","country_code":"CN","type":"education","lineage":["https://openalex.org/I13985625"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiaohui Huang","raw_affiliation_strings":["School of Information and Engineering, East China Jiaotong University, Nanchang, 330000, Jiangxi, China"],"raw_orcid":"https://orcid.org/0000-0001-7269-4484","affiliations":[{"raw_affiliation_string":"School of Information and Engineering, East China Jiaotong University, Nanchang, 330000, Jiangxi, China","institution_ids":["https://openalex.org/I13985625"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101547686","display_name":"Zhichao Huang","orcid":"https://orcid.org/0000-0002-7662-5184"},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhichao Huang","raw_affiliation_strings":["JD Intelligent Cities Research, JD iCity, JD Technology, Beijing, 100000, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"JD Intelligent Cities Research, JD iCity, JD Technology, Beijing, 100000, China","institution_ids":["https://openalex.org/I4210103986"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080377353","display_name":"Nan Jiang","orcid":"https://orcid.org/0000-0002-8838-7427"},"institutions":[{"id":"https://openalex.org/I13985625","display_name":"East China Jiaotong University","ror":"https://ror.org/05x2f1m38","country_code":"CN","type":"education","lineage":["https://openalex.org/I13985625"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Nan Jiang","raw_affiliation_strings":["School of Information and Engineering, East China Jiaotong University, Nanchang, 330000, Jiangxi, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information and Engineering, East China Jiaotong University, Nanchang, 330000, Jiangxi, China","institution_ids":["https://openalex.org/I13985625"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5052480553"],"corresponding_institution_ids":["https://openalex.org/I13985625"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":null,"fwci":0.9116,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.79189334,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"54","issue":"23","first_page":"12246","last_page":"12271"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9972000122070312,"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":0.9972000122070312,"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/T14011","display_name":"Elevator Systems and Control","score":0.9810000061988831,"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/T12546","display_name":"Smart Parking Systems Research","score":0.9535999894142151,"subfield":{"id":"https://openalex.org/subfields/2215","display_name":"Building and Construction"},"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/computer-science","display_name":"Computer science","score":0.9198136329650879},{"id":"https://openalex.org/keywords/extension","display_name":"Extension (predicate logic)","score":0.8185122013092041},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.812720775604248},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5343377590179443},{"id":"https://openalex.org/keywords/online-and-offline","display_name":"Online and offline","score":0.49604424834251404},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42216914892196655},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.42197442054748535},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.37745124101638794},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.37262338399887085},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.11606243252754211},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.06609782576560974}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9198136329650879},{"id":"https://openalex.org/C2778029271","wikidata":"https://www.wikidata.org/wiki/Q5421931","display_name":"Extension (predicate logic)","level":2,"score":0.8185122013092041},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.812720775604248},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5343377590179443},{"id":"https://openalex.org/C2780102126","wikidata":"https://www.wikidata.org/wiki/Q10928179","display_name":"Online and offline","level":2,"score":0.49604424834251404},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42216914892196655},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.42197442054748535},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.37745124101638794},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37262338399887085},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.11606243252754211},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.06609782576560974},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"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/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s10489-024-05806-2","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s10489-024-05806-2","pdf_url":null,"source":{"id":"https://openalex.org/S74726891","display_name":"Applied Intelligence","issn_l":"0924-669X","issn":["0924-669X","1573-7497"],"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":"Applied Intelligence","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2877108929","display_name":null,"funder_award_id":"62062033","funder_id":"https://openalex.org/F4320315254","funder_display_name":"Innovative Research Group Project of the National Natural Science Foundation of China"},{"id":"https://openalex.org/G4824052134","display_name":null,"funder_award_id":"20232BAB202018","funder_id":"https://openalex.org/F4320322665","funder_display_name":"Natural Science Foundation of Jiangxi Province"}],"funders":[{"id":"https://openalex.org/F4320315254","display_name":"Innovative Research Group Project of the National Natural Science Foundation of China","ror":null},{"id":"https://openalex.org/F4320322665","display_name":"Natural Science Foundation of Jiangxi Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1583837637","https://openalex.org/W2062118960","https://openalex.org/W2604738573","https://openalex.org/W2891655128","https://openalex.org/W2911293880","https://openalex.org/W2952472710","https://openalex.org/W4318159260","https://openalex.org/W4385382152","https://openalex.org/W4385626984","https://openalex.org/W4386214263","https://openalex.org/W4388543828","https://openalex.org/W6600727173","https://openalex.org/W6824051750"],"related_works":["https://openalex.org/W2920061524","https://openalex.org/W4310083477","https://openalex.org/W2328553770","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/W4225619808"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-06-13T06:13:01.061226","created_date":"2025-10-10T00:00:00"}
