{"id":"https://openalex.org/W7225801739","doi":"https://doi.org/10.1109/tcst.2026.3747302","title":"Foresight-Aware Reinforcement Learning for Infinite-Horizon Optimal Tracking Control","display_name":"Foresight-Aware Reinforcement Learning for Infinite-Horizon Optimal Tracking Control","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7225801739","doi":"https://doi.org/10.1109/tcst.2026.3747302"},"language":"en","primary_location":{"id":"doi:10.1109/tcst.2026.3747302","doi":"https://doi.org/10.1109/tcst.2026.3747302","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tcst.2026.3747302","pdf_url":null,"source":{"id":"https://openalex.org/S133363738","display_name":"IEEE Transactions on Control Systems Technology","issn_l":"1063-6536","issn":["1063-6536","1558-0865","2374-0159"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","dongbi-b","jufo-2","norway-2","poland-140","russia-white-list-1"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Control Systems Technology","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1109/tcst.2026.3747302","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5011635677","display_name":"Letian Tao","orcid":"https://orcid.org/0000-0002-0622-2208","observed_orcids":["https://orcid.org/0000-0002-0622-2208"]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Letian Tao","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":"https://orcid.org/0000-0002-0622-2208","affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100696317","display_name":"Jie Li","orcid":"https://orcid.org/0000-0002-3718-5593","observed_orcids":["https://orcid.org/0000-0002-3718-5593"]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Li","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":"https://orcid.org/0000-0002-3718-5593","affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067909017","display_name":"Jingliang Duan","orcid":"https://orcid.org/0000-0002-3697-1576","observed_orcids":["https://orcid.org/0000-0002-3697-1576"]},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingliang Duan","raw_affiliation_strings":["University of Science and Technology Beijing"],"raw_orcid":"https://orcid.org/0000-0002-3697-1576","affiliations":[{"raw_affiliation_string":"University of Science and Technology Beijing","institution_ids":["https://openalex.org/I92403157"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100747108","display_name":"Shengbo Eben Li","orcid":"https://orcid.org/0000-0003-4923-3633","observed_orcids":["https://orcid.org/0000-0003-4923-3633"]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengbo Eben Li","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":"https://orcid.org/0000-0003-4923-3633","affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5161459073","display_name":"Honglin Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210153068","display_name":"Dongfeng Motor Group (China)","ror":"https://ror.org/055ar4y96","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210153068"]},{"id":"https://openalex.org/I4210158664","display_name":"Dongfeng Motor (China)","ror":"https://ror.org/049j15k39","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210158664"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Honglin Li","raw_affiliation_strings":["Research and Development Institute, Dongfeng Motor Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research and Development Institute, Dongfeng Motor Corporation","institution_ids":["https://openalex.org/I4210153068","https://openalex.org/I4210158664"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114192733","display_name":"Liangguang Wu","orcid":"https://orcid.org/0000-0001-8858-6576","observed_orcids":["https://orcid.org/0000-0001-8858-6576"]},"institutions":[{"id":"https://openalex.org/I4210153068","display_name":"Dongfeng Motor Group (China)","ror":"https://ror.org/055ar4y96","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210153068"]},{"id":"https://openalex.org/I4210158664","display_name":"Dongfeng Motor (China)","ror":"https://ror.org/049j15k39","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210158664"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liangguang Wu","raw_affiliation_strings":["Research and Development Institute, Dongfeng Motor Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research and Development Institute, Dongfeng Motor Corporation","institution_ids":["https://openalex.org/I4210153068","https://openalex.org/I4210158664"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111280622","display_name":"Kailong Zhou","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210153068","display_name":"Dongfeng Motor Group (China)","ror":"https://ror.org/055ar4y96","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210153068"]},{"id":"https://openalex.org/I4210158664","display_name":"Dongfeng Motor (China)","ror":"https://ror.org/049j15k39","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210158664"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kailong Zhou","raw_affiliation_strings":["Research and Development Institute, Dongfeng Motor Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research and Development Institute, Dongfeng Motor Corporation","institution_ids":["https://openalex.org/I4210153068","https://openalex.org/I4210158664"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5161472387","display_name":"Dezhao Zhang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dezhao Zhang","raw_affiliation_strings":["Beijing Idriverplus Technology Company Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Idriverplus Technology Company Ltd","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100411423","display_name":"Xiao Wang","orcid":"https://orcid.org/0000-0001-5614-9582","observed_orcids":["https://orcid.org/0000-0001-5614-9582"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiao Wang","raw_affiliation_strings":["Beijing Idriverplus Technology Company Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Idriverplus Technology Company Ltd","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2645,"currency":"USD","value_usd":2645},"apc_paid":{"value":2645,"currency":"USD","value_usd":2645},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"12"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.8349999785423279,"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"}},"topics":[{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.8349999785423279,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.16410000622272491,"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.0007999999797903001,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.8029999732971191},{"id":"https://openalex.org/keywords/infinite-horizon-control","display_name":"infinite horizon control","score":0.7960000038146973},{"id":"https://openalex.org/keywords/optimal-tracking-control","display_name":"optimal tracking control","score":0.9309999942779541},{"id":"https://openalex.org/keywords/model-predictive-control","display_name":"model predictive control","score":0.5559999942779541}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5669000148773193},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4577000141143799},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.44749999046325684},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.42820000648498535},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.41679999232292175},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.4043000042438507},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.3765999972820282},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.335999995470047},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.31380000710487366},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.31290000677108765},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.27000001072883606},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2678999900817871},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.26759999990463257},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.26089999079704285},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.2517000138759613},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.2502000033855438}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcst.2026.3747302","doi":"https://doi.org/10.1109/tcst.2026.3747302","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tcst.2026.3747302","pdf_url":null,"source":{"id":"https://openalex.org/S133363738","display_name":"IEEE Transactions on Control Systems Technology","issn_l":"1063-6536","issn":["1063-6536","1558-0865","2374-0159"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","dongbi-b","jufo-2","norway-2","poland-140","russia-white-list-1"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Control Systems Technology","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1109/tcst.2026.3747302","doi":"https://doi.org/10.1109/tcst.2026.3747302","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tcst.2026.3747302","pdf_url":null,"source":{"id":"https://openalex.org/S133363738","display_name":"IEEE Transactions on Control Systems Technology","issn_l":"1063-6536","issn":["1063-6536","1558-0865","2374-0159"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","dongbi-b","jufo-2","norway-2","poland-140","russia-white-list-1"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Control Systems Technology","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Conventional":[0],"reinforcement":[1],"learning":[2,109],"(RL)":[3],"algorithms":[4],"for":[5,205],"the":[6,19,58,80,87,97,108,125,142,151,170,174,180,203,221,224],"infinite-horizon":[7],"optimal":[8,126],"tracking":[9,30,34,76,217,231],"suffer":[10],"from":[11,200],"short-sightedness,":[12],"as":[13,86,220],"their":[14],"policy":[15,114,175],"typically":[16],"considers":[17],"only":[18],"immediate":[20],"reference":[21,50,59,65,69,84,181,195,208],"state.":[22,89],"This":[23,39,185],"inherent":[24],"limitation":[25],"can":[26],"lead":[27],"to":[28,52,62],"suboptimal":[29],"performance,":[31],"particularly":[32],"when":[33],"complex":[35],"and":[36,211],"dynamic":[37,162],"trajectories.":[38],"article":[40],"proposes":[41],"a":[42,48,102,111,137,156,189],"foresight-aware":[43,160],"RL":[44,158,232],"method":[45,226],"that":[46,78,92,124,141,173,219],"incorporates":[47],"multistep":[49],"preview":[51,222],"overcome":[53],"this":[54,93,121],"limitation.":[55],"We":[56,71,134,154],"introduce":[57],"prediction":[60,182],"model":[61],"infer":[63],"future":[64,130,194],"information":[66],"based":[67],"on$N$-step":[68],"preview.":[70],"then":[72],"construct":[73],"an":[74,206],"augmented":[75,88,94],"system":[77,81,95],"takes":[79],"state":[82],"and$N$-step":[83],"signals":[85],"By":[90],"proving":[91,140],"satisfies":[96],"Markov":[98],"property,":[99],"we":[100],"formulate":[101],"corresponding":[103],"Bellman":[104],"equation,":[105],"which":[106,148],"enables":[107,188],"of":[110,179],"stationary,":[112],"time-invariant":[113],"with":[115],"foresight.":[116],"Rigorous":[117],"sensitivity":[118],"analysis":[119],"substantiates":[120],"approach,":[122],"demonstrating":[123],"control\u2019s":[127],"dependence":[128],"on":[129,215],"references":[131],"decays":[132],"exponentially.":[133],"further":[135],"derive":[136],"performance":[138],"bound,":[139],"optimality":[143],"gap":[144],"diminishes":[145],"exponentially":[146],"as$N$increases,":[147],"theoretically":[149],"validates":[150],"finite-preview":[152],"strategy.":[153],"develop":[155],"model-based":[157],"algorithm,":[159],"approximate":[161],"programming":[163],"(FAADP),":[164],"whose":[165],"practicality":[166],"is":[167,177],"enabled":[168],"by":[169],"theoretical":[171],"finding":[172,187],"gradient":[176],"independent":[178],"model\u2019s":[183],"derivatives.":[184],"key":[186],"novel":[190],"training":[191],"paradigm":[192],"where":[193],"states":[196],"are":[197],"simply":[198],"sampled":[199],"data,":[201],"obviating":[202],"need":[204],"analytical":[207],"model.":[209],"Simulation":[210],"real-world":[212],"driving":[213],"experiments":[214],"vehicle":[216],"demonstrate":[218],"horizon$N$increases,":[223],"proposed":[225],"significantly":[227],"outperforms":[228],"previous":[229],"first-point":[230],"approaches.":[233]},"counts_by_year":[],"updated_date":"2026-11-13T13:42:25.865203","created_date":"2026-11-12T00:00:00"}