{"id":"https://openalex.org/W4403374298","doi":"https://doi.org/10.1007/s13042-024-02399-7","title":"Off-policy asymptotic and adaptive maximum entropy deep reinforcement learning","display_name":"Off-policy asymptotic and adaptive maximum entropy deep reinforcement learning","publication_year":2024,"publication_date":"2024-10-13","ids":{"openalex":"https://openalex.org/W4403374298","doi":"https://doi.org/10.1007/s13042-024-02399-7"},"language":"en","primary_location":{"id":"doi:10.1007/s13042-024-02399-7","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s13042-024-02399-7","pdf_url":null,"source":{"id":"https://openalex.org/S2764999920","display_name":"International Journal of Machine Learning and Cybernetics","issn_l":"1868-8071","issn":["1868-8071","1868-808X"],"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":"International Journal of Machine Learning and Cybernetics","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/A5100651510","display_name":"Huihui Zhang","orcid":"https://orcid.org/0000-0002-5206-1871"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Huihui Zhang","raw_affiliation_strings":["Electrical Engineering, Tsinghua University, Beijing, China","Research Department, Dongsheng (Suzhou) intelligent technology Co., LTD, Suzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Electrical Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Research Department, Dongsheng (Suzhou) intelligent technology Co., LTD, Suzhou, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063337671","display_name":"Xu Han","orcid":"https://orcid.org/0000-0001-8723-7040"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu Han","raw_affiliation_strings":["Research Department, Dongsheng (Suzhou) intelligent technology Co., LTD, Suzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research Department, Dongsheng (Suzhou) intelligent technology Co., LTD, Suzhou, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5100651510"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":{"value":3590,"currency":"USD","value_usd":3590},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1289765,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"16","issue":"4","first_page":"2417","last_page":"2429"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9937000274658203,"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.9713000059127808,"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":0.819856584072113},{"id":"https://openalex.org/keywords/computational-intelligence","display_name":"Computational intelligence","score":0.7232850193977356},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.48943033814430237},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.47072210907936096},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4685215651988983},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.46412017941474915},{"id":"https://openalex.org/keywords/principle-of-maximum-entropy","display_name":"Principle of maximum entropy","score":0.4137353003025055},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.364886075258255},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.16950398683547974},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.11874598264694214},{"id":"https://openalex.org/keywords/thermodynamics","display_name":"Thermodynamics","score":0.05957487225532532}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.819856584072113},{"id":"https://openalex.org/C139502532","wikidata":"https://www.wikidata.org/wiki/Q1122090","display_name":"Computational intelligence","level":2,"score":0.7232850193977356},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.48943033814430237},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.47072210907936096},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4685215651988983},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.46412017941474915},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.4137353003025055},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.364886075258255},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.16950398683547974},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.11874598264694214},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.05957487225532532},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s13042-024-02399-7","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s13042-024-02399-7","pdf_url":null,"source":{"id":"https://openalex.org/S2764999920","display_name":"International Journal of Machine Learning and Cybernetics","issn_l":"1868-8071","issn":["1868-8071","1868-808X"],"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":"International Journal of Machine Learning and Cybernetics","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":20,"referenced_works":["https://openalex.org/W1981276685","https://openalex.org/W1994616650","https://openalex.org/W2131600418","https://openalex.org/W2145339207","https://openalex.org/W2158782408","https://openalex.org/W3015082424","https://openalex.org/W3114647763","https://openalex.org/W4382202881","https://openalex.org/W4385764347","https://openalex.org/W6600007727","https://openalex.org/W6600339963","https://openalex.org/W6600728650","https://openalex.org/W6600734602","https://openalex.org/W6600741150","https://openalex.org/W6601211009","https://openalex.org/W6601548533","https://openalex.org/W6603350349","https://openalex.org/W6606918360","https://openalex.org/W6607352852","https://openalex.org/W6814003322"],"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/W3041490575","https://openalex.org/W2970690932","https://openalex.org/W2110715801"],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}