{"id":"https://openalex.org/W4407264310","doi":"https://doi.org/10.1016/j.neunet.2025.107245","title":"Incremental model-based reinforcement learning with model constraint","display_name":"Incremental model-based reinforcement learning with model constraint","publication_year":2025,"publication_date":"2025-02-08","ids":{"openalex":"https://openalex.org/W4407264310","doi":"https://doi.org/10.1016/j.neunet.2025.107245","pmid":"https://pubmed.ncbi.nlm.nih.gov/39933321"},"language":"en","primary_location":{"id":"doi:10.1016/j.neunet.2025.107245","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.neunet.2025.107245","pdf_url":null,"source":{"id":"https://openalex.org/S123019304","display_name":"Neural Networks","issn_l":"0893-6080","issn":["0893-6080","1879-2782"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Networks","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1016/j.neunet.2025.107245","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101737483","display_name":"Zhiyou Yang","orcid":"https://orcid.org/0000-0001-8955-5835"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiyou Yang","raw_affiliation_strings":["School of Computer Science and Engineering, University of Electronic Science and Technology of China, No. 2006 Xiyuan Ave, Chengdu, 611731, Sichuan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, No. 2006 Xiyuan Ave, Chengdu, 611731, Sichuan, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002397214","display_name":"Mingsheng Fu","orcid":"https://orcid.org/0000-0002-9257-126X"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingsheng Fu","raw_affiliation_strings":["School of Computer Science and Engineering, University of Electronic Science and Technology of China, No. 2006 Xiyuan Ave, Chengdu, 611731, Sichuan, China"],"raw_orcid":"https://orcid.org/0000-0002-9257-126X","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, No. 2006 Xiyuan Ave, Chengdu, 611731, Sichuan, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021975286","display_name":"Hong Qu","orcid":"https://orcid.org/0000-0001-6114-3441"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hong Qu","raw_affiliation_strings":["School of Computer Science and Engineering, University of Electronic Science and Technology of China, No. 2006 Xiyuan Ave, Chengdu, 611731, Sichuan, China. Electronic address: hongqu@uestc.edu.cn"],"raw_orcid":"https://orcid.org/0000-0001-6114-3441","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, No. 2006 Xiyuan Ave, Chengdu, 611731, Sichuan, China. Electronic address: hongqu@uestc.edu.cn","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100373581","display_name":"Fan Li","orcid":"https://orcid.org/0000-0002-8195-7853"},"institutions":[{"id":"https://openalex.org/I24185976","display_name":"Sichuan University","ror":"https://ror.org/011ashp19","country_code":"CN","type":"education","lineage":["https://openalex.org/I24185976"]},{"id":"https://openalex.org/I4210089228","display_name":"West China Second University Hospital of Sichuan University","ror":"https://ror.org/00726et14","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210089228"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fan Li","raw_affiliation_strings":["Section of Epidemiology and Population Health, Department of Obstetrics and Gynecology, West China Second University Hospital, Sichuan University, No. 37 Guoxue Alley, Wuhou District, Chengdu, 610041, Sichuan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Section of Epidemiology and Population Health, Department of Obstetrics and Gynecology, West China Second University Hospital, Sichuan University, No. 37 Guoxue Alley, Wuhou District, Chengdu, 610041, Sichuan, China","institution_ids":["https://openalex.org/I24185976","https://openalex.org/I4210089228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113523238","display_name":"Shuqing Shi","orcid":null},"institutions":[{"id":"https://openalex.org/I183935753","display_name":"King's College London","ror":"https://ror.org/0220mzb33","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I183935753"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Shuqing Shi","raw_affiliation_strings":["King's College London, Bush House North East Wing, 30 Aldwych, WC2B 4BG, London, WC2R 2LS, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"King's College London, Bush House North East Wing, 30 Aldwych, WC2B 4BG, London, WC2R 2LS, United Kingdom","institution_ids":["https://openalex.org/I183935753"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100401021","display_name":"Wang Hu","orcid":"https://orcid.org/0000-0002-5319-7463"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang Hu","raw_affiliation_strings":["School of Computer Science and Engineering, University of Electronic Science and Technology of China, No. 2006 Xiyuan Ave, Chengdu, 611731, Sichuan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, No. 2006 Xiyuan Ave, Chengdu, 611731, Sichuan, China","institution_ids":["https://openalex.org/I150229711"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5021975286"],"corresponding_institution_ids":["https://openalex.org/I150229711"],"apc_list":{"value":3350,"currency":"USD","value_usd":3350},"apc_paid":{"value":3350,"currency":"USD","value_usd":3350},"fwci":7.1482,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.9634223,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"185","issue":null,"first_page":"107245","last_page":"107245"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9940999746322632,"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":0.9937999844551086,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7321865558624268},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6749798655509949},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6121559143066406},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.5284611582756042},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4764942526817322},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17842736840248108}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7321865558624268},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6749798655509949},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6121559143066406},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.5284611582756042},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4764942526817322},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17842736840248108},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007858","descriptor_name":"Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D007858","descriptor_name":"Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012054","descriptor_name":"Reinforcement, Psychology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012054","descriptor_name":"Reinforcement, Psychology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012054","descriptor_name":"Reinforcement, Psychology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012054","descriptor_name":"Reinforcement, Psychology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.1016/j.neunet.2025.107245","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.neunet.2025.107245","pdf_url":null,"source":{"id":"https://openalex.org/S123019304","display_name":"Neural Networks","issn_l":"0893-6080","issn":["0893-6080","1879-2782"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Networks","raw_type":"journal-article"},{"id":"pmid:39933321","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/39933321","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":"Neural networks : the official journal of the International Neural Network Society","raw_type":null}],"best_oa_location":{"id":"doi:10.1016/j.neunet.2025.107245","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.neunet.2025.107245","pdf_url":null,"source":{"id":"https://openalex.org/S123019304","display_name":"Neural Networks","issn_l":"0893-6080","issn":["0893-6080","1879-2782"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Networks","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8323016548","display_name":null,"funder_award_id":"62236007","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":67,"referenced_works":["https://openalex.org/W1549664537","https://openalex.org/W1626155273","https://openalex.org/W1980035368","https://openalex.org/W2064778949","https://openalex.org/W2145339207","https://openalex.org/W2155027007","https://openalex.org/W2749928749","https://openalex.org/W2859967432","https://openalex.org/W2950624398","https://openalex.org/W2953708620","https://openalex.org/W2963238274","https://openalex.org/W2990138404","https://openalex.org/W3142041998","https://openalex.org/W3164559980","https://openalex.org/W3164846705","https://openalex.org/W3194166078","https://openalex.org/W3194194466","https://openalex.org/W3196740181","https://openalex.org/W3202512200","https://openalex.org/W3212671125","https://openalex.org/W4214717370","https://openalex.org/W4220774516","https://openalex.org/W4239752198","https://openalex.org/W4294555834","https://openalex.org/W4298206671","https://openalex.org/W4307772200","https://openalex.org/W4313400414","https://openalex.org/W4313478562","https://openalex.org/W4319335480","https://openalex.org/W4320342971","https://openalex.org/W4327571609","https://openalex.org/W4365806381","https://openalex.org/W4376571587","https://openalex.org/W4386605775","https://openalex.org/W4388948923","https://openalex.org/W4396920632","https://openalex.org/W4399198430","https://openalex.org/W4400518895","https://openalex.org/W6629406372","https://openalex.org/W6638018090","https://openalex.org/W6640314373","https://openalex.org/W6674884181","https://openalex.org/W6679257226","https://openalex.org/W6683153233","https://openalex.org/W6683204974","https://openalex.org/W6684921986","https://openalex.org/W6730042731","https://openalex.org/W6737893269","https://openalex.org/W6738483526","https://openalex.org/W6742380005","https://openalex.org/W6743802245","https://openalex.org/W6746581380","https://openalex.org/W6747473740","https://openalex.org/W6748490488","https://openalex.org/W6751087324","https://openalex.org/W6751494529","https://openalex.org/W6756303580","https://openalex.org/W6759204722","https://openalex.org/W6760405395","https://openalex.org/W6783909840","https://openalex.org/W6790514708","https://openalex.org/W6791603559","https://openalex.org/W6800336768","https://openalex.org/W6801971982","https://openalex.org/W6803529815","https://openalex.org/W6846235960","https://openalex.org/W6846802818"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W4387369504","https://openalex.org/W3046775127","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W3107602296","https://openalex.org/W4364306694","https://openalex.org/W4312192474"],"abstract_inverted_index":{"In":[0,43],"model-based":[1,32,46,77,88,127,154,164,198],"reinforcement":[2],"learning":[3,183],"(RL)":[4],"approaches,":[5],"the":[6,27,60,66,83,103,116,125,132,136,147,152,182],"estimated":[7,40,104,137],"model":[8,41,96],"of":[9,87,203],"a":[10,25,121,160],"real":[11,133,148],"environment":[12,134],"is":[13,34],"learned":[14],"with":[15],"limited":[16],"data":[17],"and":[18,39,106,135,162,206],"then":[19],"utilized":[20],"for":[21],"policy":[22,28,38,52,55,84,109,143],"optimization.":[23],"As":[24],"result,":[26],"optimization":[29,85],"process":[30],"in":[31,146,201],"RL":[33,47,78,128,155,165,199],"influenced":[35],"by":[36,81],"both":[37,93],"updates.":[42],"practice,":[44],"previous":[45,176,196],"methods":[48,200],"only":[49],"perform":[50],"incremental":[51,62,76,95,100,108,113,126,153],"constraint":[53,97,110],"to":[54,102,115,178],"updates,":[56,63],"which":[57,139,174],"cannot":[58],"assure":[59,141],"complete":[61],"thereby":[64],"limiting":[65],"algorithm's":[67],"performance.":[68],"To":[69,150],"address":[70],"this":[71],"issue,":[72],"we":[73,119,158],"propose":[74],"an":[75,94,107],"update":[79,129,156],"scheme":[80,91,130],"analyzing":[82],"procedure":[86],"RL.":[89],"This":[90],"includes":[92],"that":[98,111,192],"guarantees":[99],"updates":[101,114],"model,":[105,138],"ensures":[112],"policy.":[117],"Further,":[118],"establish":[120],"performance":[122,144,205],"bound":[123],"incorporating":[124],"between":[131],"can":[140],"non-decreasing":[142],"improvement":[145],"environment.":[149],"implement":[151],"scheme,":[157],"develop":[159],"simple":[161],"efficient":[163],"algorithm":[166],"known":[167],"as":[168],"IMPO":[169,193],"(Incremental":[170],"Model-based":[171],"Policy":[172],"Optimization),":[173],"leverages":[175],"knowledge":[177],"enhance":[179],"stability":[180],"during":[181],"process.":[184],"Experimental":[185],"results":[186],"across":[187],"various":[188],"control":[189],"benchmarks":[190],"demonstrate":[191],"significantly":[194],"outperforms":[195],"state-of-the-art":[197],"terms":[202],"overall":[204],"sample":[207],"efficiency.":[208]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4}],"updated_date":"2026-08-09T07:27:16.801131","created_date":"2025-10-10T00:00:00"}