{"id":"https://openalex.org/W2035357342","doi":"https://doi.org/10.1109/cdc.2012.6426037","title":"Parameterized penalties in the dual representation of Markov decision processes","display_name":"Parameterized penalties in the dual representation of Markov decision processes","publication_year":2012,"publication_date":"2012-12-01","ids":{"openalex":"https://openalex.org/W2035357342","doi":"https://doi.org/10.1109/cdc.2012.6426037","mag":"2035357342"},"language":"en","primary_location":{"id":"doi:10.1109/cdc.2012.6426037","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc.2012.6426037","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE 51st IEEE Conference on Decision and Control (CDC)","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/A5100850825","display_name":"Fan Ye","orcid":"https://orcid.org/0009-0008-1978-661X"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fan Ye","raw_affiliation_strings":["Department of Industrial & Enterprise Systems Engineering, University of Illinois at Urbana-Champaign","Department of Industrial & Enterprise Systems Engineering, University of Illinois at Urbana-Champaign, 61801 USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Industrial & Enterprise Systems Engineering, University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"Department of Industrial & Enterprise Systems Engineering, University of Illinois at Urbana-Champaign, 61801 USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083807807","display_name":"Enlu Zhou","orcid":"https://orcid.org/0000-0001-5399-6508"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Enlu Zhou","raw_affiliation_strings":["Department of Industrial & Enterprise Systems Engineering, University of Illinois at Urbana-Champaign","Department of Industrial & Enterprise Systems Engineering, University of Illinois at Urbana-Champaign, 61801 USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Industrial & Enterprise Systems Engineering, University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"Department of Industrial & Enterprise Systems Engineering, University of Illinois at Urbana-Champaign, 61801 USA","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":8.4289,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.9687309,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"19","issue":null,"first_page":"870","last_page":"876"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10780","display_name":"Reliability and Maintenance Optimization","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/2213","display_name":"Safety, Risk, Reliability and Quality"},"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/T10780","display_name":"Reliability and Maintenance Optimization","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/2213","display_name":"Safety, Risk, Reliability and Quality"},"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.9911999702453613,"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/T10876","display_name":"Fault Detection and Control Systems","score":0.9890000224113464,"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/parameterized-complexity","display_name":"Parameterized complexity","score":0.8871146440505981},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.7595279216766357},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7312349677085876},{"id":"https://openalex.org/keywords/complement","display_name":"Complement (music)","score":0.7239257097244263},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6563190817832947},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.6389675140380859},{"id":"https://openalex.org/keywords/duality","display_name":"Duality (order theory)","score":0.6303730010986328},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5992469787597656},{"id":"https://openalex.org/keywords/dual-representation","display_name":"Dual representation","score":0.5890013575553894},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.5692756175994873},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.4641507863998413},{"id":"https://openalex.org/keywords/duality-gap","display_name":"Duality gap","score":0.4598781168460846},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.45766523480415344},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.295352965593338},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.24297243356704712},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.16723617911338806},{"id":"https://openalex.org/keywords/optimization-problem","display_name":"Optimization problem","score":0.16503199934959412},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.15635833144187927},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.11564803123474121}],"concepts":[{"id":"https://openalex.org/C165464430","wikidata":"https://www.wikidata.org/wiki/Q1570441","display_name":"Parameterized complexity","level":2,"score":0.8871146440505981},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.7595279216766357},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7312349677085876},{"id":"https://openalex.org/C112313634","wikidata":"https://www.wikidata.org/wiki/Q7886648","display_name":"Complement (music)","level":5,"score":0.7239257097244263},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6563190817832947},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.6389675140380859},{"id":"https://openalex.org/C2778023678","wikidata":"https://www.wikidata.org/wiki/Q554403","display_name":"Duality (order theory)","level":2,"score":0.6303730010986328},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5992469787597656},{"id":"https://openalex.org/C84750791","wikidata":"https://www.wikidata.org/wiki/Q3427408","display_name":"Dual representation","level":3,"score":0.5890013575553894},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5692756175994873},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.4641507863998413},{"id":"https://openalex.org/C5274546","wikidata":"https://www.wikidata.org/wiki/Q5310264","display_name":"Duality gap","level":3,"score":0.4598781168460846},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.45766523480415344},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.295352965593338},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.24297243356704712},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.16723617911338806},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.16503199934959412},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.15635833144187927},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.11564803123474121},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C127716648","wikidata":"https://www.wikidata.org/wiki/Q104053","display_name":"Phenotype","level":3,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C188082640","wikidata":"https://www.wikidata.org/wiki/Q1780899","display_name":"Complementation","level":4,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc.2012.6426037","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc.2012.6426037","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE 51st IEEE Conference on Decision and Control (CDC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.8100000023841858,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1499021337","https://openalex.org/W1576707917","https://openalex.org/W1601081659","https://openalex.org/W1602773783","https://openalex.org/W1832379062","https://openalex.org/W2048166500","https://openalex.org/W2081882419","https://openalex.org/W2098432798","https://openalex.org/W2100857832","https://openalex.org/W2137824542","https://openalex.org/W2144787803","https://openalex.org/W2148908587","https://openalex.org/W2151786492","https://openalex.org/W2156040550","https://openalex.org/W2542637644","https://openalex.org/W2734870733","https://openalex.org/W3122113998","https://openalex.org/W3124696154","https://openalex.org/W6741320478"],"related_works":["https://openalex.org/W2593555778","https://openalex.org/W2201555914","https://openalex.org/W2121876331","https://openalex.org/W2725387418","https://openalex.org/W2614523486","https://openalex.org/W640885572","https://openalex.org/W4220928172","https://openalex.org/W2089739134","https://openalex.org/W228544604","https://openalex.org/W2049472152"],"abstract_inverted_index":{"Duality":[0],"in":[1,36,71,99],"Markov":[2],"decision":[3],"processes":[4],"(MDPs)":[5],"has":[6],"been":[7],"studied":[8],"recently":[9],"by":[10,135],"several":[11],"researchers":[12],"with":[13,58],"the":[14,21,29,37,66,72,128,131,143],"goal":[15],"to":[16,45,97,117],"derive":[17],"dual":[18,38,56,120,132],"bounds":[19,121,133],"on":[20,102,138],"value":[22],"function.":[23],"In":[24],"this":[25,103],"paper":[26],"we":[27,74],"propose":[28],"idea":[30],"of":[31,40,49,80,91,106,110,130,145],"using":[32],"parameterized":[33,111],"penalty":[34,50],"functions":[35,51],"representation":[39],"MDPs,":[41],"which":[42],"allows":[43],"us":[44],"integrate":[46],"different":[47,136],"types":[48],"and":[52,64,93],"guarantees":[53],"a":[54,77,88,114,139],"tighter":[55,119],"bound":[57],"more":[59],"penalties":[60,69,82,112,137],"used.":[61],"To":[62],"complement":[63],"diversify":[65],"existing":[67,123],"linear":[68],"developed":[70],"literature,":[73],"also":[75,95],"introduce":[76],"new":[78,104],"class":[79,90,105],"nonlinear":[81],"that":[83],"can":[84],"be":[85],"used":[86],"for":[87],"broad":[89],"problems":[92],"are":[94],"easy":[96],"implement":[98],"practice.":[100],"Based":[101],"penalties,":[107],"our":[108,146],"framework":[109],"is":[113],"promising":[115],"method":[116],"produce":[118],"than":[122],"duality-based":[124],"methods.":[125],"We":[126],"compare":[127],"performance":[129],"induced":[134],"numerical":[140],"example,":[141],"demonstrating":[142],"effectiveness":[144],"method.":[147]},"counts_by_year":[{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":5}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}
