{"id":"https://openalex.org/W2964921297","doi":"https://doi.org/10.1109/cdc40024.2019.9029255","title":"An Information-theoretic On-line Learning Principle for Specialization in Hierarchical Decision-Making Systems","display_name":"An Information-theoretic On-line Learning Principle for Specialization in Hierarchical Decision-Making Systems","publication_year":2019,"publication_date":"2019-12-01","ids":{"openalex":"https://openalex.org/W2964921297","doi":"https://doi.org/10.1109/cdc40024.2019.9029255","mag":"2964921297"},"language":"en","primary_location":{"id":"doi:10.1109/cdc40024.2019.9029255","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc40024.2019.9029255","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE 58th Conference on Decision and Control (CDC)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1907.11452","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Heinke Hihn","orcid":null},"institutions":[{"id":"https://openalex.org/I196349391","display_name":"Universit\u00e4t Ulm","ror":"https://ror.org/032000t02","country_code":"DE","type":"education","lineage":["https://openalex.org/I196349391"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Heinke Hihn","raw_affiliation_strings":["Institute of Neural Information Processing at the Ulm University, Ulm University, Ulm, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Neural Information Processing at the Ulm University, Ulm University, Ulm, Germany","institution_ids":["https://openalex.org/I196349391"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Sebastian Gottwald","orcid":null},"institutions":[{"id":"https://openalex.org/I196349391","display_name":"Universit\u00e4t Ulm","ror":"https://ror.org/032000t02","country_code":"DE","type":"education","lineage":["https://openalex.org/I196349391"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Sebastian Gottwald","raw_affiliation_strings":["Institute of Neural Information Processing at the Ulm University, Ulm University, Ulm, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Neural Information Processing at the Ulm University, Ulm University, Ulm, Germany","institution_ids":["https://openalex.org/I196349391"]}]},{"author_position":"last","author":{"id":null,"display_name":"Daniel A. Braun","orcid":null},"institutions":[{"id":"https://openalex.org/I196349391","display_name":"Universit\u00e4t Ulm","ror":"https://ror.org/032000t02","country_code":"DE","type":"education","lineage":["https://openalex.org/I196349391"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Daniel A. Braun","raw_affiliation_strings":["Institute of Neural Information Processing at the Ulm University, Ulm University, Ulm, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Neural Information Processing at the Ulm University, Ulm University, Ulm, Germany","institution_ids":["https://openalex.org/I196349391"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I196349391"],"apc_list":null,"apc_paid":null,"fwci":0.4339,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.71742975,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"12","issue":null,"first_page":"3677","last_page":"3684"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.988099992275238,"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":0.988099992275238,"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/T12137","display_name":"Economic theories and models","score":0.9782000184059143,"subfield":{"id":"https://openalex.org/subfields/2002","display_name":"Economics and Econometrics"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11031","display_name":"Game Theory and Applications","score":0.9768000245094299,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/bounded-function","display_name":"Bounded function","score":0.592199981212616},{"id":"https://openalex.org/keywords/bounded-rationality","display_name":"Bounded rationality","score":0.5546000003814697},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4803999960422516},{"id":"https://openalex.org/keywords/rationality","display_name":"Rationality","score":0.451200008392334},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.4392000138759613},{"id":"https://openalex.org/keywords/division","display_name":"Division (mathematics)","score":0.3472000062465668}],"concepts":[{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.592199981212616},{"id":"https://openalex.org/C58694771","wikidata":"https://www.wikidata.org/wiki/Q814385","display_name":"Bounded rationality","level":2,"score":0.5546000003814697},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5383999943733215},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4803999960422516},{"id":"https://openalex.org/C201717286","wikidata":"https://www.wikidata.org/wiki/Q938185","display_name":"Rationality","level":2,"score":0.451200008392334},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4392000138759613},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4108000099658966},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.36910000443458557},{"id":"https://openalex.org/C60798267","wikidata":"https://www.wikidata.org/wiki/Q1226939","display_name":"Division (mathematics)","level":2,"score":0.3472000062465668},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.34630000591278076},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.3160000145435333},{"id":"https://openalex.org/C88548561","wikidata":"https://www.wikidata.org/wiki/Q347599","display_name":"sort","level":2,"score":0.3037000000476837},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.29249998927116394},{"id":"https://openalex.org/C125014702","wikidata":"https://www.wikidata.org/wiki/Q4680749","display_name":"Adaptive learning","level":2,"score":0.28519999980926514},{"id":"https://openalex.org/C2776542497","wikidata":"https://www.wikidata.org/wiki/Q5266672","display_name":"Development (topology)","level":2,"score":0.2816999852657318}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/cdc40024.2019.9029255","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc40024.2019.9029255","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE 58th Conference on Decision and Control (CDC)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1907.11452","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1907.11452","pdf_url":"https://arxiv.org/pdf/1907.11452","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1907.11452","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1907.11452","pdf_url":"https://arxiv.org/pdf/1907.11452","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1687991450","https://openalex.org/W1892018222","https://openalex.org/W1997318940","https://openalex.org/W2029236670","https://openalex.org/W2038730444","https://openalex.org/W2068238590","https://openalex.org/W2074499097","https://openalex.org/W2101692583","https://openalex.org/W2119717200","https://openalex.org/W2148962857","https://openalex.org/W2148986322","https://openalex.org/W2150884987","https://openalex.org/W2157201325","https://openalex.org/W2163119409","https://openalex.org/W2211766770","https://openalex.org/W2239029832","https://openalex.org/W2250513429","https://openalex.org/W2264897026","https://openalex.org/W2487087946","https://openalex.org/W2735099849","https://openalex.org/W2776886510","https://openalex.org/W2801101267","https://openalex.org/W2889269551","https://openalex.org/W2889989645","https://openalex.org/W2905156237","https://openalex.org/W2911412474","https://openalex.org/W2934590717","https://openalex.org/W2963817734","https://openalex.org/W2964177217","https://openalex.org/W4241649586","https://openalex.org/W6627932998","https://openalex.org/W6631064309","https://openalex.org/W6638018090","https://openalex.org/W6675354045","https://openalex.org/W6676560026","https://openalex.org/W6678114464","https://openalex.org/W6683195989","https://openalex.org/W6683204974","https://openalex.org/W6688150747","https://openalex.org/W6692846177","https://openalex.org/W6696692932","https://openalex.org/W6713134421","https://openalex.org/W6737893269","https://openalex.org/W6742534726","https://openalex.org/W6745983339","https://openalex.org/W6750186571","https://openalex.org/W6780559895"],"related_works":[],"abstract_inverted_index":{"Information-theoretic":[0],"bounded":[1,20],"rationality":[2,21],"describes":[3],"utility-optimizing":[4],"decision-makers":[5,25,55,111],"whose":[6,96],"limited":[7],"information-processing":[8],"capabilities":[9,37,100],"are":[10,34,59],"formalized":[11],"by":[12,85,108],"information":[13,57],"constraints.":[14],"One":[15],"of":[16,19,38,50,68,75,101,115],"the":[17,36,76,91,99,110,116],"consequences":[18],"is":[22,118,121],"that":[23,33,47,71,80,119],"resource-limited":[24],"can":[26,82,105],"join":[27],"together":[28],"to":[29],"solve":[30],"decision-making":[31,94],"problems":[32,95],"beyond":[35],"each":[39],"individual.":[40],"Here,":[41],"we":[42],"study":[43],"an":[44,64],"information-theoretic":[45],"principle":[46,70],"drives":[48],"division":[49],"labor":[51],"and":[52,123,134],"specialization":[53],"when":[54],"with":[56],"constraints":[58],"joined":[60],"together.":[61],"We":[62,89],"devise":[63],"on-line":[65],"learning":[66,133],"rule":[67],"this":[69],"learns":[72],"a":[73],"partitioning":[74],"problem":[77],"space":[78],"such":[79],"it":[81,120],"be":[83,106],"solved":[84,107],"specialized":[86],"linear":[87],"policies.":[88],"demonstrate":[90],"approach":[92],"for":[93],"complexity":[97],"exceeds":[98],"individual":[102],"decision-makers,":[103],"but":[104],"combining":[109],"optimally.":[112],"The":[113],"strength":[114],"model":[117],"abstract":[122],"principled,":[124],"yet":[125],"has":[126],"direct":[127],"applications":[128],"in":[129],"classification,":[130],"regression,":[131],"reinforcement":[132],"adaptive":[135],"control.":[136]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2019-08-13T00:00:00"}