{"id":"https://openalex.org/W4402380779","doi":"https://doi.org/10.1007/s10489-024-05508-9","title":"A multi-step on-policy deep reinforcement learning method assisted by off-policy policy evaluation","display_name":"A multi-step on-policy deep reinforcement learning method assisted by off-policy policy evaluation","publication_year":2024,"publication_date":"2024-09-09","ids":{"openalex":"https://openalex.org/W4402380779","doi":"https://doi.org/10.1007/s10489-024-05508-9"},"language":"en","primary_location":{"id":"doi:10.1007/s10489-024-05508-9","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s10489-024-05508-9","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/A5101688283","display_name":"Huaqing Zhang","orcid":"https://orcid.org/0000-0002-4218-7542"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huaqing Zhang","raw_affiliation_strings":["School of Automation, Beijing Institute of Technology, No.5, South Street, Zhongguancun, Beijing, 100081, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Automation, Beijing Institute of Technology, No.5, South Street, Zhongguancun, Beijing, 100081, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072523018","display_name":"Hongbin Ma","orcid":"https://orcid.org/0000-0002-5734-3157"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hongbin Ma","raw_affiliation_strings":["School of Automation, Beijing Institute of Technology, No.5, South Street, Zhongguancun, Beijing, 100081, China"],"raw_orcid":"https://orcid.org/0000-0002-5734-3157","affiliations":[{"raw_affiliation_string":"School of Automation, Beijing Institute of Technology, No.5, South Street, Zhongguancun, Beijing, 100081, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041868298","display_name":"Bemnet Wondimagegnehu Mersha","orcid":"https://orcid.org/0000-0002-1000-8984"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bemnet Wondimagegnehu Mersha","raw_affiliation_strings":["School of Automation, Beijing Institute of Technology, No.5, South Street, Zhongguancun, Beijing, 100081, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Automation, Beijing Institute of Technology, No.5, South Street, Zhongguancun, Beijing, 100081, China","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100776901","display_name":"Ying Jin","orcid":"https://orcid.org/0000-0001-9475-7538"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Jin","raw_affiliation_strings":["School of Automation, Beijing Institute of Technology, No.5, South Street, Zhongguancun, Beijing, 100081, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Automation, Beijing Institute of Technology, No.5, South Street, Zhongguancun, Beijing, 100081, China","institution_ids":["https://openalex.org/I125839683"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5072523018"],"corresponding_institution_ids":["https://openalex.org/I125839683"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":null,"fwci":0.2778,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.6193925,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"54","issue":"21","first_page":"11144","last_page":"11159"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9979000091552734,"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":0.9979000091552734,"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":0.980400025844574,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9772999882698059,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.9140702486038208},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8666178584098816},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4439631700515747},{"id":"https://openalex.org/keywords/policy-learning","display_name":"Policy learning","score":0.4417007565498352},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.30924999713897705}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9140702486038208},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8666178584098816},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4439631700515747},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.4417007565498352},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.30924999713897705}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s10489-024-05508-9","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s10489-024-05508-9","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/G2646844173","display_name":null,"funder_award_id":"62076028","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W2096698697","https://openalex.org/W2145339207","https://openalex.org/W2150468603","https://openalex.org/W2173248099","https://openalex.org/W2610686804","https://openalex.org/W2726187156","https://openalex.org/W2736601468","https://openalex.org/W2787938642","https://openalex.org/W2950492145","https://openalex.org/W2951923023","https://openalex.org/W2952967722","https://openalex.org/W2963403143","https://openalex.org/W2964043796","https://openalex.org/W2966349401","https://openalex.org/W2982316857","https://openalex.org/W3034440351","https://openalex.org/W3080884797","https://openalex.org/W3104164965","https://openalex.org/W3120106246","https://openalex.org/W3130292943","https://openalex.org/W3160923286","https://openalex.org/W3202717607","https://openalex.org/W3203076355","https://openalex.org/W4200241545","https://openalex.org/W4200456370","https://openalex.org/W4288359387","https://openalex.org/W4297797010","https://openalex.org/W4300311901","https://openalex.org/W4300892457","https://openalex.org/W4310336120","https://openalex.org/W4312084001","https://openalex.org/W4321611535","https://openalex.org/W4385666058","https://openalex.org/W4385737557","https://openalex.org/W4386352016","https://openalex.org/W4387018580","https://openalex.org/W4387407043","https://openalex.org/W4387571371","https://openalex.org/W4387703136"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W3046775127","https://openalex.org/W3107602296","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-02-06T02:01:19.302388","created_date":"2025-10-10T00:00:00"}