{"id":"https://openalex.org/W4312667845","doi":"https://doi.org/10.1109/tac.2022.3213763","title":"New Versions of Gradient Temporal-Difference Learning","display_name":"New Versions of Gradient Temporal-Difference Learning","publication_year":2022,"publication_date":"2022-10-11","ids":{"openalex":"https://openalex.org/W4312667845","doi":"https://doi.org/10.1109/tac.2022.3213763"},"language":"en","primary_location":{"id":"doi:10.1109/tac.2022.3213763","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tac.2022.3213763","pdf_url":"https://ieeexplore.ieee.org/ielx7/9/10196077/09916098.pdf","source":{"id":"https://openalex.org/S184954342","display_name":"IEEE Transactions on Automatic Control","issn_l":"0018-9286","issn":["0018-9286","1558-2523","2334-3303"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Automatic Control","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ieeexplore.ieee.org/ielx7/9/10196077/09916098.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100654317","display_name":"Donghwan Lee","orcid":"https://orcid.org/0000-0002-4962-8478"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Donghwan Lee","raw_affiliation_strings":["Department of Electrical Engineering, KAIST, Daejeon, South Korea"],"raw_orcid":"https://orcid.org/0000-0002-4962-8478","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, KAIST, Daejeon, South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006683710","display_name":"Han-Dong Lim","orcid":"https://orcid.org/0000-0002-1515-5836"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Han-Dong Lim","raw_affiliation_strings":["Department of Electrical Engineering, KAIST, Daejeon, South Korea"],"raw_orcid":"https://orcid.org/0000-0002-1515-5836","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, KAIST, Daejeon, South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043687478","display_name":"Jihoon Park","orcid":null},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jihoon Park","raw_affiliation_strings":["Department of Electrical Engineering, KAIST, Daejeon, South Korea"],"raw_orcid":"https://orcid.org/0000-0001-6061-3202","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, KAIST, Daejeon, South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053180967","display_name":"Okyong Choi","orcid":"https://orcid.org/0000-0002-7536-3477"},"institutions":[{"id":"https://openalex.org/I897156735","display_name":"Bank of Korea","ror":"https://ror.org/03s7h1x17","country_code":"KR","type":"other","lineage":["https://openalex.org/I897156735"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Okyong Choi","raw_affiliation_strings":["Shinhan Bank Research Team, Seoul, South Korea"],"raw_orcid":"https://orcid.org/0000-0002-7536-3477","affiliations":[{"raw_affiliation_string":"Shinhan Bank Research Team, Seoul, South Korea","institution_ids":["https://openalex.org/I897156735"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3661,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.57601667,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"68","issue":"8","first_page":"5006","last_page":"5013"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11206","display_name":"Model Reduction and Neural Networks","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11206","display_name":"Model Reduction and Neural Networks","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9944000244140625,"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/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9801999926567078,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/saddle-point","display_name":"Saddle point","score":0.7626965045928955},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.5500298738479614},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.5455049276351929},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.5094249844551086},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.49369320273399353},{"id":"https://openalex.org/keywords/saddle","display_name":"Saddle","score":0.48455873131752014},{"id":"https://openalex.org/keywords/regular-polygon","display_name":"Regular polygon","score":0.4764183759689331},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.455055296421051},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.450824499130249},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.44028618931770325},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.424716055393219},{"id":"https://openalex.org/keywords/convex-function","display_name":"Convex function","score":0.4192487597465515},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.41286417841911316},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3347642421722412},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.32199859619140625},{"id":"https://openalex.org/keywords/geometry","display_name":"Geometry","score":0.13521510362625122},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.1324842870235443}],"concepts":[{"id":"https://openalex.org/C2681867","wikidata":"https://www.wikidata.org/wiki/Q690935","display_name":"Saddle point","level":2,"score":0.7626965045928955},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.5500298738479614},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.5455049276351929},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.5094249844551086},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.49369320273399353},{"id":"https://openalex.org/C2777127463","wikidata":"https://www.wikidata.org/wiki/Q10862618","display_name":"Saddle","level":2,"score":0.48455873131752014},{"id":"https://openalex.org/C112680207","wikidata":"https://www.wikidata.org/wiki/Q714886","display_name":"Regular polygon","level":2,"score":0.4764183759689331},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.455055296421051},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.450824499130249},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.44028618931770325},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.424716055393219},{"id":"https://openalex.org/C145446738","wikidata":"https://www.wikidata.org/wiki/Q319913","display_name":"Convex function","level":3,"score":0.4192487597465515},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.41286417841911316},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3347642421722412},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.32199859619140625},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.13521510362625122},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.1324842870235443},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tac.2022.3213763","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tac.2022.3213763","pdf_url":"https://ieeexplore.ieee.org/ielx7/9/10196077/09916098.pdf","source":{"id":"https://openalex.org/S184954342","display_name":"IEEE Transactions on Automatic Control","issn_l":"0018-9286","issn":["0018-9286","1558-2523","2334-3303"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Automatic Control","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1109/tac.2022.3213763","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tac.2022.3213763","pdf_url":"https://ieeexplore.ieee.org/ielx7/9/10196077/09916098.pdf","source":{"id":"https://openalex.org/S184954342","display_name":"IEEE Transactions on Automatic Control","issn_l":"0018-9286","issn":["0018-9286","1558-2523","2334-3303"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Automatic Control","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1450359739","display_name":null,"funder_award_id":"NRF-2021R1F1A1061613","funder_id":"https://openalex.org/F4320320671","funder_display_name":"National Research Foundation"}],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4312667845.pdf","grobid_xml":"https://content.openalex.org/works/W4312667845.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W359561291","https://openalex.org/W1499021337","https://openalex.org/W1600046456","https://openalex.org/W2020123437","https://openalex.org/W2071983464","https://openalex.org/W2075268401","https://openalex.org/W2144672231","https://openalex.org/W2165905123","https://openalex.org/W2562316362","https://openalex.org/W2569419980","https://openalex.org/W2789265722","https://openalex.org/W2949996623","https://openalex.org/W2964005211","https://openalex.org/W2966952338","https://openalex.org/W3041202696","https://openalex.org/W3099870866","https://openalex.org/W4214717370","https://openalex.org/W4250589301","https://openalex.org/W4287197771","https://openalex.org/W4287746248","https://openalex.org/W4312657794","https://openalex.org/W4312667845","https://openalex.org/W6635798015","https://openalex.org/W6684488654","https://openalex.org/W6731039252","https://openalex.org/W6751921135","https://openalex.org/W6752164047","https://openalex.org/W6779390608","https://openalex.org/W6794007783","https://openalex.org/W6840505315"],"related_works":["https://openalex.org/W4236459141","https://openalex.org/W4205304778","https://openalex.org/W2020252434","https://openalex.org/W73248859","https://openalex.org/W2584253892","https://openalex.org/W2350324449","https://openalex.org/W119381072","https://openalex.org/W2034033896","https://openalex.org/W2094891943","https://openalex.org/W4240399920"],"abstract_inverted_index":{"Sutton,":[0],"Szepesv\u00e1ri":[1],"and":[2,18,38,69],"Maei":[3],"introduced":[4],"the":[5,47,63,90],"first":[6],"gradient":[7,80],"temporal-difference":[8],"(GTD)":[9],"learning":[10],"algorithms":[11],"compatible":[12],"with":[13,34],"both":[14],"linear":[15],"function":[16],"approximation":[17],"off-policy":[19],"training.":[20],"The":[21],"goal":[22],"of":[23,32,57],"this":[24],"article":[25],"is":[26,86],"1)":[27],"to":[28,40,88],"propose":[29],"some":[30],"variants":[31,50],"GTDs":[33,64],"extensive":[35],"comparative":[36,84],"analysis":[37,44,73,85],"2)":[39],"establish":[41],"new":[42,91],"theoretical":[43],"frameworks":[45],"for":[46],"GTDs.":[48],"These":[49],"are":[51],"based":[52,74],"on":[53,75,78],"convex\u2013concave":[54],"saddle-point":[55],"interpretations":[56],"GTDs,":[58],"which":[59],"effectively":[60],"unify":[61],"all":[62],"into":[65],"a":[66],"single":[67],"framework,":[68],"provide":[70],"simple":[71],"stability":[72],"recent":[76],"results":[77],"primal\u2013dual":[79],"dynamics.":[81],"Finally,":[82],"numerical":[83],"given":[87],"evaluate":[89],"approaches.":[92]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}