{"id":"https://openalex.org/W4289927812","doi":"https://doi.org/10.23919/ecc55457.2022.9838064","title":"Functional Stability of Discounted Markov Decision Processes Using Economic MPC Dissipativity Theory","display_name":"Functional Stability of Discounted Markov Decision Processes Using Economic MPC Dissipativity Theory","publication_year":2022,"publication_date":"2022-07-12","ids":{"openalex":"https://openalex.org/W4289927812","doi":"https://doi.org/10.23919/ecc55457.2022.9838064"},"language":"en","primary_location":{"id":"doi:10.23919/ecc55457.2022.9838064","is_oa":false,"landing_page_url":"https://doi.org/10.23919/ecc55457.2022.9838064","pdf_url":null,"source":{"id":"https://openalex.org/S4363607908","display_name":"2022 European Control Conference (ECC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"2022 European Control Conference (ECC)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5033874726","display_name":"Arash Bahari Kordabad","orcid":"https://orcid.org/0000-0001-8931-5372"},"institutions":[{"id":"https://openalex.org/I204778367","display_name":"Norwegian University of Science and Technology","ror":"https://ror.org/05xg72x27","country_code":"NO","type":"education","lineage":["https://openalex.org/I204778367"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Arash Bahari Kordabad","raw_affiliation_strings":["Norwegian University of Science and Technology (NTNU),Department of Engineering Cybernetics,Trondheim,Norway","Department of Engineering Cybernetics, Norwegian University of Science and Technology (NTNU), Trondheim, Norway"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Norwegian University of Science and Technology (NTNU),Department of Engineering Cybernetics,Trondheim,Norway","institution_ids":["https://openalex.org/I204778367"]},{"raw_affiliation_string":"Department of Engineering Cybernetics, Norwegian University of Science and Technology (NTNU), Trondheim, Norway","institution_ids":["https://openalex.org/I204778367"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049645185","display_name":"S\u00e9bastien Gros","orcid":"https://orcid.org/0000-0001-6054-2133"},"institutions":[{"id":"https://openalex.org/I204778367","display_name":"Norwegian University of Science and Technology","ror":"https://ror.org/05xg72x27","country_code":"NO","type":"education","lineage":["https://openalex.org/I204778367"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Sebastien Gros","raw_affiliation_strings":["Norwegian University of Science and Technology (NTNU),Department of Engineering Cybernetics,Trondheim,Norway","Department of Engineering Cybernetics, Norwegian University of Science and Technology (NTNU), Trondheim, Norway"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Norwegian University of Science and Technology (NTNU),Department of Engineering Cybernetics,Trondheim,Norway","institution_ids":["https://openalex.org/I204778367"]},{"raw_affiliation_string":"Department of Engineering Cybernetics, Norwegian University of Science and Technology (NTNU), Trondheim, Norway","institution_ids":["https://openalex.org/I204778367"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I204778367"],"apc_list":null,"apc_paid":null,"fwci":0.8849,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.66503167,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1858","last_page":"1863"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.9997000098228455,"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"}},"topics":[{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.9997000098228455,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9923999905586243,"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/T10932","display_name":"Microbial Metabolic Engineering and Bioproduction","score":0.9261999726295471,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.7407013177871704},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.730357825756073},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.6079896092414856},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5987471342086792},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.5482323169708252},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.5329505205154419},{"id":"https://openalex.org/keywords/model-predictive-control","display_name":"Model predictive control","score":0.5097343325614929},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.48126667737960815},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.4804063141345978},{"id":"https://openalex.org/keywords/markov-kernel","display_name":"Markov kernel","score":0.4391464293003082},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.42718505859375},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.4197048544883728},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.3982386887073517},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.37364503741264343},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.35845524072647095},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.32713404297828674},{"id":"https://openalex.org/keywords/variable-order-markov-model","display_name":"Variable-order Markov model","score":0.2209472358226776},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.09439826011657715},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.08892059326171875}],"concepts":[{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.7407013177871704},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.730357825756073},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.6079896092414856},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5987471342086792},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.5482323169708252},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5329505205154419},{"id":"https://openalex.org/C172205157","wikidata":"https://www.wikidata.org/wiki/Q1782962","display_name":"Model predictive control","level":3,"score":0.5097343325614929},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.48126667737960815},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.4804063141345978},{"id":"https://openalex.org/C106666656","wikidata":"https://www.wikidata.org/wiki/Q6771323","display_name":"Markov kernel","level":5,"score":0.4391464293003082},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.42718505859375},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.4197048544883728},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.3982386887073517},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.37364503741264343},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.35845524072647095},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.32713404297828674},{"id":"https://openalex.org/C54907487","wikidata":"https://www.wikidata.org/wiki/Q7915688","display_name":"Variable-order Markov model","level":4,"score":0.2209472358226776},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.09439826011657715},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.08892059326171875},{"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:10.23919/ecc55457.2022.9838064","is_oa":false,"landing_page_url":"https://doi.org/10.23919/ecc55457.2022.9838064","pdf_url":null,"source":{"id":"https://openalex.org/S4363607908","display_name":"2022 European Control Conference (ECC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"2022 European Control Conference (ECC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.5799999833106995,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320323299","display_name":"Norges Forskningsr\u00e5d","ror":"https://ror.org/00epmv149"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W2026216293","https://openalex.org/W2145339207","https://openalex.org/W2169957008","https://openalex.org/W2529970964","https://openalex.org/W2930426397","https://openalex.org/W2948652605","https://openalex.org/W3128368486","https://openalex.org/W3155270812","https://openalex.org/W3165125266","https://openalex.org/W3169649074","https://openalex.org/W3185747626","https://openalex.org/W4285446252","https://openalex.org/W4298023569","https://openalex.org/W4301753813","https://openalex.org/W6763565325","https://openalex.org/W6790627760","https://openalex.org/W6794518998","https://openalex.org/W6796178508","https://openalex.org/W7065191921"],"related_works":["https://openalex.org/W2152670157","https://openalex.org/W2386410636","https://openalex.org/W176737593","https://openalex.org/W2808418668","https://openalex.org/W2903299703","https://openalex.org/W2016648086","https://openalex.org/W3105579180","https://openalex.org/W2156021013","https://openalex.org/W4399157305","https://openalex.org/W2807018115"],"abstract_inverted_index":{"This":[0,58],"paper":[1],"discusses":[2],"the":[3,26,31,38,43,55,70,76,85,111],"functional":[4],"stability":[5,27],"of":[6,28,33,46],"closed-loop":[7],"Markov":[8,20],"Chains":[9],"under":[10],"optimal":[11,92],"policies":[12],"resulting":[13],"from":[14],"a":[15,61,66],"discounted":[16,77],"optimality":[17],"criterion,":[18],"forming":[19],"Decision":[21],"Processes":[22],"(MDPs).":[23],"We":[24,88],"investigate":[25],"MDPs":[29],"in":[30,51,95],"sense":[32],"probability":[34,71],"measures":[35,72],"(densities)":[36],"underlying":[37],"state":[39],"distributions":[40],"and":[41,74],"extend":[42],"dissipativity":[44,67,82],"theory":[45,59],"Economic":[47],"Model":[48],"Predictive":[49],"Control":[50],"order":[52,96],"to":[53,97,106,109],"characterize":[54],"MDP":[56,86],"stability.":[57,87],"requires":[60],"so-called":[62],"storage":[63,100,112],"function":[64],"satisfying":[65],"inequality.":[68],"In":[69,102],"space":[73],"for":[75],"setting,":[78],"we":[79,104],"introduce":[80],"new":[81],"conditions":[83],"ensuring":[84],"then":[89],"use":[90,107],"finite-horizon":[91],"control":[93],"problems":[94],"generate":[98],"valid":[99],"functionals.":[101,113],"practice,":[103],"propose":[105],"Q-learning":[108],"compute":[110]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}