{"id":"https://openalex.org/W4416422402","doi":"https://doi.org/10.3390/a18110729","title":"Segmenting Action-Value Functions over Time Scales in SARSA via TD(\u0394)","display_name":"Segmenting Action-Value Functions over Time Scales in SARSA via TD(\u0394)","publication_year":2025,"publication_date":"2025-11-20","ids":{"openalex":"https://openalex.org/W4416422402","doi":"https://doi.org/10.3390/a18110729"},"language":"en","primary_location":{"id":"doi:10.3390/a18110729","is_oa":true,"landing_page_url":"https://doi.org/10.3390/a18110729","pdf_url":"https://www.mdpi.com/1999-4893/18/11/729/pdf","source":{"id":"https://openalex.org/S190629608","display_name":"Algorithms","issn_l":"1999-4893","issn":["1999-4893"],"is_oa":true,"is_in_doaj":true,"is_core":true,"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":"Algorithms","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/1999-4893/18/11/729/pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5066323756","display_name":"Mahammad Humayoo","orcid":"https://orcid.org/0000-0001-6629-8186"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I41147446","display_name":"Anshan Normal University","ror":"https://ror.org/04s5wwh39","country_code":"CN","type":"education","lineage":["https://openalex.org/I41147446"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]},{"id":"https://openalex.org/I4210165736","display_name":"Hanshan Normal University","ror":"https://ror.org/05tqaz865","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210165736"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Mahammad Humayoo","raw_affiliation_strings":["CAS Key Laboratory of Network Data Science & Technology, Institute of Computing Technology, Chinese Academy of Sciences, Beijing 100190, China","Hanshan Normal University, Chaozhou 521041, China","School of Computer Science, Beijing Institute of Technology, Beijing 100081, China","University of Chinese Academy of Sciences, Beijing 101408, China","School of Computer Information Engineering, Hanshan Normal University , Chaozhou 521041, China"],"affiliations":[{"raw_affiliation_string":"CAS Key Laboratory of Network Data Science & Technology, Institute of Computing Technology, Chinese Academy of Sciences, Beijing 100190, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]},{"raw_affiliation_string":"Hanshan Normal University, Chaozhou 521041, China","institution_ids":["https://openalex.org/I4210165736"]},{"raw_affiliation_string":"School of Computer Science, Beijing Institute of Technology, Beijing 100081, China","institution_ids":["https://openalex.org/I125839683"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing 101408, China","institution_ids":["https://openalex.org/I4210165038"]},{"raw_affiliation_string":"School of Computer Information Engineering, Hanshan Normal University , Chaozhou 521041, China","institution_ids":["https://openalex.org/I4210165736","https://openalex.org/I41147446"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101562509","display_name":"Gengzhong Zheng","orcid":"https://orcid.org/0000-0002-5895-0418"},"institutions":[{"id":"https://openalex.org/I41147446","display_name":"Anshan Normal University","ror":"https://ror.org/04s5wwh39","country_code":"CN","type":"education","lineage":["https://openalex.org/I41147446"]},{"id":"https://openalex.org/I4210165736","display_name":"Hanshan Normal University","ror":"https://ror.org/05tqaz865","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210165736"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Gengzhong Zheng","raw_affiliation_strings":["Hanshan Normal University, Chaozhou 521041, China","School of Computer Information Engineering, Hanshan Normal University , Chaozhou 521041, China"],"affiliations":[{"raw_affiliation_string":"Hanshan Normal University, Chaozhou 521041, China","institution_ids":["https://openalex.org/I4210165736"]},{"raw_affiliation_string":"School of Computer Information Engineering, Hanshan Normal University , Chaozhou 521041, China","institution_ids":["https://openalex.org/I4210165736","https://openalex.org/I41147446"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059227106","display_name":"Xiaoqing Dong","orcid":"https://orcid.org/0000-0002-9839-5906"},"institutions":[{"id":"https://openalex.org/I41147446","display_name":"Anshan Normal University","ror":"https://ror.org/04s5wwh39","country_code":"CN","type":"education","lineage":["https://openalex.org/I41147446"]},{"id":"https://openalex.org/I4210165736","display_name":"Hanshan Normal University","ror":"https://ror.org/05tqaz865","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210165736"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiaoqing Dong","raw_affiliation_strings":["Hanshan Normal University, Chaozhou 521041, China","School of Computer Information Engineering, Hanshan Normal University , Chaozhou 521041, China"],"affiliations":[{"raw_affiliation_string":"Hanshan Normal University, Chaozhou 521041, China","institution_ids":["https://openalex.org/I4210165736"]},{"raw_affiliation_string":"School of Computer Information Engineering, Hanshan Normal University , Chaozhou 521041, China","institution_ids":["https://openalex.org/I4210165736","https://openalex.org/I41147446"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006226649","display_name":"Wei Huang","orcid":"https://orcid.org/0000-0002-0095-1354"},"institutions":[{"id":"https://openalex.org/I41147446","display_name":"Anshan Normal University","ror":"https://ror.org/04s5wwh39","country_code":"CN","type":"education","lineage":["https://openalex.org/I41147446"]},{"id":"https://openalex.org/I4210165736","display_name":"Hanshan Normal University","ror":"https://ror.org/05tqaz865","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210165736"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Huang","raw_affiliation_strings":["Hanshan Normal University, Chaozhou 521041, China","School of Computer Information Engineering, Hanshan Normal University , Chaozhou 521041, China"],"affiliations":[{"raw_affiliation_string":"Hanshan Normal University, Chaozhou 521041, China","institution_ids":["https://openalex.org/I4210165736"]},{"raw_affiliation_string":"School of Computer Information Engineering, Hanshan Normal University , Chaozhou 521041, China","institution_ids":["https://openalex.org/I4210165736","https://openalex.org/I41147446"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082340230","display_name":"Liming Miao","orcid":"https://orcid.org/0000-0003-2164-5476"},"institutions":[{"id":"https://openalex.org/I41147446","display_name":"Anshan Normal University","ror":"https://ror.org/04s5wwh39","country_code":"CN","type":"education","lineage":["https://openalex.org/I41147446"]},{"id":"https://openalex.org/I4210165736","display_name":"Hanshan Normal University","ror":"https://ror.org/05tqaz865","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210165736"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liming Miao","raw_affiliation_strings":["Hanshan Normal University, Chaozhou 521041, China","School of Computer Information Engineering, Hanshan Normal University , Chaozhou 521041, China"],"affiliations":[{"raw_affiliation_string":"Hanshan Normal University, Chaozhou 521041, China","institution_ids":["https://openalex.org/I4210165736"]},{"raw_affiliation_string":"School of Computer Information Engineering, Hanshan Normal University , Chaozhou 521041, China","institution_ids":["https://openalex.org/I4210165736","https://openalex.org/I41147446"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101200792","display_name":"Shuwei Qiu","orcid":"https://orcid.org/0000-0002-4387-0503"},"institutions":[{"id":"https://openalex.org/I41147446","display_name":"Anshan Normal University","ror":"https://ror.org/04s5wwh39","country_code":"CN","type":"education","lineage":["https://openalex.org/I41147446"]},{"id":"https://openalex.org/I4210165736","display_name":"Hanshan Normal University","ror":"https://ror.org/05tqaz865","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210165736"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuwei Qiu","raw_affiliation_strings":["Hanshan Normal University, Chaozhou 521041, China","School of Computer Information Engineering, Hanshan Normal University , Chaozhou 521041, China"],"affiliations":[{"raw_affiliation_string":"Hanshan Normal University, Chaozhou 521041, China","institution_ids":["https://openalex.org/I4210165736"]},{"raw_affiliation_string":"School of Computer Information Engineering, Hanshan Normal University , Chaozhou 521041, China","institution_ids":["https://openalex.org/I4210165736","https://openalex.org/I41147446"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029328744","display_name":"Zexun Zhou","orcid":"https://orcid.org/0000-0002-4742-2505"},"institutions":[{"id":"https://openalex.org/I41147446","display_name":"Anshan Normal University","ror":"https://ror.org/04s5wwh39","country_code":"CN","type":"education","lineage":["https://openalex.org/I41147446"]},{"id":"https://openalex.org/I4210165736","display_name":"Hanshan Normal University","ror":"https://ror.org/05tqaz865","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210165736"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zexun Zhou","raw_affiliation_strings":["Hanshan Normal University, Chaozhou 521041, China","School of Computer Information Engineering, Hanshan Normal University , Chaozhou 521041, China"],"affiliations":[{"raw_affiliation_string":"Hanshan Normal University, Chaozhou 521041, China","institution_ids":["https://openalex.org/I4210165736"]},{"raw_affiliation_string":"School of Computer Information Engineering, Hanshan Normal University , Chaozhou 521041, China","institution_ids":["https://openalex.org/I4210165736","https://openalex.org/I41147446"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015738339","display_name":"Peitao Wang","orcid":"https://orcid.org/0000-0002-6188-102X"},"institutions":[{"id":"https://openalex.org/I41147446","display_name":"Anshan Normal University","ror":"https://ror.org/04s5wwh39","country_code":"CN","type":"education","lineage":["https://openalex.org/I41147446"]},{"id":"https://openalex.org/I4210165736","display_name":"Hanshan Normal University","ror":"https://ror.org/05tqaz865","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210165736"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peitao Wang","raw_affiliation_strings":["Hanshan Normal University, Chaozhou 521041, China","School of Computer Information Engineering, Hanshan Normal University , Chaozhou 521041, China"],"affiliations":[{"raw_affiliation_string":"Hanshan Normal University, Chaozhou 521041, China","institution_ids":["https://openalex.org/I4210165736"]},{"raw_affiliation_string":"School of Computer Information Engineering, Hanshan Normal University , Chaozhou 521041, China","institution_ids":["https://openalex.org/I4210165736","https://openalex.org/I41147446"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042577447","display_name":"Zakir Ullah","orcid":"https://orcid.org/0000-0001-8921-6550"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]},{"id":"https://openalex.org/I90259746","display_name":"Capital University of Economics and Business","ror":"https://ror.org/01r5sf951","country_code":"CN","type":"education","lineage":["https://openalex.org/I90259746"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zakir Ullah","raw_affiliation_strings":["School of Data Science, Capital University of Economics and Business, Beijing 100070, China","University of Chinese Academy of Sciences, Beijing 101408, China"],"affiliations":[{"raw_affiliation_string":"School of Data Science, Capital University of Economics and Business, Beijing 100070, China","institution_ids":["https://openalex.org/I90259746"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing 101408, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034238399","display_name":"Naveed Ur Rehman Junejo","orcid":"https://orcid.org/0000-0002-1947-5255"},"institutions":[{"id":"https://openalex.org/I41147446","display_name":"Anshan Normal University","ror":"https://ror.org/04s5wwh39","country_code":"CN","type":"education","lineage":["https://openalex.org/I41147446"]},{"id":"https://openalex.org/I4210165736","display_name":"Hanshan Normal University","ror":"https://ror.org/05tqaz865","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210165736"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Naveed Ur Rehman Junejo","raw_affiliation_strings":["Hanshan Normal University, Chaozhou 521041, China","School of Computer Information Engineering, Hanshan Normal University , Chaozhou 521041, China"],"affiliations":[{"raw_affiliation_string":"Hanshan Normal University, Chaozhou 521041, China","institution_ids":["https://openalex.org/I4210165736"]},{"raw_affiliation_string":"School of Computer Information Engineering, Hanshan Normal University , Chaozhou 521041, China","institution_ids":["https://openalex.org/I4210165736","https://openalex.org/I41147446"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029998682","display_name":"Xueqi Cheng","orcid":"https://orcid.org/0000-0002-5201-8195"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xueqi Cheng","raw_affiliation_strings":["CAS Key Laboratory of Network Data Science & Technology, Institute of Computing Technology, Chinese Academy of Sciences, Beijing 100190, China","University of Chinese Academy of Sciences, Beijing 101408, China"],"affiliations":[{"raw_affiliation_string":"CAS Key Laboratory of Network Data Science & Technology, Institute of Computing Technology, Chinese Academy of Sciences, Beijing 100190, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing 101408, China","institution_ids":["https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":11,"corresponding_author_ids":["https://openalex.org/A5059227106","https://openalex.org/A5066323756","https://openalex.org/A5101562509"],"corresponding_institution_ids":["https://openalex.org/I125839683","https://openalex.org/I19820366","https://openalex.org/I41147446","https://openalex.org/I4210090176","https://openalex.org/I4210165038","https://openalex.org/I4210165736"],"apc_list":{"value":1400,"currency":"CHF","value_usd":1515},"apc_paid":{"value":1400,"currency":"CHF","value_usd":1515},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.18691879,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"18","issue":"11","first_page":"729","last_page":"729"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.8776000142097473,"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":0.8776000142097473,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.01810000091791153,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11326","display_name":"Stock Market Forecasting Methods","score":0.010099999606609344,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7290999889373779},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6586999893188477},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"Temporal difference learning","score":0.6365000009536743},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.6341999769210815},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5080999732017517},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.4740999937057495},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4156000018119812}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7290999889373779},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7056999802589417},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6586999893188477},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.6365000009536743},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.6341999769210815},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5267000198364258},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5080999732017517},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.4740999937057495},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4156000018119812},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.4077000021934509},{"id":"https://openalex.org/C2777027219","wikidata":"https://www.wikidata.org/wiki/Q1284190","display_name":"Constant (computer programming)","level":2,"score":0.40070000290870667},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.38940000534057617},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3871999979019165},{"id":"https://openalex.org/C2781039887","wikidata":"https://www.wikidata.org/wiki/Q1391724","display_name":"Factor (programming language)","level":2,"score":0.3531999886035919},{"id":"https://openalex.org/C91873725","wikidata":"https://www.wikidata.org/wiki/Q3445816","display_name":"Function approximation","level":3,"score":0.3330000042915344},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.32339999079704285},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.30720001459121704},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.30640000104904175},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.29980000853538513},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.2572999894618988}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3390/a18110729","is_oa":true,"landing_page_url":"https://doi.org/10.3390/a18110729","pdf_url":"https://www.mdpi.com/1999-4893/18/11/729/pdf","source":{"id":"https://openalex.org/S190629608","display_name":"Algorithms","issn_l":"1999-4893","issn":["1999-4893"],"is_oa":true,"is_in_doaj":true,"is_core":true,"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":"Algorithms","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:bed493eefb4b402f8f8952e72113eb31","is_oa":true,"landing_page_url":"https://doaj.org/article/bed493eefb4b402f8f8952e72113eb31","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Algorithms, Vol 18, Iss 11, p 729 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/a18110729","is_oa":true,"landing_page_url":"https://doi.org/10.3390/a18110729","pdf_url":"https://www.mdpi.com/1999-4893/18/11/729/pdf","source":{"id":"https://openalex.org/S190629608","display_name":"Algorithms","issn_l":"1999-4893","issn":["1999-4893"],"is_oa":true,"is_in_doaj":true,"is_core":true,"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":"Algorithms","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2723974393","display_name":null,"funder_award_id":"2021KCXTD038","funder_id":"https://openalex.org/F4320321921","funder_display_name":"Natural Science Foundation of Guangdong Province"},{"id":"https://openalex.org/G4791869945","display_name":null,"funder_award_id":"2021KCXTD038","funder_id":"https://openalex.org/F4320326279","funder_display_name":"Department of Education of Guangdong Province"},{"id":"https://openalex.org/G765747151","display_name":null,"funder_award_id":"2022A1515010990","funder_id":"https://openalex.org/F4320321921","funder_display_name":"Natural Science Foundation of Guangdong Province"},{"id":"https://openalex.org/G7854535207","display_name":null,"funder_award_id":"2022KSYS003","funder_id":"https://openalex.org/F4320326279","funder_display_name":"Department of Education of Guangdong Province"},{"id":"https://openalex.org/G914301285","display_name":null,"funder_award_id":"XY202105","funder_id":"https://openalex.org/F4320326686","funder_display_name":"Hanshan Normal University"}],"funders":[{"id":"https://openalex.org/F4320321921","display_name":"Natural Science Foundation of Guangdong Province","ror":null},{"id":"https://openalex.org/F4320326279","display_name":"Department of Education of Guangdong Province","ror":null},{"id":"https://openalex.org/F4320326686","display_name":"Hanshan Normal University","ror":"https://ror.org/05tqaz865"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416422402.pdf","grobid_xml":"https://content.openalex.org/works/W4416422402.grobid-xml"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W1536990779","https://openalex.org/W1586162706","https://openalex.org/W2041282815","https://openalex.org/W2100677568","https://openalex.org/W2100752967","https://openalex.org/W2136064843","https://openalex.org/W2489939061","https://openalex.org/W2962845991","https://openalex.org/W2962847657","https://openalex.org/W3081393816","https://openalex.org/W4214717370","https://openalex.org/W4297225315","https://openalex.org/W4382318251","https://openalex.org/W4400488003"],"related_works":[],"abstract_inverted_index":{"In":[0],"numerous":[1],"episodic":[2],"reinforcement":[3],"learning":[4,132,142,204],"(RL)":[5],"environments,":[6],"SARSA-based":[7],"methodologies":[8],"are":[9],"employed":[10],"to":[11,37,59,80,87,95,108,167],"enhance":[12],"policies":[13],"aimed":[14],"at":[15],"maximizing":[16],"returns":[17],"over":[18],"long":[19],"horizons.":[20],"Traditional":[21],"SARSA":[22,61,111],"algorithms":[23],"face":[24],"challenges":[25],"in":[26,149,170,177,184,206],"achieving":[27],"an":[28],"optimal":[29],"balance":[30],"between":[31,76],"bias":[32,169],"and":[33,100,145,173,180,209],"variation,":[34],"primarily":[35],"due":[36],"their":[38],"dependence":[39],"on":[40,73],"a":[41,89,96,113,134,191],"single,":[42],"constant":[43],"discount":[44,82,98],"factor":[45,99],"(\u03b7).":[46],"This":[47,103,127,139],"study":[48],"enhances":[49,120],"the":[50,60,64,74,163,198],"temporal":[51,124],"difference":[52,125],"decomposition":[53],"method,":[54],"TD(\u0394),":[55],"by":[56],"applying":[57],"it":[58],"algorithm,":[62],"wherein":[63],"action-value":[65,77,121],"function":[66],"is":[67,93,106,112,154],"segmented":[68],"into":[69],"several":[70],"components":[71],"based":[72],"differences":[75],"functions":[78,122],"linked":[79,94],"specific":[81,97],"factors.":[83],"Each":[84],"component,":[85],"referred":[86,107],"as":[88,109],"delta":[90],"estimator":[91],"(D),":[92],"learned":[101],"independently.":[102],"modified":[104],"technique":[105,165],"SARSA(\u0394).":[110],"widely":[114],"used":[115],"on-policy":[116],"RL":[117,211],"method":[118],"that":[119,162,197],"via":[123],"updates.":[126],"decomposition,":[128],"namely":[129],"SARSA(\u0394),":[130],"facilitates":[131],"across":[133],"range":[135],"of":[136,158,193],"time":[137],"scales.":[138],"analysis":[140],"makes":[141],"more":[143],"effective":[144],"guarantees":[146],"consistency,":[147],"especially":[148],"situations":[150],"where":[151],"long-horizon":[152],"improvement":[153],"needed.":[155],"The":[156],"results":[157,189],"this":[159],"research":[160],"show":[161,196],"proposed":[164,199],"works":[166],"lower":[168],"SARSA\u2019s":[171],"updates":[172],"speed":[174],"up":[175],"convergence":[176],"both":[178,207],"deterministic":[179],"stochastic":[181],"settings,":[182],"even":[183],"dense-reward":[185],"Atari":[186],"environments.":[187,212],"Experimental":[188],"from":[190],"variety":[192],"benchmark":[194],"settings":[195],"SARSA(\u0394)":[200],"outperforms":[201],"existing":[202],"TD":[203],"techniques":[205],"tabular":[208],"deep":[210]},"counts_by_year":[],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-11-20T00:00:00"}