{"id":"https://openalex.org/W4405055433","doi":"https://doi.org/10.1109/tnnls.2024.3511670","title":"Conformal Symplectic Optimization for Stable Reinforcement Learning","display_name":"Conformal Symplectic Optimization for Stable Reinforcement Learning","publication_year":2024,"publication_date":"2024-12-11","ids":{"openalex":"https://openalex.org/W4405055433","doi":"https://doi.org/10.1109/tnnls.2024.3511670","pmid":"https://pubmed.ncbi.nlm.nih.gov/40030460"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2024.3511670","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2024.3511670","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"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 Neural Networks and Learning Systems","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2412.02291","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5083537762","display_name":"Yao Lyu","orcid":"https://orcid.org/0000-0003-1539-472X"},"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":true,"raw_author_name":"Yao Lyu","raw_affiliation_strings":["School of Vehicle and Mobility, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Vehicle and Mobility, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061121548","display_name":"Xiangteng Zhang","orcid":"https://orcid.org/0009-0001-4532-7467"},"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":"Xiangteng Zhang","raw_affiliation_strings":["School of Vehicle and Mobility, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Vehicle and Mobility, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100747108","display_name":"Shengbo Eben Li","orcid":"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":["School of Vehicle and Mobility and the College of Artificial Intelligence, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Vehicle and Mobility and the College of Artificial Intelligence, Tsinghua University, Beijing, China","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"},"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":["School of Mechanical Engineering, University of Science and Technology Beijing, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Mechanical Engineering, University of Science and Technology Beijing, Beijing, China","institution_ids":["https://openalex.org/I92403157"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011635677","display_name":"Letian Tao","orcid":null},"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":["State Key Laboratory of Intelligent Green Vehicle and Mobility, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Intelligent Green Vehicle and Mobility, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Qing Xu","orcid":"https://orcid.org/0009-0000-8516-1185"},"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":"Qing Xu","raw_affiliation_strings":["School of Vehicle and Mobility, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Vehicle and Mobility, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Lei He","orcid":"https://orcid.org/0009-0002-0370-177X"},"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":"Lei He","raw_affiliation_strings":["State Key Laboratory of Intelligent Green Vehicle and Mobility, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Intelligent Green Vehicle and Mobility, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031855986","display_name":"Keqiang Li","orcid":"https://orcid.org/0000-0002-9333-7416"},"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":"Keqiang Li","raw_affiliation_strings":["School of Vehicle and Mobility, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Vehicle and Mobility, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5083537762"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.3223,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.61127406,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"36","issue":"6","first_page":"11049","last_page":"11063"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11749","display_name":"Iterative Learning Control Systems","score":0.9617999792098999,"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/T11749","display_name":"Iterative Learning Control Systems","score":0.9617999792098999,"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/T12611","display_name":"Neural Networks and Reservoir Computing","score":0.9488999843597412,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/symplectic-geometry","display_name":"Symplectic geometry","score":0.7472883462905884},{"id":"https://openalex.org/keywords/conformal-map","display_name":"Conformal map","score":0.5837183594703674},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5689051747322083},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.46059051156044006},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.3417811393737793},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.33671969175338745},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.32311391830444336},{"id":"https://openalex.org/keywords/pure-mathematics","display_name":"Pure mathematics","score":0.2913511395454407},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.20962277054786682},{"id":"https://openalex.org/keywords/composite-material","display_name":"Composite material","score":0.19249194860458374},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.17977356910705566}],"concepts":[{"id":"https://openalex.org/C168619227","wikidata":"https://www.wikidata.org/wiki/Q2190991","display_name":"Symplectic geometry","level":2,"score":0.7472883462905884},{"id":"https://openalex.org/C98214594","wikidata":"https://www.wikidata.org/wiki/Q850275","display_name":"Conformal map","level":2,"score":0.5837183594703674},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5689051747322083},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.46059051156044006},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3417811393737793},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.33671969175338745},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.32311391830444336},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.2913511395454407},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.20962277054786682},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.19249194860458374},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.17977356910705566}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tnnls.2024.3511670","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2024.3511670","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"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 Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:40030460","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40030460","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on neural networks and learning systems","raw_type":null},{"id":"pmh:oai:arXiv.org:2412.02291","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2412.02291","pdf_url":"https://arxiv.org/pdf/2412.02291","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2412.02291","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2412.02291","pdf_url":"https://arxiv.org/pdf/2412.02291","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.8500000238418579}],"awards":[{"id":"https://openalex.org/G1121271761","display_name":null,"funder_award_id":"Program","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1231421488","display_name":null,"funder_award_id":"under","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1500936459","display_name":null,"funder_award_id":"2022YFB2502901","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G166390454","display_name":null,"funder_award_id":"U20A20334","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2048979999","display_name":null,"funder_award_id":"U20A2033","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G391238517","display_name":null,"funder_award_id":", and","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5939423041","display_name":null,"funder_award_id":"Technology","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6468925182","display_name":null,"funder_award_id":"2022YFB2502901","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/F4320322392","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4405055433.pdf"},"referenced_works_count":36,"referenced_works":["https://openalex.org/W587555435","https://openalex.org/W1601081659","https://openalex.org/W2145339207","https://openalex.org/W2150468603","https://openalex.org/W2158782408","https://openalex.org/W2280533987","https://openalex.org/W2746553466","https://openalex.org/W2768950724","https://openalex.org/W2776855315","https://openalex.org/W2904246096","https://openalex.org/W2921285456","https://openalex.org/W2963430672","https://openalex.org/W2963433607","https://openalex.org/W2969232873","https://openalex.org/W2972507487","https://openalex.org/W2982316857","https://openalex.org/W3015082424","https://openalex.org/W3017061634","https://openalex.org/W3125488110","https://openalex.org/W4224216677","https://openalex.org/W4362650413","https://openalex.org/W4366158867","https://openalex.org/W4376481351","https://openalex.org/W4388878609","https://openalex.org/W4394006698","https://openalex.org/W6631190155","https://openalex.org/W6638018090","https://openalex.org/W6681435938","https://openalex.org/W6684921986","https://openalex.org/W6738491991","https://openalex.org/W6748839928","https://openalex.org/W6754654111","https://openalex.org/W6757107679","https://openalex.org/W6757817989","https://openalex.org/W6774451767","https://openalex.org/W6922480057"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W1979597421","https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W2007980826","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2061531152","https://openalex.org/W3002753104"],"abstract_inverted_index":{"Training":[0],"deep":[1],"reinforcement":[2],"learning":[3,136],"(RL)":[4],"agents":[5],"necessitates":[6],"overcoming":[7],"the":[8,16,47,73,79,117,163],"highly":[9],"unstable":[10],"nonconvex":[11,145],"stochastic":[12],"optimization":[13,27,84,115],"inherent":[14],"in":[15,218,224],"trial-and-error":[17],"mechanism.":[18],"To":[19],"tackle":[20],"this":[21],"challenge,":[22],"we":[23,54],"propose":[24],"a":[25,50,56,102,120,182,212],"physics-inspired":[26],"algorithm":[28,169],"called":[29],"relativistic":[30,88],"adaptive":[31,135,165],"gradient":[32,108,149],"descent":[33],"(RAD),":[34],"which":[35],"enhances":[36],"long-term":[37,61],"training":[38,45],"stability.":[39],"By":[40,86],"conceptualizing":[41],"neural":[42],"network":[43],"(NN)":[44],"as":[46,116,128,176,181],"evolution":[48,118],"of":[49,75,82,119],"conformal":[51,64],"Hamiltonian":[52],"system,":[53],"present":[55],"universal":[57],"framework":[58],"for":[59],"transferring":[60],"stability":[62],"from":[63,94],"symplectic":[65,179],"integrators":[66],"to":[67,156,162,211],"iterative":[68],"NN":[69,114],"updating":[70],"rules,":[71],"where":[72,123,147],"choice":[74],"kinetic":[76,89],"energy":[77],"governs":[78],"dynamical":[80],"properties":[81],"resulting":[83],"algorithms.":[85],"utilizing":[87],"energy,":[90],"RAD":[91,112,160,189,208],"incorporates":[92],"principles":[93],"special":[95],"relativity":[96],"and":[97,151,178,204,226],"limits":[98],"parameter":[99,126],"updates":[100],"below":[101],"finite":[103],"speed,":[104],"effectively":[105],"mitigating":[106],"abnormal":[107],"influences.":[109],"In":[110],"addition,":[111],"models":[113],"multiparticle":[121],"system":[122],"each":[124],"trainable":[125],"acts":[127],"an":[129,133],"independent":[130],"particle":[131],"with":[132,194],"individual":[134],"rate.":[137],"We":[138],"prove":[139],"RAD's":[140],"sublinear":[141],"convergence":[142],"under":[143],"general":[144],"settings,":[146],"smaller":[148],"variance":[150],"larger":[152],"batch":[153],"sizes":[154],"contribute":[155],"tighter":[157],"convergence.":[158],"Notably,":[159,207],"degrades":[161],"well-known":[164],"moment":[166],"estimation":[167],"(ADAM)":[168],"when":[170],"its":[171,222],"speed":[172],"coefficient":[173],"is":[174],"chosen":[175],"one":[177],"factor":[180],"small":[183],"positive":[184],"value.":[185],"Experimental":[186],"results":[187],"show":[188],"outperforming":[190],"nine":[191],"baseline":[192],"optimizers":[193],"five":[195],"RL":[196,228],"algorithms":[197],"across":[198],"twelve":[199],"environments,":[200],"including":[201],"standard":[202],"benchmarks":[203],"challenging":[205],"scenarios.":[206],"achieves":[209],"up":[210],"155.1%":[213],"performance":[214],"improvement":[215],"over":[216],"ADAM":[217],"Atari":[219],"games,":[220],"showcasing":[221],"efficacy":[223],"stabilizing":[225],"accelerating":[227],"training.":[229]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}