{"id":"https://openalex.org/W2084979015","doi":"https://doi.org/10.1109/aucc.2013.6697239","title":"Computing monotone policies for Markov decision processes by exploiting sparsity","display_name":"Computing monotone policies for Markov decision processes by exploiting sparsity","publication_year":2013,"publication_date":"2013-11-01","ids":{"openalex":"https://openalex.org/W2084979015","doi":"https://doi.org/10.1109/aucc.2013.6697239","mag":"2084979015"},"language":"en","primary_location":{"id":"doi:10.1109/aucc.2013.6697239","is_oa":false,"landing_page_url":"https://doi.org/10.1109/aucc.2013.6697239","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 Australian Control Conference","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/A5068804090","display_name":"Vikram Krishnamurthy","orcid":"https://orcid.org/0000-0002-4170-6056"},"institutions":[{"id":"https://openalex.org/I141945490","display_name":"University of British Columbia","ror":"https://ror.org/03rmrcq20","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Vikram Krishnamurthy","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of British Columbia, Vancouver, Canada","Dept. of Electr. & Comput. Eng., Univ. of British Columbia., Vancouver, BC, Canada"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of British Columbia, Vancouver, Canada","institution_ids":["https://openalex.org/I141945490"]},{"raw_affiliation_string":"Dept. of Electr. & Comput. Eng., Univ. of British Columbia., Vancouver, BC, Canada","institution_ids":["https://openalex.org/I141945490"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057105677","display_name":"Cristian R. Rojas","orcid":"https://orcid.org/0000-0003-0355-2663"},"institutions":[{"id":"https://openalex.org/I141945490","display_name":"University of British Columbia","ror":"https://ror.org/03rmrcq20","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490"]},{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["CA","SE"],"is_corresponding":false,"raw_author_name":"Cristian R. Rojas","raw_affiliation_strings":["Department of Automatic Control, KTH Royal Institute of Technology, Stockholm, Sweden","Dept. of Electr. & Comput. Eng., Univ. of British Columbia., Vancouver, BC, Canada"],"affiliations":[{"raw_affiliation_string":"Department of Automatic Control, KTH Royal Institute of Technology, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]},{"raw_affiliation_string":"Dept. of Electr. & Comput. Eng., Univ. of British Columbia., Vancouver, BC, Canada","institution_ids":["https://openalex.org/I141945490"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045354671","display_name":"Bo Wahlberg","orcid":"https://orcid.org/0000-0002-1927-1690"},"institutions":[{"id":"https://openalex.org/I86987016","display_name":"KTH Royal Institute of Technology","ror":"https://ror.org/026vcq606","country_code":"SE","type":"education","lineage":["https://openalex.org/I86987016"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Bo Wahlberg","raw_affiliation_strings":["Department of Automatic Control, KTH Royal Institute of Technology, Stockholm, Sweden","Dept. of Autom. Control, KTH R. Inst. of Technol., Stockholm, Sweden"],"affiliations":[{"raw_affiliation_string":"Department of Automatic Control, KTH Royal Institute of Technology, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]},{"raw_affiliation_string":"Dept. of Autom. Control, KTH R. Inst. of Technol., Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5068804090"],"corresponding_institution_ids":["https://openalex.org/I141945490"],"apc_list":null,"apc_paid":null,"fwci":1.3139,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.83725873,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10663","display_name":"Advanced Battery Technologies Research","score":0.9976000189781189,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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/T10663","display_name":"Advanced Battery Technologies Research","score":0.9976000189781189,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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/T10768","display_name":"Electric Vehicles and Infrastructure","score":0.9889000058174133,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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/T10780","display_name":"Reliability and Maintenance Optimization","score":0.9790999889373779,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.8350183367729187},{"id":"https://openalex.org/keywords/monotone-polygon","display_name":"Monotone polygon","score":0.7647286653518677},{"id":"https://openalex.org/keywords/subgradient-method","display_name":"Subgradient method","score":0.7275408506393433},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.6399312019348145},{"id":"https://openalex.org/keywords/convex-optimization","display_name":"Convex optimization","score":0.5637755393981934},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5332246422767639},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.5259445309638977},{"id":"https://openalex.org/keywords/dynamic-programming","display_name":"Dynamic programming","score":0.48507991433143616},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.4761103093624115},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.4505199193954468},{"id":"https://openalex.org/keywords/regular-polygon","display_name":"Regular polygon","score":0.44685015082359314},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.36605092883110046},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.18319514393806458},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.11902010440826416}],"concepts":[{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.8350183367729187},{"id":"https://openalex.org/C2834757","wikidata":"https://www.wikidata.org/wiki/Q4925424","display_name":"Monotone polygon","level":2,"score":0.7647286653518677},{"id":"https://openalex.org/C158968445","wikidata":"https://www.wikidata.org/wiki/Q7631150","display_name":"Subgradient method","level":2,"score":0.7275408506393433},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.6399312019348145},{"id":"https://openalex.org/C157972887","wikidata":"https://www.wikidata.org/wiki/Q463359","display_name":"Convex optimization","level":3,"score":0.5637755393981934},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5332246422767639},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.5259445309638977},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.48507991433143616},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.4761103093624115},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.4505199193954468},{"id":"https://openalex.org/C112680207","wikidata":"https://www.wikidata.org/wiki/Q714886","display_name":"Regular polygon","level":2,"score":0.44685015082359314},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.36605092883110046},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.18319514393806458},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.11902010440826416},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"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/aucc.2013.6697239","is_oa":false,"landing_page_url":"https://doi.org/10.1109/aucc.2013.6697239","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 Australian Control Conference","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.800000011920929}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W5385147","https://openalex.org/W389907844","https://openalex.org/W1518931405","https://openalex.org/W2124541940","https://openalex.org/W2124715093","https://openalex.org/W2124839177","https://openalex.org/W2136762313","https://openalex.org/W2138019504","https://openalex.org/W2171033594","https://openalex.org/W2334782222","https://openalex.org/W4292363360"],"related_works":["https://openalex.org/W4389475841","https://openalex.org/W4241327272","https://openalex.org/W2120406836","https://openalex.org/W1996214847","https://openalex.org/W2903299703","https://openalex.org/W4211224558","https://openalex.org/W2117282672","https://openalex.org/W1672382258","https://openalex.org/W2119790124","https://openalex.org/W4281791088"],"abstract_inverted_index":{"This":[0],"paper":[1],"considers":[2],"Markov":[3],"decision":[4],"processes":[5],"whose":[6],"optimal":[7,35,100],"policy":[8,36],"is":[9,91],"a":[10,27,52,66],"randomized":[11],"mixture":[12],"of":[13,47,79,98],"monotone":[14,18,72,96],"increasing":[15],"policies.":[16],"Such":[17],"policies":[19],"have":[20],"an":[21,43],"inherent":[22],"sparsity":[23,73],"structure.":[24],"We":[25],"present":[26],"two-stage":[28],"convex":[29],"optimization":[30],"algorithm":[31],"for":[32],"computing":[33],"the":[34,39,59,71,76,80,83,86,95,99],"that":[37,69],"exploits":[38],"sparsity.":[40],"It":[41],"combines":[42],"alternating":[44],"direction":[45],"method":[46],"multipliers":[48],"(ADMM)":[49],"to":[50,58,93],"solve":[51],"linear":[53],"programming":[54],"problem":[55],"with":[56,65],"respect":[57],"joint":[60],"action":[61,81],"state":[62],"probabilities,":[63],"together":[64],"subgradient":[67],"step":[68],"promotes":[70],"pattern":[74],"in":[75],"conditional":[77],"probabilities":[78],"given":[82],"state.":[84],"In":[85],"second":[87],"step,":[88],"sum-of-norms":[89],"regularization":[90],"used":[92],"stress":[94],"structure":[97],"policy.":[101]},"counts_by_year":[{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}