{"id":"https://openalex.org/W4414404777","doi":"https://doi.org/10.1109/tcds.2025.3611975","title":"Sarsa-Augmented Off-Policy Reinforcement Learning","display_name":"Sarsa-Augmented Off-Policy Reinforcement Learning","publication_year":2025,"publication_date":"2025-09-22","ids":{"openalex":"https://openalex.org/W4414404777","doi":"https://doi.org/10.1109/tcds.2025.3611975"},"language":"en","primary_location":{"id":"doi:10.1109/tcds.2025.3611975","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcds.2025.3611975","pdf_url":null,"source":{"id":"https://openalex.org/S2488537894","display_name":"IEEE Transactions on Cognitive and Developmental Systems","issn_l":"2379-8920","issn":["2379-8920","2379-8939"],"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 Cognitive and Developmental Systems","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":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":["School of Automation and Intelligent Sensing, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-4322-4314","affiliations":[{"raw_affiliation_string":"School of Automation and Intelligent Sensing, Shanghai Jiao Tong University, Shanghai, 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":["School of Automation and Intelligent Sensing, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-5123-5043","affiliations":[{"raw_affiliation_string":"School of Automation and Intelligent Sensing, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","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":["School of Automation and Intelligent Sensing, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-2026-6856","affiliations":[{"raw_affiliation_string":"School of Automation and Intelligent Sensing, Shanghai Jiao Tong University, Shanghai, 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":["School of Automation and Intelligent Sensing, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-8600-9668","affiliations":[{"raw_affiliation_string":"School of Automation and Intelligent Sensing, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100328090","display_name":"Xin Wang","orcid":"https://orcid.org/0000-0003-2070-960X"},"institutions":[{"id":"https://openalex.org/I142108993","display_name":"Southwest University","ror":"https://ror.org/01kj4z117","country_code":"CN","type":"education","lineage":["https://openalex.org/I142108993"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Wang","raw_affiliation_strings":["College of Electronic and Information Engineering, Southwest University, Chongqing, China"],"raw_orcid":"https://orcid.org/0000-0003-2070-960X","affiliations":[{"raw_affiliation_string":"College of Electronic and Information Engineering, Southwest University, Chongqing, China","institution_ids":["https://openalex.org/I142108993"]}]},{"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":["School of Automation and Intelligent Sensing, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-4700-1276","affiliations":[{"raw_affiliation_string":"School of Automation and Intelligent Sensing, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.396,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.8605185,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"18","issue":"2","first_page":"504","last_page":"517"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.46639999747276306,"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":0.46639999747276306,"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":0.45559999346733093,"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":0.40860000252723694,"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/extrapolation","display_name":"Extrapolation","score":0.7750999927520752},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7534999847412109},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.5855000019073486},{"id":"https://openalex.org/keywords/conditional-entropy","display_name":"Conditional entropy","score":0.527999997138977},{"id":"https://openalex.org/keywords/principle-of-maximum-entropy","display_name":"Principle of maximum entropy","score":0.5260999798774719},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.48919999599456787},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.4587000012397766},{"id":"https://openalex.org/keywords/data-collection","display_name":"Data collection","score":0.4487999975681305}],"concepts":[{"id":"https://openalex.org/C132459708","wikidata":"https://www.wikidata.org/wiki/Q744069","display_name":"Extrapolation","level":2,"score":0.7750999927520752},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7534999847412109},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7383999824523926},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.5855000019073486},{"id":"https://openalex.org/C101721835","wikidata":"https://www.wikidata.org/wiki/Q813908","display_name":"Conditional entropy","level":3,"score":0.527999997138977},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.5260999798774719},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5120999813079834},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.48919999599456787},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.4587000012397766},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.4487999975681305},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41839998960494995},{"id":"https://openalex.org/C91873725","wikidata":"https://www.wikidata.org/wiki/Q3445816","display_name":"Function approximation","level":3,"score":0.33320000767707825},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.326200008392334},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.322299987077713},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.32109999656677246},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.3206000030040741},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.30630001425743103},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.30410000681877136},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.2994999885559082},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.2953000068664551},{"id":"https://openalex.org/C186215838","wikidata":"https://www.wikidata.org/wiki/Q772232","display_name":"Conditional expectation","level":2,"score":0.2827000021934509},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.27059999108314514},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2687999904155731},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.259799987077713}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcds.2025.3611975","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcds.2025.3611975","pdf_url":null,"source":{"id":"https://openalex.org/S2488537894","display_name":"IEEE Transactions on Cognitive and Developmental Systems","issn_l":"2379-8920","issn":["2379-8920","2379-8939"],"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 Cognitive and Developmental Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1586938274","display_name":null,"funder_award_id":"2022ZD0119900","funder_id":"https://openalex.org/F4320329860","funder_display_name":"National Science and Technology Major Project"},{"id":"https://openalex.org/G2260626412","display_name":null,"funder_award_id":"U24A20260","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"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":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"In":[0,45],"classic":[1],"online":[2,137],"off-policy":[3],"reinforcement":[4],"learning":[5],"(RL),":[6],"the":[7,11,18,23,28,48,52,99,106,119,131],"action":[8],"sampled":[9],"from":[10,51],"target":[12,20,33],"policy":[13,31,34,43,69],"is":[14,57,93],"used":[15],"to":[16],"calculate":[17],"temporal-difference":[19],"for":[21],"updating":[22],"Q-function.":[24],"The":[25,87,127],"discrepancy":[26],"between":[27],"data":[29,56],"collection":[30],"and":[32,83,110,121],"can":[35],"result":[36],"in":[37,64],"certain":[38],"extrapolation":[39,81],"errors":[40,82],"that":[41,130],"mislead":[42],"evaluation.":[44],"this":[46],"work,":[47],"Q-value":[49],"derived":[50],"State-action-reward-state-action":[53],"(Sarsa)-style":[54],"trajectory":[55,78],"incorporated":[58],"as":[59],"a":[60,65],"regularization":[61],"term,":[62],"resulting":[63],"Sarsa-augmented":[66],"on-policy":[67,88],"regularized":[68,89],"evaluation":[70],"(ORPE)":[71],"approach.":[72],"Such":[73],"an":[74],"operation":[75],"introduces":[76],"historical":[77],"information,":[79],"mitigating":[80],"potentially":[84],"improving":[85],"stability.":[86],"actor-critic":[90,102],"(OR-AC)":[91],"algorithm":[92,133],"designed":[94],"by":[95],"combining":[96],"ORPE":[97],"with":[98],"maximum":[100],"entropy":[101],"architecture.":[103],"We":[104],"analyze":[105],"convergence,":[107],"conditional":[108],"monotonicity,":[109],"value":[111],"function":[112],"gap":[113],"of":[114],"ORPE.":[115],"Comparative":[116],"experiments":[117],"on":[118],"Mujoco":[120],"OpenAI":[122],"Gym":[123],"platforms":[124],"are":[125],"conducted.":[126],"results":[128],"indicate":[129],"OR-AC":[132],"surpasses":[134],"other":[135],"mainstream":[136],"RL":[138],"algorithms.":[139]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-04-09T06:08:40.794217","created_date":"2025-10-10T00:00:00"}