{"id":"https://openalex.org/W7220434736","doi":"https://doi.org/10.48550/arxiv.2610.03506","title":"Optimality of delayed reward attainment under uncertainty","display_name":"Optimality of delayed reward attainment under uncertainty","publication_year":2026,"publication_date":"2026-10-02","ids":{"openalex":"https://openalex.org/W7220434736","doi":"https://doi.org/10.48550/arxiv.2610.03506"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.03506","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.03506","pdf_url":"https://arxiv.org/pdf/2610.03506","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","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2610.03506","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5125213107","display_name":"Chuwei Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wang, Chuwei","raw_affiliation_strings":["Department of Mathematics , Cornell University , Ithaca , NY 14853 , USA","Sibley School of Mechanical and Aerospace Engineering , Cornell University , Ithaca , NY 14853 , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mathematics , Cornell University , Ithaca , NY 14853 , USA","institution_ids":["https://openalex.org/I205783295"]},{"raw_affiliation_string":"Sibley School of Mechanical and Aerospace Engineering , Cornell University , Ithaca , NY 14853 , USA","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028818054","display_name":"Alexander Vladimirsky","orcid":"https://orcid.org/0000-0003-4284-4546","observed_orcids":["https://orcid.org/0000-0003-4284-4546"]},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vladimirsky, Alexander","raw_affiliation_strings":["Sibley School of Mechanical and Aerospace Engineering , Cornell University , Ithaca , NY 14853 , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sibley School of Mechanical and Aerospace Engineering , Cornell University , Ithaca , NY 14853 , USA","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072253048","display_name":"Anastasia Bizyaeva","orcid":"https://orcid.org/0000-0003-0728-9655","observed_orcids":["https://orcid.org/0000-0003-0728-9655"]},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bizyaeva, Anastasia","raw_affiliation_strings":["Sibley School of Mechanical and Aerospace Engineering , Cornell University , Ithaca , NY 14853 , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sibley School of Mechanical and Aerospace Engineering , Cornell University , Ithaca , NY 14853 , USA","institution_ids":["https://openalex.org/I205783295"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I205783295"],"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":0.46459999680519104,"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":0.46459999680519104,"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":0.3596000075340271,"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/T12288","display_name":"Optimization and Search Problems","score":0.09769999980926514,"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/decision-making-under-uncertainty","display_name":"decision making under uncertainty","score":0.8569999933242798},{"id":"https://openalex.org/keywords/optimal-control","display_name":"optimal control","score":0.6710000038146973},{"id":"https://openalex.org/keywords/reward-learning","display_name":"reward learning","score":0.6639999747276306},{"id":"https://openalex.org/keywords/state-evolution","display_name":"state evolution","score":0.5180000066757202},{"id":"https://openalex.org/keywords/value-of-information","display_name":"value of information","score":0.7039999961853027},{"id":"https://openalex.org/keywords/embodied-decision-making","display_name":"embodied decision-making","score":0.5339999794960022},{"id":"https://openalex.org/keywords/planning-horizon","display_name":"planning horizon","score":0.5239999890327454},{"id":"https://openalex.org/keywords/observation-quality","display_name":"observation quality","score":0.3630000054836273},{"id":"https://openalex.org/keywords/animal-foraging","display_name":"animal foraging","score":0.5189999938011169}],"concepts":[{"id":"https://openalex.org/C92424840","wikidata":"https://www.wikidata.org/wiki/Q7912772","display_name":"Value of information","level":2,"score":0.5824000239372253},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5162000060081482},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5073999762535095},{"id":"https://openalex.org/C28761237","wikidata":"https://www.wikidata.org/wiki/Q7805321","display_name":"Time horizon","level":2,"score":0.5045999884605408},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.47510001063346863},{"id":"https://openalex.org/C150325174","wikidata":"https://www.wikidata.org/wiki/Q4335500","display_name":"Optimal decision","level":3,"score":0.47209998965263367},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.4706999957561493},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4277999997138977},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.42719998955726624},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.3962000012397766},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.38199999928474426},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.36970001459121704},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.36809998750686646},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.36000001430511475},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.33169999718666077},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.3312000036239624},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32359999418258667},{"id":"https://openalex.org/C84839998","wikidata":"https://www.wikidata.org/wiki/Q5249245","display_name":"Decision rule","level":2,"score":0.3181000053882599},{"id":"https://openalex.org/C2779351106","wikidata":"https://www.wikidata.org/wiki/Q24965456","display_name":"Decision quality","level":3,"score":0.31029999256134033},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.29350000619888306},{"id":"https://openalex.org/C115988155","wikidata":"https://www.wikidata.org/wiki/Q3262192","display_name":"Decision problem","level":2,"score":0.29319998621940613},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.2888999879360199},{"id":"https://openalex.org/C28901747","wikidata":"https://www.wikidata.org/wiki/Q177571","display_name":"Decision theory","level":2,"score":0.2879999876022339},{"id":"https://openalex.org/C2776035688","wikidata":"https://www.wikidata.org/wiki/Q1606558","display_name":"Affect (linguistics)","level":2,"score":0.2775999903678894},{"id":"https://openalex.org/C123676819","wikidata":"https://www.wikidata.org/wiki/Q1074338","display_name":"Perfect information","level":2,"score":0.27720001339912415},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.2766000032424927},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.27000001072883606},{"id":"https://openalex.org/C45983554","wikidata":"https://www.wikidata.org/wiki/Q3412851","display_name":"Information quality","level":3,"score":0.26350000500679016},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.25999999046325684},{"id":"https://openalex.org/C113336015","wikidata":"https://www.wikidata.org/wiki/Q574010","display_name":"Complete information","level":2,"score":0.2590999901294708},{"id":"https://openalex.org/C59594135","wikidata":"https://www.wikidata.org/wiki/Q5249242","display_name":"Decision model","level":2,"score":0.2587999999523163}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.03506","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.03506","pdf_url":"https://arxiv.org/pdf/2610.03506","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.2610.03506","doi":"https://doi.org/10.48550/arxiv.2610.03506","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.03506","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:2610.03506","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.03506","pdf_url":"https://arxiv.org/pdf/2610.03506","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":[{"id":"https://openalex.org/G4121837576","display_name":null,"funder_award_id":"FA9550- 22-1-0528","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"},{"id":"https://openalex.org/G4487006324","display_name":"Optimality and Robustness in Piecewise-Deterministic Systems","funder_award_id":"2111522","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320338279","display_name":"Air Force Office of Scientific Research","ror":"https://ror.org/011e9bt93"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7220434736.pdf","grobid_xml":"https://content.openalex.org/works/W7220434736.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2008136256","https://openalex.org/W2530417802","https://openalex.org/W2044175598","https://openalex.org/W2588821007","https://openalex.org/W3173185086","https://openalex.org/W4400275348","https://openalex.org/W4368408237","https://openalex.org/W3198958095","https://openalex.org/W3203259721","https://openalex.org/W2293900942"],"abstract_inverted_index":{"Decision":[0],"making":[1,217],"under":[2],"uncertainty":[3],"requires":[4],"balancing":[5],"the":[6,12,16,52,57,69,88,121,145,153,173,185,194,208,223],"value":[7,186],"of":[8,14,54,59,65,76,140,155,163],"additional":[9],"information":[10,20,55],"against":[11],"cost":[13,58,154],"delaying":[15],"decision":[17,70,89],"until":[18],"that":[19,130,170,179,198],"becomes":[21],"available.":[22],"This":[23],"challenge":[24],"is":[25,71,95,134,157,200],"especially":[26,142],"prevalent":[27],"for":[28,203],"embodied":[29],"decisions":[30],"such":[31],"as":[32,105],"those":[33,80],"faced":[34],"by":[35],"animals":[36],"moving":[37],"between":[38,98],"food":[39],"sources":[40],"and":[41,56,79,101,120,152,229],"robots":[42],"selecting":[43],"navigation":[44],"targets,":[45],"where":[46,68],"movement":[47],"through":[48,86,125],"space":[49],"shapes":[50],"both":[51],"quality":[53,191],"acting.":[60],"We":[61,128],"consider":[62],"a":[63,106,117,138,161,176,204,218],"version":[64],"this":[66],"problem,":[67],"on":[72,96,193],"choosing":[73],"among":[74],"rewards":[75,81],"uncertain":[77],"value,":[78],"can":[82],"only":[83],"be":[84],"attained":[85],"changing":[87],"maker's":[90],"state":[91,102,209],"sufficiently.":[92],"Our":[93],"focus":[94],"interactions":[97],"reward":[99,119,132],"learning":[100],"evolution,":[103],"restated":[104],"deterministic":[107],"optimal":[108,136,202],"control":[109],"problem":[110],"with":[111,116,222],"two":[112],"terminal":[113],"alternatives,":[114],"one":[115],"known":[118],"other":[122],"learned":[123],"gradually":[124],"noisy":[126],"observations.":[127],"demonstrate":[129],"delayed":[131],"attainment":[133],"often":[135,201],"in":[137,220,227],"variety":[139],"systems,":[141],"so":[143],"when":[144,189],"alternatives":[146],"are":[147],"initially":[148],"difficult":[149],"to":[150,206],"distinguish":[151],"waiting":[156],"relatively":[158],"low.":[159],"For":[160],"subset":[162],"problems,":[164],"we":[165,196],"also":[166],"derive":[167],"sufficient":[168],"conditions":[169],"allow":[171],"shortening":[172],"planning":[174],"horizon":[175],"priori,":[177],"guaranteeing":[178],"further":[180],"observations":[181],"would":[182],"not":[183],"affect":[184],"function.":[187],"Finally,":[188],"observation":[190],"depends":[192],"state,":[195],"show":[197],"it":[199],"controller":[205],"evolve":[207],"strategically":[210],"toward":[211],"more":[212],"informative":[213],"sensing":[214],"locations":[215],"before":[216],"decision,":[219],"line":[221],"behavior":[224],"broadly":[225],"observed":[226],"biological":[228],"engineered":[230],"systems.":[231]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-10-06T00:00:00"}