{"id":"https://openalex.org/W3150105804","doi":"https://doi.org/10.1109/tac.2021.3069347","title":"Transfer-Entropy-Regularized Markov Decision Processes","display_name":"Transfer-Entropy-Regularized Markov Decision Processes","publication_year":2021,"publication_date":"2021-03-29","ids":{"openalex":"https://openalex.org/W3150105804","doi":"https://doi.org/10.1109/tac.2021.3069347","mag":"3150105804"},"language":"en","primary_location":{"id":"doi:10.1109/tac.2021.3069347","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tac.2021.3069347","pdf_url":null,"source":{"id":"https://openalex.org/S184954342","display_name":"IEEE Transactions on Automatic Control","issn_l":"0018-9286","issn":["0018-9286","1558-2523","2334-3303"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Automatic Control","raw_type":"journal-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/A5082230661","display_name":"Takashi Tanaka","orcid":"https://orcid.org/0000-0001-7424-0064"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Takashi Tanaka","raw_affiliation_strings":["Aerospace Engineering and Engineering Mechanics, University of Texas at Austin, Austin, TX, USA"],"raw_orcid":"https://orcid.org/0000-0001-7424-0064","affiliations":[{"raw_affiliation_string":"Aerospace Engineering and Engineering Mechanics, University of Texas at Austin, Austin, TX, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056120878","display_name":"Henrik Sandberg","orcid":"https://orcid.org/0000-0003-1835-2963"},"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":"Henrik Sandberg","raw_affiliation_strings":["Decision and Control Systems, KTH Royal Institute of Technology, Stockholm, Sweden"],"raw_orcid":"https://orcid.org/0000-0003-1835-2963","affiliations":[{"raw_affiliation_string":"Decision and Control Systems, KTH Royal Institute of Technology, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041348422","display_name":"Mikael Skoglund","orcid":"https://orcid.org/0000-0002-7926-5081"},"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":"Mikael Skoglund","raw_affiliation_strings":["Decision and Control Systems, KTH Royal Institute of Technology, Stockholm, Sweden"],"raw_orcid":"https://orcid.org/0000-0002-7926-5081","affiliations":[{"raw_affiliation_string":"Decision and Control Systems, KTH Royal Institute of Technology, Stockholm, Sweden","institution_ids":["https://openalex.org/I86987016"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.3947,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.80673708,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"67","issue":"4","first_page":"1944","last_page":"1951"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11520","display_name":"Advanced Thermodynamics and Statistical Mechanics","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11520","display_name":"Advanced Thermodynamics and Statistical Mechanics","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10581","display_name":"Neural dynamics and brain function","score":0.9853000044822693,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.9811999797821045,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.6759802103042603},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.6213656663894653},{"id":"https://openalex.org/keywords/transfer-entropy","display_name":"Transfer entropy","score":0.5935816764831543},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.5782055854797363},{"id":"https://openalex.org/keywords/limit-point","display_name":"Limit point","score":0.5391547679901123},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.5343149900436401},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.5284338593482971},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.4664081633090973},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.43062126636505127},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.421270489692688},{"id":"https://openalex.org/keywords/principle-of-maximum-entropy","display_name":"Principle of maximum entropy","score":0.411733478307724},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.35904693603515625},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.33186978101730347},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.20611613988876343},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.12765365839004517}],"concepts":[{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6759802103042603},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.6213656663894653},{"id":"https://openalex.org/C182049051","wikidata":"https://www.wikidata.org/wiki/Q17147155","display_name":"Transfer entropy","level":3,"score":0.5935816764831543},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.5782055854797363},{"id":"https://openalex.org/C63548660","wikidata":"https://www.wikidata.org/wiki/Q858223","display_name":"Limit point","level":2,"score":0.5391547679901123},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5343149900436401},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.5284338593482971},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.4664081633090973},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.43062126636505127},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.421270489692688},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.411733478307724},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.35904693603515625},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.33186978101730347},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.20611613988876343},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.12765365839004517},{"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"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:10.1109/tac.2021.3069347","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tac.2021.3069347","pdf_url":null,"source":{"id":"https://openalex.org/S184954342","display_name":"IEEE Transactions on Automatic Control","issn_l":"0018-9286","issn":["0018-9286","1558-2523","2334-3303"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Automatic Control","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7599999904632568,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G3775629894","display_name":null,"funder_award_id":"D19AP00078","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G4061599517","display_name":"Security, Privacy, and Information Limitations in Control Systems","funder_award_id":"2016-00861","funder_id":"https://openalex.org/F4320322581","funder_display_name":"Vetenskapsr\u00e5det"},{"id":"https://openalex.org/G6001495769","display_name":"Information Theoretic Tools for Networked Inference","funder_award_id":"2015-04361","funder_id":"https://openalex.org/F4320322581","funder_display_name":"Vetenskapsr\u00e5det"}],"funders":[{"id":"https://openalex.org/F4320322581","display_name":"Vetenskapsr\u00e5det","ror":"https://ror.org/03zttf063"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W48257500","https://openalex.org/W563793012","https://openalex.org/W1489262227","https://openalex.org/W1540764732","https://openalex.org/W1759288767","https://openalex.org/W1833579107","https://openalex.org/W1966514629","https://openalex.org/W1997835326","https://openalex.org/W1998713330","https://openalex.org/W2029148261","https://openalex.org/W2029236670","https://openalex.org/W2041782669","https://openalex.org/W2063002186","https://openalex.org/W2071214852","https://openalex.org/W2082484220","https://openalex.org/W2082639035","https://openalex.org/W2099111195","https://openalex.org/W2129885443","https://openalex.org/W2148986322","https://openalex.org/W2174375947","https://openalex.org/W2336193807","https://openalex.org/W2567304693","https://openalex.org/W2878525925","https://openalex.org/W2941237017","https://openalex.org/W2962948942","https://openalex.org/W3104074915","https://openalex.org/W3123899698","https://openalex.org/W3145190972","https://openalex.org/W3150105804","https://openalex.org/W4298023569","https://openalex.org/W6629237864","https://openalex.org/W6681130209"],"related_works":["https://openalex.org/W2009218479","https://openalex.org/W1999409691","https://openalex.org/W2012408753","https://openalex.org/W4385562674","https://openalex.org/W3048657985","https://openalex.org/W2004597074","https://openalex.org/W4213214852","https://openalex.org/W2751002382","https://openalex.org/W2810315705","https://openalex.org/W3150105804"],"abstract_inverted_index":{"We":[0],"consider":[1],"the":[2,12,16,21,25,30,70,83,87,95,103,128,134],"framework":[3],"of":[4,15,57,82,94,98,105,130],"transfer-entropy-regularized":[5],"Markov":[6],"decision":[7,136],"process":[8,28,33],"(TERMDP)":[9],"in":[10,102],"which":[11,62],"weighted":[13],"sum":[14],"classical":[17],"state-dependent":[18],"cost":[19],"and":[20,110],"transfer":[22],"entropy":[23],"from":[24],"state":[26],"random":[27],"to":[29,69,118],"control":[31,107],"input":[32],"is":[34,73,76,90,116],"minimized.":[35],"Although":[36],"TERMDPs":[37,99],"are":[38,100],"generally":[39],"formulated":[40],"as":[41,53],"nonconvex":[42],"optimization":[43],"problems,":[44],"an":[45,63,119],"analytical":[46],"necessary":[47],"optimality":[48],"condition":[49],"can":[50],"be":[51],"expressed":[52],"a":[54,91],"finite":[55],"set":[56],"nonlinear":[58],"equations,":[59],"based":[60],"on":[61],"iterative":[64],"forward\u2013backward":[65],"computational":[66],"procedure":[67],"similar":[68],"Arimoto\u2013Blahut":[71],"algorithm":[72,89,115],"developed.":[74],"It":[75],"shown":[77],"that":[78],"every":[79],"limit":[80],"point":[81,93],"sequence":[84],"generated":[85],"by":[86],"proposed":[88,114],"stationary":[92],"TERMDP.":[96],"Applications":[97],"discussed":[101],"context":[104],"networked":[106],"systems":[108],"theory":[109],"nonequilibrium":[111],"thermodynamics.":[112],"The":[113],"applied":[117],"information-constrained":[120],"maze":[121],"navigation":[122],"problem,":[123],"whereby":[124],"we":[125],"study":[126],"how":[127],"price":[129],"information":[131],"qualitatively":[132],"alters":[133],"optimal":[135],"polices.":[137]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}