{"id":"https://openalex.org/W4404871448","doi":"https://doi.org/10.1109/lcsys.2024.3509815","title":"Gradient Flow Approximations in Temporal Difference Learning","display_name":"Gradient Flow Approximations in Temporal Difference Learning","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4404871448","doi":"https://doi.org/10.1109/lcsys.2024.3509815"},"language":"en","primary_location":{"id":"doi:10.1109/lcsys.2024.3509815","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lcsys.2024.3509815","pdf_url":null,"source":{"id":"https://openalex.org/S4306422535","display_name":"IEEE Control Systems Letters","issn_l":"2475-1456","issn":["2475-1456"],"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 Control Systems Letters","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":"https://openalex.org/A5095777283","display_name":"Amirreza Neshaei Moghaddam","orcid":null},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Amirreza Neshaei Moghaddam","raw_affiliation_strings":["Electrical and Computer Engineering Department, University of California at Los Angeles, Los Angeles, CA, USA"],"raw_orcid":"https://orcid.org/0009-0000-6213-8396","affiliations":[{"raw_affiliation_string":"Electrical and Computer Engineering Department, University of California at Los Angeles, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022064746","display_name":"Bahman Gharesifard","orcid":"https://orcid.org/0000-0003-1495-3489"},"institutions":[{"id":"https://openalex.org/I204722609","display_name":"Queen's University","ror":"https://ror.org/02y72wh86","country_code":"CA","type":"education","lineage":["https://openalex.org/I204722609"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Bahman Gharesifard","raw_affiliation_strings":["Mathematics and Statistics Department, Queen’s University, Kingston, ON, Canada"],"raw_orcid":"https://orcid.org/0000-0003-1495-3489","affiliations":[{"raw_affiliation_string":"Mathematics and Statistics Department, Queen’s University, Kingston, ON, Canada","institution_ids":["https://openalex.org/I204722609"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.30769465,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"8","issue":null,"first_page":"2655","last_page":"2660"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10515","display_name":"Cancer-related molecular mechanisms research","score":0.6098999977111816,"subfield":{"id":"https://openalex.org/subfields/1306","display_name":"Cancer Research"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10515","display_name":"Cancer-related molecular mechanisms research","score":0.6098999977111816,"subfield":{"id":"https://openalex.org/subfields/1306","display_name":"Cancer Research"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11206","display_name":"Model Reduction and Neural Networks","score":0.5335999727249146,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.5236999988555908,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/temporal-difference-learning","display_name":"Temporal difference learning","score":0.6914709210395813},{"id":"https://openalex.org/keywords/flow","display_name":"Flow (mathematics)","score":0.4892556667327881},{"id":"https://openalex.org/keywords/balanced-flow","display_name":"Balanced flow","score":0.4813597798347473},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.38354796171188354},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.375291645526886},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.3496817350387573},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.27324265241622925},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.24132698774337769},{"id":"https://openalex.org/keywords/geometry","display_name":"Geometry","score":0.13927340507507324},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.07763040065765381}],"concepts":[{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.6914709210395813},{"id":"https://openalex.org/C38349280","wikidata":"https://www.wikidata.org/wiki/Q1434290","display_name":"Flow (mathematics)","level":2,"score":0.4892556667327881},{"id":"https://openalex.org/C167879884","wikidata":"https://www.wikidata.org/wiki/Q727568","display_name":"Balanced flow","level":2,"score":0.4813597798347473},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.38354796171188354},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.375291645526886},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.3496817350387573},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27324265241622925},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.24132698774337769},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.13927340507507324},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.07763040065765381}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lcsys.2024.3509815","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lcsys.2024.3509815","pdf_url":null,"source":{"id":"https://openalex.org/S4306422535","display_name":"IEEE Control Systems Letters","issn_l":"2475-1456","issn":["2475-1456"],"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 Control Systems Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.5}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W395117528","https://openalex.org/W2139418546","https://openalex.org/W2508752903","https://openalex.org/W3041202696","https://openalex.org/W3210638057","https://openalex.org/W4300511988","https://openalex.org/W6750489461","https://openalex.org/W6752495264","https://openalex.org/W6768405397","https://openalex.org/W6785020549","https://openalex.org/W6859625924"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W1979597421","https://openalex.org/W2007980826","https://openalex.org/W2061531152","https://openalex.org/W2575776545","https://openalex.org/W2111336616","https://openalex.org/W2035082207","https://openalex.org/W3102086522","https://openalex.org/W3000992358","https://openalex.org/W2954778286"],"abstract_inverted_index":{"We":[0,56],"consider":[1],"the":[2,21,38,47,71,76,104,107,110],"continuous-time":[3],"temporal":[4],"difference":[5],"(TD)":[6],"learning":[7],"dynamics":[8,49],"with":[9],"nonlinear":[10,96],"value":[11,40],"function":[12,41],"approximations,":[13,115],"where":[14,116],"there":[15],"is":[16],"a":[17,53,63,83,87,92,100],"slim":[18],"understanding":[19],"of":[20,65,73,79,106,113],"convergence":[22],"properties":[23],"in":[24],"irreversible":[25],"regimes.":[26],"Motivated":[27],"by":[28],"Krener\u2019s":[29],"linearization":[30],"idea":[31],"ala":[32],"Lie-brackets,":[33],"we":[34,90,102],"obtain":[35],"conditions":[36,60,118],"on":[37],"approximating":[39],"and":[42,69,121],"irreversibility":[43],"coefficients":[44],"under":[45],"which":[46],"TD":[48,97],"behaves":[50],"close":[51],"to":[52,62],"gradient":[54],"flow.":[55],"show":[57],"that":[58],"our":[59,117],"lead":[61],"set":[64],"partial":[66],"differential":[67,80],"equations,":[68],"study":[70],"existence":[72],"solutions":[74],"using":[75,86],"algebraic":[77],"invertibility":[78],"operators.":[81],"Whenever":[82],"solution":[84],"exists,":[85],"perturbation":[88],"analysis,":[89],"provide":[91],"stability":[93],"result":[94],"for":[95,109],"dynamics.":[98],"As":[99],"by-product,":[101],"state":[103],"implications":[105],"results":[108],"classical":[111],"case":[112],"linear":[114],"are":[119],"algebraic,":[120],"easily":[122],"verifiable.":[123]},"counts_by_year":[],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}