{"id":"https://openalex.org/W2031259314","doi":"https://doi.org/10.1109/cdc.2012.6426485","title":"The complexity of Policy Iteration is exponential for discounted Markov Decision Processes","display_name":"The complexity of Policy Iteration is exponential for discounted Markov Decision Processes","publication_year":2012,"publication_date":"2012-12-01","ids":{"openalex":"https://openalex.org/W2031259314","doi":"https://doi.org/10.1109/cdc.2012.6426485","mag":"2031259314"},"language":"en","primary_location":{"id":"doi:10.1109/cdc.2012.6426485","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc.2012.6426485","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":"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/A5050191936","display_name":"Romain Hollanders","orcid":null},"institutions":[{"id":"https://openalex.org/I95674353","display_name":"UCLouvain","ror":"https://ror.org/02495e989","country_code":"BE","type":"education","lineage":["https://openalex.org/I95674353"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Romain Hollanders","raw_affiliation_strings":["Department of Mathematical Engineering and ICTEAM, Universite catholique de Louvain, Louvain-la-Neuve, Belgium","Department of Mathematical Engineering at UCLouvain, 4, avenue G. Lemaitre, B-1348 Louvain-la-Neuve, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mathematical Engineering and ICTEAM, Universite catholique de Louvain, Louvain-la-Neuve, Belgium","institution_ids":["https://openalex.org/I95674353"]},{"raw_affiliation_string":"Department of Mathematical Engineering at UCLouvain, 4, avenue G. Lemaitre, B-1348 Louvain-la-Neuve, Belgium","institution_ids":["https://openalex.org/I95674353"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006354562","display_name":"Jean\u2010Charles Delvenne","orcid":"https://orcid.org/0000-0003-2356-7790"},"institutions":[{"id":"https://openalex.org/I95674353","display_name":"UCLouvain","ror":"https://ror.org/02495e989","country_code":"BE","type":"education","lineage":["https://openalex.org/I95674353"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Jean-Charles Delvenne","raw_affiliation_strings":["Department of Mathematical Engineering and ICTEAM, Universite catholique de Louvain, Louvain-la-Neuve, Belgium","Department of Mathematical Engineering at UCLouvain, 4, avenue G. Lemaitre, B-1348 Louvain-la-Neuve, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mathematical Engineering and ICTEAM, Universite catholique de Louvain, Louvain-la-Neuve, Belgium","institution_ids":["https://openalex.org/I95674353"]},{"raw_affiliation_string":"Department of Mathematical Engineering at UCLouvain, 4, avenue G. Lemaitre, B-1348 Louvain-la-Neuve, Belgium","institution_ids":["https://openalex.org/I95674353"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056625594","display_name":"Rapha\u00ebl M. Jungers","orcid":"https://orcid.org/0000-0002-7789-0940"},"institutions":[{"id":"https://openalex.org/I95674353","display_name":"UCLouvain","ror":"https://ror.org/02495e989","country_code":"BE","type":"education","lineage":["https://openalex.org/I95674353"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Raphael M. Jungers","raw_affiliation_strings":["Department of Mathematical Engineering and ICTEAM, Universite catholique de Louvain, Louvain-la-Neuve, Belgium","Department of Mathematical Engineering at UCLouvain, 4, avenue G. Lemaitre, B-1348 Louvain-la-Neuve, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mathematical Engineering and ICTEAM, Universite catholique de Louvain, Louvain-la-Neuve, Belgium","institution_ids":["https://openalex.org/I95674353"]},{"raw_affiliation_string":"Department of Mathematical Engineering at UCLouvain, 4, avenue G. Lemaitre, B-1348 Louvain-la-Neuve, Belgium","institution_ids":["https://openalex.org/I95674353"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I95674353"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5997","last_page":"6002"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9987999796867371,"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":0.9987999796867371,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9731000065803528,"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/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.9715999960899353,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7560780048370361},{"id":"https://openalex.org/keywords/exponential-function","display_name":"Exponential function","score":0.7123060822486877},{"id":"https://openalex.org/keywords/discounting","display_name":"Discounting","score":0.6250338554382324},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5860088467597961},{"id":"https://openalex.org/keywords/polynomial","display_name":"Polynomial","score":0.5205013155937195},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.5133794546127319},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.49531617760658264},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.4871825575828552},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.44902101159095764},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.4314529299736023},{"id":"https://openalex.org/keywords/mathematical-economics","display_name":"Mathematical economics","score":0.3316255807876587},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.17507022619247437},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.08324569463729858},{"id":"https://openalex.org/keywords/finance","display_name":"Finance","score":0.06830665469169617}],"concepts":[{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7560780048370361},{"id":"https://openalex.org/C151376022","wikidata":"https://www.wikidata.org/wiki/Q168698","display_name":"Exponential function","level":2,"score":0.7123060822486877},{"id":"https://openalex.org/C6177178","wikidata":"https://www.wikidata.org/wiki/Q10998070","display_name":"Discounting","level":2,"score":0.6250338554382324},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5860088467597961},{"id":"https://openalex.org/C90119067","wikidata":"https://www.wikidata.org/wiki/Q43260","display_name":"Polynomial","level":2,"score":0.5205013155937195},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5133794546127319},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.49531617760658264},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.4871825575828552},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.44902101159095764},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.4314529299736023},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.3316255807876587},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.17507022619247437},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.08324569463729858},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.06830665469169617},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc.2012.6426485","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc.2012.6426485","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":[{"score":0.7200000286102295,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1494380152","https://openalex.org/W1502195915","https://openalex.org/W1522772123","https://openalex.org/W1543756640","https://openalex.org/W1819827759","https://openalex.org/W1928484725","https://openalex.org/W1978942630","https://openalex.org/W1984901446","https://openalex.org/W1995696058","https://openalex.org/W2020804487","https://openalex.org/W2026950860","https://openalex.org/W2034053794","https://openalex.org/W2068014951","https://openalex.org/W2081287319","https://openalex.org/W2090502364","https://openalex.org/W2098432798","https://openalex.org/W2101521346","https://openalex.org/W2141076336","https://openalex.org/W2141252092","https://openalex.org/W2334782222","https://openalex.org/W3022909171","https://openalex.org/W3102056532","https://openalex.org/W4301242114","https://openalex.org/W6629437211"],"related_works":["https://openalex.org/W2348852664","https://openalex.org/W4311335936","https://openalex.org/W2379651310","https://openalex.org/W2113019827","https://openalex.org/W1541249122","https://openalex.org/W2413828414","https://openalex.org/W2367222340","https://openalex.org/W187740018","https://openalex.org/W2162286586","https://openalex.org/W4255368532"],"abstract_inverted_index":{"The":[0],"question":[1],"of":[2,35,44,94],"knowing":[3],"whether":[4],"the":[5,28,51,54,58,77],"Policy":[6],"Iteration":[7],"algorithm":[8],"(PI)":[9],"for":[10,50],"solving":[11],"stationary":[12],"Markov":[13],"Decision":[14],"Processes":[15],"(MDPs)":[16],"has":[17,23],"exponential":[18,42,92],"or":[19],"(strongly)":[20],"polynomial":[21,69],"complexity":[22],"attracted":[24],"much":[25],"attention":[26],"in":[27,67],"last":[29],"25":[30],"years.":[31],"Recently,":[32],"a":[33,102],"family":[34],"examples":[36],"on":[37,71,98],"which":[38],"PI":[39,65,89],"requires":[40],"an":[41,91],"number":[43,93],"iterations":[45],"to":[46,96],"converge":[47,97],"was":[48,62],"proposed":[49],"total-reward":[52],"and":[53],"average-reward":[55],"criteria.":[56],"On":[57],"other":[59],"hand,":[60],"it":[61],"shown":[63],"that":[64,88],"runs":[66],"strongly":[68],"time":[70],"discounted-reward":[72,99],"MDPs,":[73],"yet":[74],"only":[75],"when":[76],"discount":[78,104],"factor":[79],"is":[80],"fixed":[81],"beforehand.":[82],"In":[83],"this":[84],"work,":[85],"we":[86],"show":[87],"needs":[90],"steps":[95],"MDPs":[100],"with":[101],"general":[103],"factor.":[105]},"counts_by_year":[{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":2},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}