{"id":"https://openalex.org/W4416335446","doi":"https://doi.org/10.1007/s10489-025-06963-8","title":"Adaptive joint entropy reward: a mechanism to efficient exploration in reinforcement learning","display_name":"Adaptive joint entropy reward: a mechanism to efficient exploration in reinforcement learning","publication_year":2025,"publication_date":"2025-11-01","ids":{"openalex":"https://openalex.org/W4416335446","doi":"https://doi.org/10.1007/s10489-025-06963-8"},"language":"en","primary_location":{"id":"doi:10.1007/s10489-025-06963-8","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s10489-025-06963-8","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/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":true,"raw_author_name":"Chunru Dong","raw_affiliation_strings":["Hebei Key Laboratory of Machine Learning and Computational Intelligence, College of Mathematics and Information Science, Hebei University, Baoding, Hebei Provience, 071002, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hebei Key Laboratory of Machine Learning and Computational Intelligence, College of Mathematics and Information Science, Hebei University, Baoding, Hebei Provience, 071002, China","institution_ids":["https://openalex.org/I43337087"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004682528","display_name":"Yang Wang","orcid":"https://orcid.org/0000-0002-7717-5031"},"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":"Yang Wang","raw_affiliation_strings":["Hebei Key Laboratory of Machine Learning and Computational Intelligence, College of Mathematics and Information Science, Hebei University, Baoding, Hebei Provience, 071002, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hebei Key Laboratory of Machine Learning and Computational Intelligence, College of Mathematics and Information Science, Hebei University, Baoding, Hebei Provience, 071002, China","institution_ids":["https://openalex.org/I43337087"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090039861","display_name":"Aoxiang Wang","orcid":null},"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":"Aoxiang Wang","raw_affiliation_strings":["Hebei Key Laboratory of Machine Learning and Computational Intelligence, College of Mathematics and Information Science, Hebei University, Baoding, Hebei Provience, 071002, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hebei Key Laboratory of Machine Learning and Computational Intelligence, College of Mathematics and Information Science, Hebei University, Baoding, Hebei Provience, 071002, 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, College of Mathematics and Information Science, Hebei University, Baoding, Hebei Provience, 071002, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hebei Key Laboratory of Machine Learning and Computational Intelligence, College of Mathematics and Information Science, Hebei University, Baoding, Hebei Provience, 071002, 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, College of Mathematics and Information Science, Hebei University, Baoding, Hebei Provience, 071002, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hebei Key Laboratory of Machine Learning and Computational Intelligence, College of Mathematics and Information Science, Hebei University, Baoding, Hebei Provience, 071002, China","institution_ids":["https://openalex.org/I43337087"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5018560081"],"corresponding_institution_ids":["https://openalex.org/I43337087"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":null,"fwci":1.8914,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.90167958,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"55","issue":"17","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":0.7372000217437744,"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":0.7372000217437744,"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/T10429","display_name":"EEG and Brain-Computer Interfaces","score":0.022199999541044235,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.018300000578165054,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7681999802589417},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.7087000012397766},{"id":"https://openalex.org/keywords/conditional-entropy","display_name":"Conditional entropy","score":0.36800000071525574},{"id":"https://openalex.org/keywords/joint-entropy","display_name":"Joint entropy","score":0.3529999852180481},{"id":"https://openalex.org/keywords/joint-probability-distribution","display_name":"Joint probability distribution","score":0.34869998693466187},{"id":"https://openalex.org/keywords/suite","display_name":"Suite","score":0.322299987077713},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.3154999911785126}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8188999891281128},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7681999802589417},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.7087000012397766},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5597000122070312},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43950000405311584},{"id":"https://openalex.org/C101721835","wikidata":"https://www.wikidata.org/wiki/Q813908","display_name":"Conditional entropy","level":3,"score":0.36800000071525574},{"id":"https://openalex.org/C106752470","wikidata":"https://www.wikidata.org/wiki/Q1364826","display_name":"Joint entropy","level":3,"score":0.3529999852180481},{"id":"https://openalex.org/C18653775","wikidata":"https://www.wikidata.org/wiki/Q1333358","display_name":"Joint probability distribution","level":2,"score":0.34869998693466187},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.322299987077713},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.3154999911785126},{"id":"https://openalex.org/C171752962","wikidata":"https://www.wikidata.org/wiki/Q255166","display_name":"Kullback\u2013Leibler divergence","level":2,"score":0.29429998993873596},{"id":"https://openalex.org/C124551494","wikidata":"https://www.wikidata.org/wiki/Q3055345","display_name":"Differential entropy","level":4,"score":0.2928999960422516},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.29269999265670776},{"id":"https://openalex.org/C2983203078","wikidata":"https://www.wikidata.org/wiki/Q255166","display_name":"Information gain","level":2,"score":0.29269999265670776},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.2759000062942505},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.27219998836517334},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.26980000734329224},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.250900000333786}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s10489-025-06963-8","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s10489-025-06963-8","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/G178810287","display_name":null,"funder_award_id":"22567623H","funder_id":"https://openalex.org/F4320324965","funder_display_name":"Hebei Provincial Department of Bureau of Science and Technology"},{"id":"https://openalex.org/G7312010516","display_name":null,"funder_award_id":"2022YFE0196100","funder_id":"https://openalex.org/F4320321540","funder_display_name":"Ministry of Science and Technology of the People's Republic of China"},{"id":"https://openalex.org/G7986329312","display_name":null,"funder_award_id":"521000981092","funder_id":"https://openalex.org/F4320324851","funder_display_name":"Hebei University"}],"funders":[{"id":"https://openalex.org/F4320321540","display_name":"Ministry of Science and Technology of the People's Republic of China","ror":"https://ror.org/027s68j25"},{"id":"https://openalex.org/F4320324851","display_name":"Hebei University","ror":"https://ror.org/01p884a79"},{"id":"https://openalex.org/F4320324965","display_name":"Hebei Provincial Department of Bureau of Science and Technology","ror":"https://ror.org/05k812a28"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W2145339207","https://openalex.org/W2257979135","https://openalex.org/W2766447205","https://openalex.org/W2910953461","https://openalex.org/W2997343068","https://openalex.org/W3014101816","https://openalex.org/W3034962946","https://openalex.org/W3036619998","https://openalex.org/W3094387578","https://openalex.org/W3175662487","https://openalex.org/W3196183762","https://openalex.org/W4214717370","https://openalex.org/W4250979948","https://openalex.org/W4285114615","https://openalex.org/W4379087234","https://openalex.org/W4382202993","https://openalex.org/W4382319558","https://openalex.org/W4382334265","https://openalex.org/W4406158006","https://openalex.org/W4409474007"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-05-26T13:28:51.108037","created_date":"2025-11-19T00:00:00"}