{"id":"https://openalex.org/W4416445890","doi":"https://doi.org/10.52202/085713-0856","title":"A Temporal Difference Method for Stochastic Continuous Dynamics","display_name":"A Temporal Difference Method for Stochastic Continuous Dynamics","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416445890","doi":"https://doi.org/10.52202/085713-0856"},"language":"en","primary_location":{"id":"doi:10.52202/085713-0856","doi":"https://doi.org/10.52202/085713-0856","is_oa":false,"landing_page_url":"https://doi.org/10.52202/085713-0856","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Neural Information Processing Systems 38","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2505.15544","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5120510228","display_name":"Haruki Settai","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Haruki Settai","raw_affiliation_strings":["The University of Tokyo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Tokyo","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064628313","display_name":"Naoya Takeishi","orcid":"https://orcid.org/0000-0003-0111-2269","observed_orcids":["https://orcid.org/0000-0003-0111-2269"]},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Naoya Takeishi","raw_affiliation_strings":["UTokyo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UTokyo","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113898040","display_name":"Takehisa Yairi","orcid":"https://orcid.org/0000-0003-2408-028X","observed_orcids":["https://orcid.org/0000-0003-2408-028X"]},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takehisa Yairi","raw_affiliation_strings":["The University of Tokyo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Tokyo","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":0.7133,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.71654306,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"28792","last_page":"28816"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9926999807357788,"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":0.9926999807357788,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.0071000000461936,"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/T11195","display_name":"Simulation Techniques and Applications","score":0.0,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"temporal difference learning","score":0.8420000076293945},{"id":"https://openalex.org/keywords/hamilton-jacobi-bellman-equation","display_name":"Hamilton-Jacobi-Bellman equation","score":0.9739999771118164},{"id":"https://openalex.org/keywords/model-free-reinforcement-learning","display_name":"model-free reinforcement learning","score":0.8769999742507935},{"id":"https://openalex.org/keywords/stochastic-differential-equations","display_name":"stochastic differential equations","score":0.8960000276565552},{"id":"https://openalex.org/keywords/ordinary-differential-equations","display_name":"ordinary differential equations","score":0.8870000243186951},{"id":"https://openalex.org/keywords/exponential-convergence","display_name":"exponential convergence","score":0.5720000267028809},{"id":"https://openalex.org/keywords/continuous-time-control","display_name":"continuous-time control","score":0.5040000081062317},{"id":"https://openalex.org/keywords/value-function-approximation","display_name":"value function approximation","score":0.6790000200271606}],"concepts":[{"id":"https://openalex.org/C196978813","wikidata":"https://www.wikidata.org/wiki/Q3302775","display_name":"Hamilton\u2013Jacobi\u2013Bellman equation","level":3,"score":0.6642000079154968},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6202999949455261},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.5896999835968018},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.5680999755859375},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.5669999718666077},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5590999722480774},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5426999926567078},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4675000011920929},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.45489999651908875},{"id":"https://openalex.org/C34862557","wikidata":"https://www.wikidata.org/wiki/Q178985","display_name":"Ode","level":2,"score":0.44679999351501465},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.4431999921798706},{"id":"https://openalex.org/C79379906","wikidata":"https://www.wikidata.org/wiki/Q3174497","display_name":"Dynamical systems theory","level":2,"score":0.415800005197525},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.4036000072956085},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.38659998774528503},{"id":"https://openalex.org/C151376022","wikidata":"https://www.wikidata.org/wiki/Q168698","display_name":"Exponential function","level":2,"score":0.38589999079704285},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3741999864578247},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.34630000591278076},{"id":"https://openalex.org/C77405623","wikidata":"https://www.wikidata.org/wiki/Q598451","display_name":"System dynamics","level":2,"score":0.3425999879837036},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.33410000801086426},{"id":"https://openalex.org/C170131372","wikidata":"https://www.wikidata.org/wiki/Q7617811","display_name":"Stochastic control","level":3,"score":0.3321000039577484},{"id":"https://openalex.org/C33962884","wikidata":"https://www.wikidata.org/wiki/Q378637","display_name":"Dynamical system (definition)","level":3,"score":0.32409998774528503},{"id":"https://openalex.org/C8272713","wikidata":"https://www.wikidata.org/wiki/Q176737","display_name":"Stochastic process","level":2,"score":0.29760000109672546},{"id":"https://openalex.org/C5917680","wikidata":"https://www.wikidata.org/wiki/Q2621825","display_name":"Basis function","level":2,"score":0.2879999876022339},{"id":"https://openalex.org/C57869625","wikidata":"https://www.wikidata.org/wiki/Q1783502","display_name":"Rate of convergence","level":3,"score":0.28540000319480896},{"id":"https://openalex.org/C60640748","wikidata":"https://www.wikidata.org/wiki/Q2337858","display_name":"Lyapunov function","level":3,"score":0.27090001106262207}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.52202/085713-0856","doi":"https://doi.org/10.52202/085713-0856","is_oa":false,"landing_page_url":"https://doi.org/10.52202/085713-0856","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Neural Information Processing Systems 38","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2505.15544","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.15544","pdf_url":"https://arxiv.org/pdf/2505.15544","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2505.15544","doi":"https://doi.org/10.48550/arxiv.2505.15544","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2505.15544","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2505.15544","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.15544","pdf_url":"https://arxiv.org/pdf/2505.15544","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416445890.pdf","grobid_xml":"https://content.openalex.org/works/W4416445890.grobid-xml"},"referenced_works_count":3,"referenced_works":["https://openalex.org/W2736601468","https://openalex.org/W2902907165","https://openalex.org/W2992977009"],"related_works":["https://openalex.org/W2166356462","https://openalex.org/W4416138633","https://openalex.org/W7099616101","https://openalex.org/W4300463344","https://openalex.org/W4283323179","https://openalex.org/W7215032931","https://openalex.org/W7204656145","https://openalex.org/W2130746277","https://openalex.org/W2113501460","https://openalex.org/W4381059439"],"abstract_inverted_index":{"For":[0],"continuous":[1],"systems":[2],"modeled":[3],"by":[4],"dynamical":[5,64],"equations":[6,65],"such":[7],"as":[8],"ODEs":[9],"and":[10,93,109,128],"SDEs,":[11],"Bellman's":[12],"Principle":[13],"of":[14,19,29,63,80,104],"Optimality":[15],"takes":[16],"the":[17,20,26,42,47,60,68,72,90,95,105,122],"form":[18],"Hamilton-Jacobi-Bellman":[21],"(HJB)":[22],"equation,":[23],"which":[24],"provides":[25],"theoretical":[27],"target":[28],"reinforcement":[30,130],"learning":[31],"(RL).":[32],"Although":[33],"recent":[34],"advances":[35],"in":[36],"RL":[37],"successfully":[38],"leverage":[39],"this":[40,77],"formulation,":[41],"existing":[43],"methods":[44],"typically":[45],"assume":[46],"underlying":[48],"dynamics":[49,108],"are":[50],"known":[51],"a":[52,85],"priori":[53],"because":[54],"they":[55],"need":[56],"explicit":[57],"access":[58],"to":[59,66],"coefficient":[61],"functions":[62],"update":[67],"value":[69],"function":[70],"following":[71],"HJB":[73,91],"equation.":[74],"We":[75,100],"address":[76],"inherent":[78],"limitation":[79],"HJB-based":[81],"RL;":[82],"we":[83],"propose":[84,94],"model-free":[86,129],"approach":[87],"still":[88],"targeting":[89],"equation":[92],"corresponding":[96],"temporal":[97],"difference":[98],"method.":[99],"establish":[101],"exponential":[102],"convergence":[103],"idealized":[106],"continuous-time":[107],"empirically":[110],"demonstrate":[111],"its":[112],"potential":[113],"advantages":[114],"over":[115],"transition-kernel-based":[116],"formulations.":[117],"The":[118],"proposed":[119],"formulation":[120],"paves":[121],"way":[123],"toward":[124],"bridging":[125],"stochastic":[126],"control":[127],"learning.":[131]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2025-10-10T00:00:00"}