{"id":"https://openalex.org/W2955005925","doi":"https://doi.org/10.1109/dsw.2019.8755551","title":"Learning Partially Observable Markov Decision Processes Using Coupled Canonical Polyadic Decomposition","display_name":"Learning Partially Observable Markov Decision Processes Using Coupled Canonical Polyadic Decomposition","publication_year":2019,"publication_date":"2019-06-01","ids":{"openalex":"https://openalex.org/W2955005925","doi":"https://doi.org/10.1109/dsw.2019.8755551","mag":"2955005925"},"language":"en","primary_location":{"id":"doi:10.1109/dsw.2019.8755551","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dsw.2019.8755551","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Data Science Workshop (DSW)","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/A5002695199","display_name":"Kejun Huang","orcid":"https://orcid.org/0000-0002-6460-6365"},"institutions":[{"id":"https://openalex.org/I33213144","display_name":"University of Florida","ror":"https://ror.org/02y3ad647","country_code":"US","type":"education","lineage":["https://openalex.org/I33213144"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Kejun Huang","raw_affiliation_strings":["Department of Computer and Information Science and Engineering, University of Florida"],"affiliations":[{"raw_affiliation_string":"Department of Computer and Information Science and Engineering, University of Florida","institution_ids":["https://openalex.org/I33213144"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101727948","display_name":"Zhuoran Yang","orcid":"https://orcid.org/0000-0001-5269-9958"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhuoran Yang","raw_affiliation_strings":["Department of Operations Research and Financial Engineering, Princeton University"],"affiliations":[{"raw_affiliation_string":"Department of Operations Research and Financial Engineering, Princeton University","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101934111","display_name":"Zhaoran Wang","orcid":"https://orcid.org/0000-0002-6617-4842"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhaoran Wang","raw_affiliation_strings":["Department of Industrial Engineering and Management Sciences, Northwestern University"],"affiliations":[{"raw_affiliation_string":"Department of Industrial Engineering and Management Sciences, Northwestern University","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100633783","display_name":"Mingyi Hong","orcid":"https://orcid.org/0000-0003-1263-9365"},"institutions":[{"id":"https://openalex.org/I130238516","display_name":"University of Minnesota","ror":"https://ror.org/017zqws13","country_code":"US","type":"education","lineage":["https://openalex.org/I130238516"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mingyi Hong","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Minnesota"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Minnesota","institution_ids":["https://openalex.org/I130238516"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5002695199"],"corresponding_institution_ids":["https://openalex.org/I33213144"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.06892231,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"295","last_page":"299"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12303","display_name":"Tensor decomposition and applications","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/2605","display_name":"Computational Mathematics"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12303","display_name":"Tensor decomposition and applications","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/2605","display_name":"Computational Mathematics"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"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":0.9598000049591064,"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":0.958899974822998,"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/identifiability","display_name":"Identifiability","score":0.9181115627288818},{"id":"https://openalex.org/keywords/partially-observable-markov-decision-process","display_name":"Partially observable Markov decision process","score":0.7530001401901245},{"id":"https://openalex.org/keywords/observable","display_name":"Observable","score":0.6861061453819275},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.6031687259674072},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5480508804321289},{"id":"https://openalex.org/keywords/decomposition","display_name":"Decomposition","score":0.5464869141578674},{"id":"https://openalex.org/keywords/extension","display_name":"Extension (predicate logic)","score":0.5037083029747009},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.49955272674560547},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.49740174412727356},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.4608682096004486},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.44671767950057983},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.4303932785987854},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.4246845841407776},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4246799349784851},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.4031103551387787},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3258994519710541},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.21852877736091614},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.07115375995635986}],"concepts":[{"id":"https://openalex.org/C122770356","wikidata":"https://www.wikidata.org/wiki/Q1656753","display_name":"Identifiability","level":2,"score":0.9181115627288818},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.7530001401901245},{"id":"https://openalex.org/C32848918","wikidata":"https://www.wikidata.org/wiki/Q845789","display_name":"Observable","level":2,"score":0.6861061453819275},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.6031687259674072},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5480508804321289},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.5464869141578674},{"id":"https://openalex.org/C2778029271","wikidata":"https://www.wikidata.org/wiki/Q5421931","display_name":"Extension (predicate logic)","level":2,"score":0.5037083029747009},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.49955272674560547},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.49740174412727356},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4608682096004486},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.44671767950057983},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.4303932785987854},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.4246845841407776},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4246799349784851},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.4031103551387787},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3258994519710541},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.21852877736091614},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.07115375995635986},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/dsw.2019.8755551","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dsw.2019.8755551","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Data Science Workshop (DSW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.7799999713897705,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W52153049","https://openalex.org/W1562564874","https://openalex.org/W1601974704","https://openalex.org/W1723883201","https://openalex.org/W2032100464","https://openalex.org/W2067483065","https://openalex.org/W2070135644","https://openalex.org/W2086699924","https://openalex.org/W2105724942","https://openalex.org/W2144283793","https://openalex.org/W2144446635","https://openalex.org/W2144794447","https://openalex.org/W2160067530","https://openalex.org/W2165421048","https://openalex.org/W2469230926","https://openalex.org/W2556090297","https://openalex.org/W2569025259","https://openalex.org/W2752365628","https://openalex.org/W2787899050","https://openalex.org/W2791154158","https://openalex.org/W2950143340","https://openalex.org/W2950265833","https://openalex.org/W2955787666","https://openalex.org/W2962956149","https://openalex.org/W2963254349","https://openalex.org/W2963390855","https://openalex.org/W3100202987","https://openalex.org/W3103182070","https://openalex.org/W3104256134","https://openalex.org/W4242200182","https://openalex.org/W4293536486","https://openalex.org/W6635991215","https://openalex.org/W6637615226","https://openalex.org/W6638541763","https://openalex.org/W6667083858","https://openalex.org/W6676039487","https://openalex.org/W6681472862","https://openalex.org/W6681633084","https://openalex.org/W6683935339","https://openalex.org/W6684096483","https://openalex.org/W6693997783","https://openalex.org/W6708993328","https://openalex.org/W6730067477","https://openalex.org/W6748646952","https://openalex.org/W6765217860"],"related_works":["https://openalex.org/W2999848267","https://openalex.org/W2096013579","https://openalex.org/W52153049","https://openalex.org/W1760611253","https://openalex.org/W1589140671","https://openalex.org/W1515117609","https://openalex.org/W4323315247","https://openalex.org/W131709709","https://openalex.org/W2294884454","https://openalex.org/W3169161914"],"abstract_inverted_index":{"We":[0,61],"propose":[1],"a":[2,11,28,66,75,78],"new":[3],"algorithm":[4,53],"for":[5,27,37,54],"learning":[6],"the":[7,57,72,92],"model":[8,93],"parameters":[9],"of":[10,30,68,74],"partially":[12],"observable":[13],"Markov":[14],"decision":[15],"process":[16],"(POMDP)":[17],"based":[18],"on":[19],"coupled":[20,84],"canonical":[21],"polyadic":[22],"decomposition":[23],"(CPD).":[24],"Coupled":[25],"CPD":[26,36,85],"set":[29,67],"tensors":[31,70],"is":[32],"an":[33,48],"extension":[34],"to":[35,64,90],"individual":[38],"tensors,":[39],"which":[40],"has":[41],"improved":[42],"identifiability":[43,96],"properties,":[44],"as":[45,47],"well":[46],"analogous":[49],"simultaneous":[50],"diagonalization":[51],"(SD)":[52],"uniquely":[55],"recovering":[56],"latent":[58],"factors":[59],"efficiently.":[60],"explain":[62],"how":[63],"form":[65],"three-way":[69],"from":[71],"trajectory":[73],"POMDP":[76],"under":[77],"stationary":[79],"memoryless":[80],"policy,":[81],"so":[82],"that":[83],"can":[86],"be":[87],"applied":[88],"afterwards":[89],"recover":[91],"parameters,":[94],"with":[95],"and":[97],"computational":[98],"guarantees.":[99]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}