{"id":"https://openalex.org/W4404481983","doi":"https://doi.org/10.3390/math12223603","title":"Off-Policy Temporal Difference Learning with Bellman Residuals","display_name":"Off-Policy Temporal Difference Learning with Bellman Residuals","publication_year":2024,"publication_date":"2024-11-18","ids":{"openalex":"https://openalex.org/W4404481983","doi":"https://doi.org/10.3390/math12223603"},"language":"en","primary_location":{"id":"doi:10.3390/math12223603","doi":"https://doi.org/10.3390/math12223603","is_oa":true,"landing_page_url":"https://doi.org/10.3390/math12223603","pdf_url":"https://www.mdpi.com/2227-7390/12/22/3603/pdf?version=1731924930","source":{"id":"https://openalex.org/S4210192031","display_name":"Mathematics","issn_l":"2227-7390","issn":["2227-7390"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-scientific","cwts-core","doaj","poland-20","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Mathematics","raw_type":"journal-article"},"volume":null,"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2227-7390/12/22/3603/pdf?version=1731924930","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100764370","display_name":"Shangdong Yang","orcid":"https://orcid.org/0000-0001-5379-9539","observed_orcids":["https://orcid.org/0000-0001-5379-9539"]},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shangdong Yang","raw_affiliation_strings":["School of Computer Science, Nanjing University of Posts and Telecommunications, Nanjing 210023, China"],"raw_orcid":"https://orcid.org/0000-0001-5379-9539","affiliations":[{"raw_affiliation_string":"School of Computer Science, Nanjing University of Posts and Telecommunications, Nanjing 210023, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088206029","display_name":"Dingyuanhao Sun","orcid":"https://orcid.org/0009-0005-0023-619X","observed_orcids":["https://orcid.org/0009-0005-0023-619X"]},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dingyuanhao Sun","raw_affiliation_strings":["School of Computer Science, Nanjing University of Posts and Telecommunications, Nanjing 210023, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Nanjing University of Posts and Telecommunications, Nanjing 210023, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087374601","display_name":"Xingguo Chen","orcid":"https://orcid.org/0000-0002-8757-1767","observed_orcids":["https://orcid.org/0000-0002-8757-1767"]},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xingguo Chen","raw_affiliation_strings":["School of Computer Science, Nanjing University of Posts and Telecommunications, Nanjing 210023, China"],"raw_orcid":"https://orcid.org/0000-0002-8757-1767","affiliations":[{"raw_affiliation_string":"School of Computer Science, Nanjing University of Posts and Telecommunications, Nanjing 210023, China","institution_ids":["https://openalex.org/I41198531"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5087374601"],"corresponding_institution_ids":["https://openalex.org/I41198531"],"apc_list":{"value":2600,"currency":"CHF","value_usd":2955},"apc_paid":{"value":2600,"currency":"CHF","value_usd":2955},"fwci":0.1481,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.49409237,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"12","issue":"22","first_page":"3603","last_page":"3603"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":1.0,"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":1.0,"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":0.0,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.0,"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/off-policy-learning","display_name":"off-policy learning","score":0.8519999980926514},{"id":"https://openalex.org/keywords/value-function-approximation","display_name":"value function approximation","score":0.8550000190734863},{"id":"https://openalex.org/keywords/convergence-stability","display_name":"convergence stability","score":0.6650000214576721},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"temporal difference learning","score":0.6000000238418579}],"concepts":[{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.7411900758743286},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.34686315059661865},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.3420785665512085},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.326516330242157},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.2750030755996704},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.24092701077461243}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3390/math12223603","doi":"https://doi.org/10.3390/math12223603","is_oa":true,"landing_page_url":"https://doi.org/10.3390/math12223603","pdf_url":"https://www.mdpi.com/2227-7390/12/22/3603/pdf?version=1731924930","source":{"id":"https://openalex.org/S4210192031","display_name":"Mathematics","issn_l":"2227-7390","issn":["2227-7390"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-scientific","cwts-core","doaj","poland-20","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Mathematics","raw_type":"journal-article"},{"id":"pmh:oai:RePEc:gam:jmathe:v:12:y:2024:i:22:p:3603-:d:1523394","doi":null,"is_oa":false,"landing_page_url":"https://www.mdpi.com/2227-7390/12/22/3603/","pdf_url":null,"source":{"id":"https://openalex.org/S4306401271","display_name":"RePEc: Research Papers in Economics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I77793887","host_organization_name":"Federal Reserve Bank of St. Louis","host_organization_lineage":["https://openalex.org/I77793887"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},{"id":"pmh:oai:doaj.org/article:7bc1dba110154c2db1ac64f9ee67dbd9","doi":null,"is_oa":false,"landing_page_url":"https://doaj.org/article/7bc1dba110154c2db1ac64f9ee67dbd9","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Mathematics, Vol 12, Iss 22, p 3603 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/math12223603","doi":"https://doi.org/10.3390/math12223603","is_oa":true,"landing_page_url":"https://doi.org/10.3390/math12223603","pdf_url":"https://www.mdpi.com/2227-7390/12/22/3603/pdf?version=1731924930","source":{"id":"https://openalex.org/S4210192031","display_name":"Mathematics","issn_l":"2227-7390","issn":["2227-7390"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-scientific","cwts-core","doaj","poland-20","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Mathematics","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G669068149","display_name":null,"funder_award_id":"62276142","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7334411499","display_name":null,"funder_award_id":"62206133","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":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4404481983.pdf","grobid_xml":"https://content.openalex.org/works/W4404481983.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1600046456","https://openalex.org/W1646707810","https://openalex.org/W2065134213","https://openalex.org/W2071983464","https://openalex.org/W2075268401","https://openalex.org/W2094364653","https://openalex.org/W2100677568","https://openalex.org/W2108596215","https://openalex.org/W2121832485","https://openalex.org/W2131600418","https://openalex.org/W2145339207","https://openalex.org/W2155027007","https://openalex.org/W2781726626","https://openalex.org/W2898016531","https://openalex.org/W2952014622","https://openalex.org/W3035547404","https://openalex.org/W3046190872","https://openalex.org/W4214717370","https://openalex.org/W4225623389","https://openalex.org/W4362587465","https://openalex.org/W4382203490","https://openalex.org/W4385988208"],"related_works":["https://openalex.org/W2988737553","https://openalex.org/W2609125576","https://openalex.org/W7148729830","https://openalex.org/W4321471531","https://openalex.org/W2899652047","https://openalex.org/W4404863462","https://openalex.org/W7124138453","https://openalex.org/W2406456910","https://openalex.org/W4402677598","https://openalex.org/W2151613683"],"abstract_inverted_index":{"In":[0],"reinforcement":[1,79,145],"learning,":[2],"off-policy":[3,22,45,68,92,144],"temporal":[4,23,46],"difference":[5,24,47],"learning":[6,69,80,146],"methods":[7,25,123],"have":[8],"gained":[9],"significant":[10],"attention":[11],"due":[12],"to":[13,163,169],"their":[14],"flexibility":[15],"in":[16,91,107,111,124,175],"utilizing":[17],"existing":[18],"data.":[19],"However,":[20],"traditional":[21,122],"often":[26],"suffer":[27],"from":[28],"poor":[29],"convergence":[30,63,128],"and":[31,64,81,98,130,140,159,166,173],"stability":[32,65],"when":[33],"handling":[34],"complex":[35],"problems.":[36,177],"To":[37],"address":[38],"these":[39],"issues,":[40],"this":[41],"paper":[42,72],"proposes":[43],"an":[44,138],"algorithm":[48,59,104,119,136,157],"with":[49,147],"Bellman":[50,55,89],"residuals":[51,90],"(TDBR).":[52],"By":[53],"incorporating":[54],"residuals,":[56],"the":[57,62,67,75,86,95,102,117,134,156],"proposed":[58],"effectively":[60],"improves":[61],"of":[66,78,88,101,126],"process.":[70],"This":[71],"first":[73],"introduces":[74],"basic":[76],"concepts":[77],"value":[82],"function":[83],"approximation,":[84],"highlighting":[85],"importance":[87],"learning.":[93],"Then,":[94],"theoretical":[96],"foundation":[97],"implementation":[99],"details":[100],"TDBR":[103,118,135],"are":[105],"described":[106],"detail.":[108],"Experimental":[109],"results":[110],"multiple":[112],"benchmark":[113],"environments":[114],"demonstrate":[115],"that":[116],"significantly":[120],"outperforms":[121],"terms":[125],"both":[127],"speed":[129],"solution":[131,142],"quality.":[132],"Overall,":[133],"provides":[137],"effective":[139],"stable":[141],"for":[143],"broad":[148],"application":[149,162],"prospects.":[150],"Future":[151],"research":[152],"can":[153],"further":[154],"optimize":[155],"parameters":[158],"extend":[160],"its":[161,171],"continuous":[164],"state":[165],"action":[167],"spaces":[168],"enhance":[170],"applicability":[172],"performance":[174],"real-world":[176]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2024-11-19T00:00:00"}