{"id":"https://openalex.org/W4403863643","doi":"https://doi.org/10.1109/tnnls.2024.3481887","title":"Historical Decision-Making Regularized Maximum Entropy Reinforcement Learning","display_name":"Historical Decision-Making Regularized Maximum Entropy Reinforcement Learning","publication_year":2024,"publication_date":"2024-10-29","ids":{"openalex":"https://openalex.org/W4403863643","doi":"https://doi.org/10.1109/tnnls.2024.3481887","pmid":"https://pubmed.ncbi.nlm.nih.gov/39471125"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2024.3481887","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2024.3481887","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5002412202","display_name":"Botao Dong","orcid":"https://orcid.org/0000-0002-2026-6856"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Botao Dong","raw_affiliation_strings":["Department of Automation, Shanghai Jiao Tong University, Shanghai, China","Department of Automation, Shanghai Jiao Tong University, Shang-hai, China"],"raw_orcid":"https://orcid.org/0000-0002-2026-6856","affiliations":[{"raw_affiliation_string":"Department of Automation, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Automation, Shanghai Jiao Tong University, Shang-hai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085372626","display_name":"Longyang Huang","orcid":"https://orcid.org/0000-0001-5123-5043"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Longyang Huang","raw_affiliation_strings":["Department of Automation, Shanghai Jiao Tong University, Shanghai, China","Department of Automation, Shanghai Jiao Tong University, Shang-hai, China"],"raw_orcid":"https://orcid.org/0000-0001-5123-5043","affiliations":[{"raw_affiliation_string":"Department of Automation, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Automation, Shanghai Jiao Tong University, Shang-hai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ning Pang","orcid":"https://orcid.org/0000-0003-4322-4314"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ning Pang","raw_affiliation_strings":["Department of Automation, Shanghai Jiao Tong University, Shanghai, China","Department of Automation, Shanghai Jiao Tong University, Shang-hai, China"],"raw_orcid":"https://orcid.org/0000-0003-4322-4314","affiliations":[{"raw_affiliation_string":"Department of Automation, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Automation, Shanghai Jiao Tong University, Shang-hai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019419996","display_name":"Hongtian Chen","orcid":"https://orcid.org/0000-0002-8600-9668"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongtian Chen","raw_affiliation_strings":["Department of Automation, Shanghai Jiao Tong University, Shanghai, China","Department of Automation, Shanghai Jiao Tong University, Shang-hai, China"],"raw_orcid":"https://orcid.org/0000-0002-8600-9668","affiliations":[{"raw_affiliation_string":"Department of Automation, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Department of Automation, Shanghai Jiao Tong University, Shang-hai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100414775","display_name":"Weidong Zhang","orcid":"https://orcid.org/0000-0002-4700-1276"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weidong Zhang","raw_affiliation_strings":["Department of Automation, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-4700-1276","affiliations":[{"raw_affiliation_string":"Department of Automation, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":1.1114,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.81786825,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"36","issue":"7","first_page":"13446","last_page":"13459"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.8651999831199646,"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/T10320","display_name":"Neural Networks and Applications","score":0.8651999831199646,"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":0.7240278720855713},{"id":"https://openalex.org/keywords/principle-of-maximum-entropy","display_name":"Principle of maximum entropy","score":0.7037133574485779},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46576547622680664},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.44078049063682556},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.43989092111587524},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3578120470046997},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.33366137742996216},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.17603188753128052},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.08548721671104431}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7240278720855713},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.7037133574485779},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46576547622680664},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.44078049063682556},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.43989092111587524},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3578120470046997},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.33366137742996216},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.17603188753128052},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.08548721671104431}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2024.3481887","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2024.3481887","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:39471125","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/39471125","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on neural networks and learning systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.699999988079071,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G3947000257","display_name":null,"funder_award_id":"2022ZD0119903","funder_id":"https://openalex.org/F4320329860","funder_display_name":"National Science and Technology Major Project"},{"id":"https://openalex.org/G5721963804","display_name":null,"funder_award_id":"U2141234","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7941178911","display_name":null,"funder_award_id":"62303308","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"},{"id":"https://openalex.org/F4320329860","display_name":"National Science and Technology Major Project","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W2144744117","https://openalex.org/W2158782408","https://openalex.org/W2965140792","https://openalex.org/W3047221759","https://openalex.org/W3118881636","https://openalex.org/W3135203571","https://openalex.org/W3170872007","https://openalex.org/W3200066794","https://openalex.org/W3210013777","https://openalex.org/W4220747123","https://openalex.org/W4220774516","https://openalex.org/W4223992650","https://openalex.org/W4226257065","https://openalex.org/W4285076891","https://openalex.org/W4285110581","https://openalex.org/W4294982764","https://openalex.org/W4295308578","https://openalex.org/W4307230233","https://openalex.org/W4311486598","https://openalex.org/W4319165238","https://openalex.org/W4320015828","https://openalex.org/W4322706623","https://openalex.org/W4375796951","https://openalex.org/W4377298394","https://openalex.org/W4379527413","https://openalex.org/W4382202993","https://openalex.org/W4382239405","https://openalex.org/W4384499218","https://openalex.org/W4385338914","https://openalex.org/W4386883060","https://openalex.org/W4387415195","https://openalex.org/W4388543828","https://openalex.org/W4391305708","https://openalex.org/W4401210763","https://openalex.org/W6638018090","https://openalex.org/W6684921986","https://openalex.org/W6741002519","https://openalex.org/W6747473740","https://openalex.org/W6748839928","https://openalex.org/W6767569084","https://openalex.org/W6770927411","https://openalex.org/W6780559895","https://openalex.org/W6784938585","https://openalex.org/W6791110673","https://openalex.org/W6845850219","https://openalex.org/W6853445487","https://openalex.org/W6864232018","https://openalex.org/W7043747221"],"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":{"The":[0,68,107],"challenge":[1],"of":[2,16,65,75,84,103,109],"the":[3,14,40,48,53,62,73,78,87,90,96,101,104],"exploration-exploitation":[4],"dilemma":[5],"persists":[6],"in":[7],"off-policy":[8],"reinforcement":[9],"learning":[10],"(RL)":[11],"algorithms,":[12],"impeding":[13],"improvement":[15],"policy":[17],"performance":[18,108,137],"and":[19,44,82,95,99,120,133],"sample":[20,131],"efficiency.":[21],"To":[22],"tackle":[23],"this":[24],"challenge,":[25],"a":[26],"novel":[27],"historical":[28,54],"decision-making":[29,55],"regularized":[30],"maximum":[31,49],"entropy":[32,50],"(HDMRME)":[33],"RL":[34,51,66,142],"algorithm":[35],"is":[36,58,111],"developed":[37],"to":[38,60],"strike":[39],"balance":[41],"between":[42,80,89],"exploration":[43,81],"exploitation.":[45],"Built":[46],"upon":[47],"framework,":[52],"regularization":[56],"method":[57],"proposed":[59],"enhance":[61],"exploitation":[63,83],"capability":[64],"policies.":[67],"theoretical":[69],"analysis":[70],"involves":[71],"proving":[72],"convergence":[74],"HDMRME,":[76,85],"investigating":[77],"tradeoff":[79],"examining":[86],"disparity":[88],"Q-function":[91],"learned":[92],"through":[93],"HDMRME":[94,110,128],"classic":[97],"one,":[98],"analyzing":[100],"suboptimality":[102],"trained":[105],"policy.":[106],"evaluated":[112],"across":[113],"various":[114],"continuous-action":[115],"control":[116],"tasks":[117],"from":[118],"Mujoco":[119],"OpenAI":[121],"Gym":[122],"platforms.":[123],"Comparative":[124],"experiments":[125],"demonstrate":[126],"that":[127],"exhibits":[129],"superior":[130],"efficiency":[132],"achieves":[134],"more":[135],"competitive":[136],"compared":[138],"with":[139],"other":[140],"state-of-the-art":[141],"algorithms.":[143]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2}],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}