{"id":"https://openalex.org/W4413855480","doi":"https://doi.org/10.1007/s13042-025-02780-0","title":"Diffusion policy with Q-ensemble for offline reinforcement learning","display_name":"Diffusion policy with Q-ensemble for offline reinforcement learning","publication_year":2025,"publication_date":"2025-08-31","ids":{"openalex":"https://openalex.org/W4413855480","doi":"https://doi.org/10.1007/s13042-025-02780-0"},"language":"en","primary_location":{"id":"doi:10.1007/s13042-025-02780-0","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s13042-025-02780-0","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/A5100391422","display_name":"Dong Wang","orcid":"https://orcid.org/0000-0001-7877-7440"},"institutions":[{"id":"https://openalex.org/I43337087","display_name":"Hebei University","ror":"https://ror.org/01p884a79","country_code":"CN","type":"education","lineage":["https://openalex.org/I43337087"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Dong Wang","raw_affiliation_strings":["Hebei Key Laboratory of Machine Learning and Computational Intelligence, Baoding, People\u2019s Republic of China","Hebei University, Baoding, 071000, Hebei, People\u2019s Republic of China"],"affiliations":[{"raw_affiliation_string":"Hebei Key Laboratory of Machine Learning and Computational Intelligence, Baoding, People\u2019s Republic of China","institution_ids":["https://openalex.org/I43337087"]},{"raw_affiliation_string":"Hebei University, Baoding, 071000, Hebei, People\u2019s Republic of China","institution_ids":["https://openalex.org/I43337087"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100437210","display_name":"Xu Zhang","orcid":"https://orcid.org/0000-0002-1944-6630"},"institutions":[{"id":"https://openalex.org/I43337087","display_name":"Hebei University","ror":"https://ror.org/01p884a79","country_code":"CN","type":"education","lineage":["https://openalex.org/I43337087"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu Zhang","raw_affiliation_strings":["Hebei Key Laboratory of Machine Learning and Computational Intelligence, Baoding, People\u2019s Republic of China","Hebei University, Baoding, 071000, Hebei, People\u2019s Republic of China"],"affiliations":[{"raw_affiliation_string":"Hebei Key Laboratory of Machine Learning and Computational Intelligence, Baoding, People\u2019s Republic of China","institution_ids":["https://openalex.org/I43337087"]},{"raw_affiliation_string":"Hebei University, Baoding, 071000, Hebei, People\u2019s Republic of China","institution_ids":["https://openalex.org/I43337087"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064830115","display_name":"Qiang Hua","orcid":"https://orcid.org/0000-0001-9017-0043"},"institutions":[{"id":"https://openalex.org/I43337087","display_name":"Hebei University","ror":"https://ror.org/01p884a79","country_code":"CN","type":"education","lineage":["https://openalex.org/I43337087"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiang Hua","raw_affiliation_strings":["Hebei Key Laboratory of Machine Learning and Computational Intelligence, Baoding, People\u2019s Republic of China","Hebei University, Baoding, 071000, Hebei, People\u2019s Republic of China"],"affiliations":[{"raw_affiliation_string":"Hebei Key Laboratory of Machine Learning and Computational Intelligence, Baoding, People\u2019s Republic of China","institution_ids":["https://openalex.org/I43337087"]},{"raw_affiliation_string":"Hebei University, Baoding, 071000, Hebei, People\u2019s Republic of China","institution_ids":["https://openalex.org/I43337087"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018560081","display_name":"Chun-Ru Dong","orcid":"https://orcid.org/0000-0003-1726-5534"},"institutions":[{"id":"https://openalex.org/I43337087","display_name":"Hebei University","ror":"https://ror.org/01p884a79","country_code":"CN","type":"education","lineage":["https://openalex.org/I43337087"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunru Dong","raw_affiliation_strings":["Hebei Key Laboratory of Machine Learning and Computational Intelligence, Baoding, People\u2019s Republic of China","Hebei University, Baoding, 071000, Hebei, People\u2019s Republic of China"],"affiliations":[{"raw_affiliation_string":"Hebei Key Laboratory of Machine Learning and Computational Intelligence, Baoding, People\u2019s Republic of China","institution_ids":["https://openalex.org/I43337087"]},{"raw_affiliation_string":"Hebei University, Baoding, 071000, Hebei, People\u2019s Republic of China","institution_ids":["https://openalex.org/I43337087"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100401204","display_name":"Feng Zhang","orcid":"https://orcid.org/0000-0001-7178-0735"},"institutions":[{"id":"https://openalex.org/I43337087","display_name":"Hebei University","ror":"https://ror.org/01p884a79","country_code":"CN","type":"education","lineage":["https://openalex.org/I43337087"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Zhang","raw_affiliation_strings":["Hebei Key Laboratory of Machine Learning and Computational Intelligence, Baoding, People\u2019s Republic of China","Hebei University, Baoding, 071000, Hebei, People\u2019s Republic of China"],"affiliations":[{"raw_affiliation_string":"Hebei Key Laboratory of Machine Learning and Computational Intelligence, Baoding, People\u2019s Republic of China","institution_ids":["https://openalex.org/I43337087"]},{"raw_affiliation_string":"Hebei University, Baoding, 071000, Hebei, People\u2019s Republic of China","institution_ids":["https://openalex.org/I43337087"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100391422"],"corresponding_institution_ids":["https://openalex.org/I43337087"],"apc_list":{"value":2790,"currency":"EUR","value_usd":3590},"apc_paid":null,"fwci":2.6995,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.91912049,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"16","issue":"11","first_page":"9717","last_page":"9729"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9987999796867371,"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":0.9987999796867371,"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":0.9900000095367432,"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":0.9789000153541565,"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/computational-intelligence","display_name":"Computational intelligence","score":0.7214711308479309},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.713947594165802},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5896568298339844},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.5244220495223999},{"id":"https://openalex.org/keywords/ensemble-learning","display_name":"Ensemble learning","score":0.5140258073806763},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48387205600738525},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.40818944573402405},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.15523061156272888},{"id":"https://openalex.org/keywords/thermodynamics","display_name":"Thermodynamics","score":0.06976661086082458}],"concepts":[{"id":"https://openalex.org/C139502532","wikidata":"https://www.wikidata.org/wiki/Q1122090","display_name":"Computational intelligence","level":2,"score":0.7214711308479309},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.713947594165802},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5896568298339844},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.5244220495223999},{"id":"https://openalex.org/C45942800","wikidata":"https://www.wikidata.org/wiki/Q245652","display_name":"Ensemble learning","level":2,"score":0.5140258073806763},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48387205600738525},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40818944573402405},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.15523061156272888},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.06976661086082458}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s13042-025-02780-0","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s13042-025-02780-0","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W2145339207","https://openalex.org/W2225156818","https://openalex.org/W2746553466","https://openalex.org/W4360884927","https://openalex.org/W4385403849","https://openalex.org/W4387806972","https://openalex.org/W4388033982","https://openalex.org/W4390872297","https://openalex.org/W4401417422","https://openalex.org/W4403337227"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W4376643315","https://openalex.org/W4324137541","https://openalex.org/W2900445707","https://openalex.org/W4285741730","https://openalex.org/W1191482210","https://openalex.org/W4285046548"],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-08T23:21:52.890332","created_date":"2025-10-10T00:00:00"}
