{"id":"https://openalex.org/W2553083024","doi":"https://doi.org/10.1109/allerton.2012.6483256","title":"Efficient solution of Markov decision problems with multiscale representations","display_name":"Efficient solution of Markov decision problems with multiscale representations","publication_year":2012,"publication_date":"2012-10-01","ids":{"openalex":"https://openalex.org/W2553083024","doi":"https://doi.org/10.1109/allerton.2012.6483256","mag":"2553083024"},"language":"en","primary_location":{"id":"doi:10.1109/allerton.2012.6483256","is_oa":false,"landing_page_url":"https://doi.org/10.1109/allerton.2012.6483256","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 50th 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/A5111435078","display_name":"Jake Bouvrie","orcid":null},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jake Bouvrie","raw_affiliation_strings":["Department of Mathematics, Duke University, Durham, NC, USA"],"affiliations":[{"raw_affiliation_string":"Department of Mathematics, Duke University, Durham, NC, USA","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089371996","display_name":"Mauro Maggioni","orcid":"https://orcid.org/0000-0003-3258-9297"},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mauro Maggioni","raw_affiliation_strings":["Departments of Mathematics and Computer Science, Duke University, Durham, NC, USA"],"affiliations":[{"raw_affiliation_string":"Departments of Mathematics and Computer Science, Duke University, Durham, NC, USA","institution_ids":["https://openalex.org/I170897317"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5111435078"],"corresponding_institution_ids":["https://openalex.org/I170897317"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.31204864,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"21","issue":null,"first_page":"474","last_page":"481"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9991999864578247,"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":0.9991999864578247,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.991599977016449,"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/T11273","display_name":"Advanced Graph Neural Networks","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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8040519952774048},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7715365290641785},{"id":"https://openalex.org/keywords/hierarchy","display_name":"Hierarchy","score":0.6960930824279785},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6533368825912476},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.583938479423523},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.555683434009552},{"id":"https://openalex.org/keywords/decision-problem","display_name":"Decision problem","score":0.5051077008247375},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4737173914909363},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.41138219833374023},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3935388922691345},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.36911076307296753},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2442721724510193},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12004697322845459}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8040519952774048},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7715365290641785},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.6960930824279785},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6533368825912476},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.583938479423523},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.555683434009552},{"id":"https://openalex.org/C115988155","wikidata":"https://www.wikidata.org/wiki/Q3262192","display_name":"Decision problem","level":2,"score":0.5051077008247375},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4737173914909363},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.41138219833374023},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3935388922691345},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.36911076307296753},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2442721724510193},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12004697322845459},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C34447519","wikidata":"https://www.wikidata.org/wiki/Q179522","display_name":"Market economy","level":1,"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/allerton.2012.6483256","is_oa":false,"landing_page_url":"https://doi.org/10.1109/allerton.2012.6483256","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 50th Annual Allerton Conference on Communication, Control, and Computing (Allerton)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.298.3458","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.298.3458","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.math.duke.edu/~mauro/Papers/BouvrieMaggioni_Allerton2012.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.7799999713897705}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W755194005","https://openalex.org/W1592847719","https://openalex.org/W1607318605","https://openalex.org/W2069992656","https://openalex.org/W2097381042","https://openalex.org/W2098432798","https://openalex.org/W2109910161","https://openalex.org/W2121517924","https://openalex.org/W2135512436","https://openalex.org/W2140432232","https://openalex.org/W2158548602","https://openalex.org/W2168640731","https://openalex.org/W2225974540","https://openalex.org/W2334782222","https://openalex.org/W2952395520","https://openalex.org/W4249441547","https://openalex.org/W6636145462","https://openalex.org/W6674600207","https://openalex.org/W6683443546","https://openalex.org/W6685218902","https://openalex.org/W6689337587"],"related_works":["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","https://openalex.org/W2171353008","https://openalex.org/W2403631390"],"abstract_inverted_index":{"Many":[0],"problems":[1],"in":[2],"sequential":[3],"decision":[4,47],"making":[5],"and":[6,26,68,87],"stochastic":[7],"control":[8],"naturally":[9],"enjoy":[10],"strong":[11],"multiscale":[12,39,76],"structure:":[13],"sub-tasks":[14,83],"are":[15,63],"often":[16],"assembled":[17],"together":[18],"to":[19,93],"accomplish":[20],"complex":[21],"goals.":[22],"However,":[23],"systematically":[24],"inferring":[25],"leveraging":[27],"hierarchical":[28],"structure":[29],"has":[30],"remained":[31],"a":[32,37,51,100],"longstanding":[33],"challenge.":[34],"We":[35],"describe":[36],"fast":[38],"procedure":[40],"for":[41],"repeatedly":[42],"compressing":[43],"or":[44],"homogenizing":[45],"Markov":[46],"processes":[48],"(MDPs),":[49],"wherein":[50],"hierarchy":[52],"of":[53],"sub-problems":[54],"at":[55],"different":[56],"scales":[57],"is":[58],"automatically":[59],"determined.":[60],"Coarsened":[61],"MDPs":[62],"themselves":[64],"independent,":[65],"deterministic":[66],"MDPs,":[67],"may":[69],"be":[70],"solved":[71],"using":[72],"any":[73],"method.":[74],"The":[75],"representation":[77],"delivered":[78],"by":[79],"the":[80],"algorithm":[81],"decouples":[82],"from":[84],"each":[85],"other":[86],"improves":[88],"conditioning.":[89],"These":[90],"advantages":[91],"lead":[92],"potentially":[94],"significant":[95],"computational":[96],"savings":[97],"when":[98],"solving":[99],"problem,":[101],"as":[102,104],"well":[103],"immediate":[105],"transfer":[106],"learning":[107],"opportunities":[108],"across":[109],"related":[110],"tasks.":[111]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}