{"id":"https://openalex.org/W2551230555","doi":"https://doi.org/10.1109/allerton.2010.5707071","title":"Finite horizon Markov control with one-step variance penalties","display_name":"Finite horizon Markov control with one-step variance penalties","publication_year":2010,"publication_date":"2010-09-01","ids":{"openalex":"https://openalex.org/W2551230555","doi":"https://doi.org/10.1109/allerton.2010.5707071","mag":"2551230555"},"language":"en","primary_location":{"id":"doi:10.1109/allerton.2010.5707071","is_oa":false,"landing_page_url":"https://doi.org/10.1109/allerton.2010.5707071","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 48th Annual Allerton Conference on Communication, Control, and Computing (Allerton)","raw_type":"proceedings-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/A5053889549","display_name":"Abhijit Gosavi","orcid":"https://orcid.org/0000-0002-9703-4076"},"institutions":[{"id":"https://openalex.org/I20382870","display_name":"Missouri University of Science and Technology","ror":"https://ror.org/00scwqd12","country_code":"US","type":"education","lineage":["https://openalex.org/I20382870"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Abhijit Gosavi","raw_affiliation_strings":["Department of Engineering Management and Systems Engineering, Missouri University of Science and Technology, Rolla, MO, USA"],"affiliations":[{"raw_affiliation_string":"Department of Engineering Management and Systems Engineering, Missouri University of Science and Technology, Rolla, MO, USA","institution_ids":["https://openalex.org/I20382870"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5053889549"],"corresponding_institution_ids":["https://openalex.org/I20382870"],"apc_list":null,"apc_paid":null,"fwci":0.3561,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.68677008,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1355","last_page":"1359"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12288","display_name":"Optimization and Search Problems","score":0.9962000250816345,"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"}},"topics":[{"id":"https://openalex.org/T12288","display_name":"Optimization and Search Problems","score":0.9962000250816345,"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"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9948999881744385,"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.9936000108718872,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.6329838633537292},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.5905091762542725},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5705252885818481},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.4911768138408661},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4783691465854645},{"id":"https://openalex.org/keywords/horizon","display_name":"Horizon","score":0.4397605061531067},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4147307872772217},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.32984060049057007},{"id":"https://openalex.org/keywords/econometrics","display_name":"Econometrics","score":0.32357877492904663},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.2550365924835205},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1899261772632599},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.13836774230003357},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.13771015405654907},{"id":"https://openalex.org/keywords/accounting","display_name":"Accounting","score":0.06077820062637329}],"concepts":[{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.6329838633537292},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.5905091762542725},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5705252885818481},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.4911768138408661},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4783691465854645},{"id":"https://openalex.org/C159176650","wikidata":"https://www.wikidata.org/wiki/Q43261","display_name":"Horizon","level":2,"score":0.4397605061531067},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4147307872772217},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.32984060049057007},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.32357877492904663},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.2550365924835205},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1899261772632599},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.13836774230003357},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.13771015405654907},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.06077820062637329},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/allerton.2010.5707071","is_oa":false,"landing_page_url":"https://doi.org/10.1109/allerton.2010.5707071","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 48th Annual Allerton Conference on Communication, Control, and Computing (Allerton)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.7799999713897705,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1544291029","https://openalex.org/W1576452626","https://openalex.org/W1969027466","https://openalex.org/W1997856328","https://openalex.org/W2001908737","https://openalex.org/W2057510529","https://openalex.org/W2071983464","https://openalex.org/W2073126768","https://openalex.org/W2081287319","https://openalex.org/W2094364653","https://openalex.org/W2098432798","https://openalex.org/W2100857832","https://openalex.org/W2121494316","https://openalex.org/W2128661050","https://openalex.org/W2169927262","https://openalex.org/W2313791856","https://openalex.org/W3011120880","https://openalex.org/W6632525517","https://openalex.org/W6775686901","https://openalex.org/W6807091881"],"related_works":["https://openalex.org/W1660242800","https://openalex.org/W2077211377","https://openalex.org/W4233159725","https://openalex.org/W1006270037","https://openalex.org/W3152686072","https://openalex.org/W2379651310","https://openalex.org/W2113019827","https://openalex.org/W1541249122","https://openalex.org/W2413828414","https://openalex.org/W2367222340"],"abstract_inverted_index":{"Variance-penalized":[0],"Markov":[1],"decision":[2],"processes":[3],"(MDPs)":[4],"for":[5,16,64,89,128],"an":[6],"infinite":[7],"time":[8,51,78,95],"horizon":[9,96],"have":[10],"been":[11,56],"studied":[12],"in":[13,21,58,92,97,103,134],"the":[14,24,29,37,49,74,77,93,113,135,138],"literature":[15],"asymptotic":[17,53],"and":[18,120],"one-step":[19,90],"variance;":[20],"these":[22],"models,":[23],"objective":[25],"function":[26],"is":[27,41,71],"generally":[28],"expected":[30],"long-run":[31],"reward":[32,70],"minus":[33],"a":[34,44,66,87,108,125,129],"constant":[35],"times":[36],"variance,":[38],"where":[39],"variance":[40,54,91],"used":[42],"as":[43],"measure":[45],"of":[46,76,118,137],"risk.":[47],"For":[48],"finite":[50,94],"horizon,":[52],"has":[55],"considered":[57],"Collins,":[59],"but":[60],"this":[61,81],"model":[62],"accounts":[63],"only":[65],"terminal":[67],"reward,":[68],"i.e.,":[69],"earned":[72],"at":[73],"end":[75],"horizon.":[79],"In":[80],"paper,":[82],"we":[83],"seek":[84],"to":[85],"develop":[86,107],"framework":[88],"which":[98,132],"rewards":[99],"can":[100],"be":[101],"non-zero":[102],"every":[104],"state.":[105],"We":[106,122],"solution":[109],"algorithm":[110,117,127],"based":[111],"on":[112],"stochastic":[114],"shortest":[115],"path":[116],"Bertsekas":[119],"Tsitsiklis.":[121],"also":[123],"present":[124],"Q-Learning":[126],"simulation-based":[130],"scenario":[131],"applies":[133],"absence":[136],"transition":[139],"probability":[140],"model,":[141],"along":[142],"with":[143],"some":[144],"preliminary":[145],"convergence":[146],"results.":[147]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}