{"id":"https://openalex.org/W7220917346","doi":"https://doi.org/10.48550/arxiv.2610.09712","title":"Boundary-aware Reinforcement Learning for Hypercube State Spaces via Deterministic Policy Gradient","display_name":"Boundary-aware Reinforcement Learning for Hypercube State Spaces via Deterministic Policy Gradient","publication_year":2026,"publication_date":"2026-10-07","ids":{"openalex":"https://openalex.org/W7220917346","doi":"https://doi.org/10.48550/arxiv.2610.09712"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.09712","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.09712","pdf_url":"https://arxiv.org/pdf/2610.09712","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2610.09712","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5056831910","display_name":"Lijun Bo","orcid":"https://orcid.org/0000-0003-4914-6150","observed_orcids":["https://orcid.org/0000-0003-4914-6150"]},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo, Lijun","raw_affiliation_strings":["School of Mathematics and Statistics , Xidian University , Xi'an , 710126 , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Mathematics and Statistics , Xidian University , Xi'an , 710126 , China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5157909644","display_name":"Yijie Huang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Yijie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5157966994","display_name":"Chenhao Lu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lu, Chenhao","raw_affiliation_strings":["School of Mathematics and Statistics , Xidian University , Xi'an , 710126 , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Mathematics and Statistics , Xidian University , Xi'an , 710126 , China","institution_ids":["https://openalex.org/I149594827"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9125999808311462,"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":0.9125999808311462,"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":0.08089999854564667,"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/T10067","display_name":"Stochastic processes and financial applications","score":0.0027000000700354576,"subfield":{"id":"https://openalex.org/subfields/2003","display_name":"Finance"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/deterministic-policy-gradient","display_name":"deterministic policy gradient","score":0.8069999814033508},{"id":"https://openalex.org/keywords/reflected-stochastic-differential-equations","display_name":"reflected stochastic differential equations","score":0.8920000195503235},{"id":"https://openalex.org/keywords/neumann-boundary-conditions","display_name":"Neumann boundary conditions","score":0.859000027179718},{"id":"https://openalex.org/keywords/martingale-characterization","display_name":"martingale characterization","score":0.7940000295639038},{"id":"https://openalex.org/keywords/reservoir-operation","display_name":"reservoir operation","score":0.8289999961853027},{"id":"https://openalex.org/keywords/discretization-error","display_name":"discretization error","score":0.5680000185966492},{"id":"https://openalex.org/keywords/exploration-noise","display_name":"exploration noise","score":0.6570000052452087}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7910000085830688},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.5659999847412109},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4934999942779541},{"id":"https://openalex.org/C163681178","wikidata":"https://www.wikidata.org/wiki/Q1149279","display_name":"Neumann boundary condition","level":3,"score":0.4683000147342682},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.42419999837875366},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.4196999967098236},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4162999987602234},{"id":"https://openalex.org/C80469333","wikidata":"https://www.wikidata.org/wiki/Q189088","display_name":"Von Neumann architecture","level":2,"score":0.391400009393692},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3865000009536743},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.3840000033378601},{"id":"https://openalex.org/C182310444","wikidata":"https://www.wikidata.org/wiki/Q1332643","display_name":"Boundary value problem","level":2,"score":0.3698999881744385},{"id":"https://openalex.org/C48406656","wikidata":"https://www.wikidata.org/wiki/Q534112","display_name":"Martingale (probability theory)","level":2,"score":0.35199999809265137},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.34360000491142273},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.3418999910354614},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.33970001339912415},{"id":"https://openalex.org/C2776639384","wikidata":"https://www.wikidata.org/wiki/Q840396","display_name":"Ideal (ethics)","level":2,"score":0.3319000005722046},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.32170000672340393},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.3095000088214874},{"id":"https://openalex.org/C13355873","wikidata":"https://www.wikidata.org/wiki/Q2920850","display_name":"Connection (principal bundle)","level":2,"score":0.28529998660087585},{"id":"https://openalex.org/C50820777","wikidata":"https://www.wikidata.org/wiki/Q213723","display_name":"Hypercube","level":2,"score":0.2849000096321106},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.28200000524520874},{"id":"https://openalex.org/C51955184","wikidata":"https://www.wikidata.org/wiki/Q1545585","display_name":"Stochastic differential equation","level":2,"score":0.27549999952316284},{"id":"https://openalex.org/C115680565","wikidata":"https://www.wikidata.org/wiki/Q5977448","display_name":"Gradient method","level":2,"score":0.2754000127315521},{"id":"https://openalex.org/C93779851","wikidata":"https://www.wikidata.org/wiki/Q271977","display_name":"Partial differential equation","level":2,"score":0.2734000086784363},{"id":"https://openalex.org/C129537906","wikidata":"https://www.wikidata.org/wiki/Q7603913","display_name":"State variable","level":2,"score":0.2648000121116638},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.26409998536109924},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.25850000977516174},{"id":"https://openalex.org/C8272713","wikidata":"https://www.wikidata.org/wiki/Q176737","display_name":"Stochastic process","level":2,"score":0.25519999861717224}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.09712","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.09712","pdf_url":"https://arxiv.org/pdf/2610.09712","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2610.09712","doi":"https://doi.org/10.48550/arxiv.2610.09712","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.09712","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2610.09712","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.09712","pdf_url":"https://arxiv.org/pdf/2610.09712","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":null,"license_id":null,"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/W7220917346.pdf","grobid_xml":"https://content.openalex.org/works/W7220917346.grobid-xml"},"referenced_works_count":7,"referenced_works":["https://openalex.org/W4400434133","https://openalex.org/W4400434804","https://openalex.org/W4415332651","https://openalex.org/W7159626559","https://openalex.org/W7159650847","https://openalex.org/W7164316200","https://openalex.org/W7168277454"],"related_works":["https://openalex.org/W4415332651","https://openalex.org/W7215032931","https://openalex.org/W7099616101","https://openalex.org/W7163534244","https://openalex.org/W2113501460","https://openalex.org/W4416138633","https://openalex.org/W2166356462","https://openalex.org/W2142377262","https://openalex.org/W6922036200","https://openalex.org/W2146979682"],"abstract_inverted_index":{"We":[0,99],"develop":[1],"a":[2,22,29,54,72],"continuous-time":[3,73,107],"deterministic":[4,55,75],"policy":[5,56,76],"gradient":[6,57,77],"framework":[7],"for":[8,79],"reinforcement":[9],"learning":[10,157],"with":[11],"reflected":[12,24,80],"state":[13,17],"dynamics,":[14],"where":[15],"the":[16,37,40,44,61,85,102,105,110,120,124,140,143],"process":[18],"is":[19,89,127],"governed":[20],"by":[21,66],"controlled":[23],"stochastic":[25,81],"differential":[26],"equation":[27],"on":[28,135],"hypercube.":[30],"Under":[31],"suitable":[32],"regularity":[33],"assumptions,":[34],"we":[35,70],"establish":[36],"connection":[38],"between":[39,104],"value":[41],"function":[42,51],"and":[43,59,109,129,155],"Neumann":[45,86,152],"Bellman":[46],"equation,":[47],"introduce":[48],"an":[49],"advantage-rate":[50],"that":[52,119,147],"yields":[53],"formula,":[58],"prove":[60],"martingale":[62],"characterization":[63],"theorem.":[64],"Motivated":[65],"these":[67],"theoretical":[68],"results,":[69],"propose":[71],"deep":[74],"algorithm":[78],"systems,":[82],"in":[83,116],"which":[84],"boundary":[87,153],"condition":[88],"imposed":[90],"via":[91],"either":[92],"soft":[93],"penalization":[94],"or":[95],"hard":[96],"architectural":[97],"constraint.":[98],"further":[100],"quantify":[101],"discrepancy":[103],"ideal":[106],"dynamics":[108,114],"discretely":[111],"sampled":[112],"exploratory":[113],"executed":[115],"practice,":[117],"showing":[118],"error":[121],"decays":[122],"as":[123],"time":[125],"grid":[126],"refined":[128],"exploration":[130],"noise":[131],"vanishes.":[132],"Our":[133],"experiments":[134],"reservoir":[136],"control":[137],"problems":[138],"illustrate":[139],"effectiveness":[141],"of":[142],"RL":[144],"framework,":[145],"highlighting":[146],"boundary-aware":[148],"methods":[149],"substantially":[150],"reduce":[151],"residuals":[154],"enhance":[156],"stability.":[158]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-10-09T00:00:00"}