{"id":"https://openalex.org/W4387185546","doi":"https://doi.org/10.3233/faia230290","title":"Theoretical Remarks on Feudal Hierarchies and Reinforcement Learning","display_name":"Theoretical Remarks on Feudal Hierarchies and Reinforcement Learning","publication_year":2023,"publication_date":"2023-09-28","ids":{"openalex":"https://openalex.org/W4387185546","doi":"https://doi.org/10.3233/faia230290"},"language":"en","primary_location":{"id":"doi:10.3233/faia230290","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia230290","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA230290","source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA230290","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009216751","display_name":"Diogo S. Carvalho","orcid":"https://orcid.org/0000-0003-3008-7322"},"institutions":[{"id":"https://openalex.org/I121345201","display_name":"Instituto de Engenharia de Sistemas e Computadores Investiga\u00e7\u00e3o e Desenvolvimento","ror":"https://ror.org/04mqy3p58","country_code":"PT","type":"nonprofit","lineage":["https://openalex.org/I121345201","https://openalex.org/I4210125590"]},{"id":"https://openalex.org/I141596103","display_name":"University of Lisbon","ror":"https://ror.org/01c27hj86","country_code":"PT","type":"education","lineage":["https://openalex.org/I141596103"]}],"countries":["PT"],"is_corresponding":true,"raw_author_name":"Diogo S. Carvalho","raw_affiliation_strings":["INESC-ID, Lisbon, Portugal","Instituto Superior T\u00e9cnico, University of Lisbon, Lisbon, Portugal"],"affiliations":[{"raw_affiliation_string":"INESC-ID, Lisbon, Portugal","institution_ids":["https://openalex.org/I121345201"]},{"raw_affiliation_string":"Instituto Superior T\u00e9cnico, University of Lisbon, Lisbon, Portugal","institution_ids":["https://openalex.org/I141596103"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101616573","display_name":"Francisco S. Melo","orcid":"https://orcid.org/0000-0001-5705-7372"},"institutions":[{"id":"https://openalex.org/I121345201","display_name":"Instituto de Engenharia de Sistemas e Computadores Investiga\u00e7\u00e3o e Desenvolvimento","ror":"https://ror.org/04mqy3p58","country_code":"PT","type":"nonprofit","lineage":["https://openalex.org/I121345201","https://openalex.org/I4210125590"]},{"id":"https://openalex.org/I141596103","display_name":"University of Lisbon","ror":"https://ror.org/01c27hj86","country_code":"PT","type":"education","lineage":["https://openalex.org/I141596103"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Francisco S. Melo","raw_affiliation_strings":["INESC-ID, Lisbon, Portugal","Instituto Superior T\u00e9cnico, University of Lisbon, Lisbon, Portugal"],"affiliations":[{"raw_affiliation_string":"INESC-ID, Lisbon, Portugal","institution_ids":["https://openalex.org/I121345201"]},{"raw_affiliation_string":"Instituto Superior T\u00e9cnico, University of Lisbon, Lisbon, Portugal","institution_ids":["https://openalex.org/I141596103"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056845990","display_name":"Pedro A. Santos","orcid":"https://orcid.org/0000-0002-1369-0085"},"institutions":[{"id":"https://openalex.org/I121345201","display_name":"Instituto de Engenharia de Sistemas e Computadores Investiga\u00e7\u00e3o e Desenvolvimento","ror":"https://ror.org/04mqy3p58","country_code":"PT","type":"nonprofit","lineage":["https://openalex.org/I121345201","https://openalex.org/I4210125590"]},{"id":"https://openalex.org/I141596103","display_name":"University of Lisbon","ror":"https://ror.org/01c27hj86","country_code":"PT","type":"education","lineage":["https://openalex.org/I141596103"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Pedro A. Santos","raw_affiliation_strings":["INESC-ID, Lisbon, Portugal","Instituto Superior T\u00e9cnico, University of Lisbon, Lisbon, Portugal"],"affiliations":[{"raw_affiliation_string":"INESC-ID, Lisbon, Portugal","institution_ids":["https://openalex.org/I121345201"]},{"raw_affiliation_string":"Instituto Superior T\u00e9cnico, University of Lisbon, Lisbon, Portugal","institution_ids":["https://openalex.org/I141596103"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5009216751"],"corresponding_institution_ids":["https://openalex.org/I121345201","https://openalex.org/I141596103"],"apc_list":null,"apc_paid":null,"fwci":0.5238,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.68697231,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.8335000276565552,"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":0.8335000276565552,"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/feudalism","display_name":"Feudalism","score":0.944508969783783},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8404952883720398},{"id":"https://openalex.org/keywords/hierarchy","display_name":"Hierarchy","score":0.8002611398696899},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5826981067657471},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.5508829355239868},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5442128777503967},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4827391505241394},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.4476376175880432},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.44130146503448486},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.4169619381427765},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.3613656163215637},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34978818893432617},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19185706973075867},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.15077057480812073},{"id":"https://openalex.org/keywords/political-science","display_name":"Political science","score":0.14029014110565186},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.12290647625923157},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.09592130780220032},{"id":"https://openalex.org/keywords/law","display_name":"Law","score":0.09360358119010925},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.09059417247772217}],"concepts":[{"id":"https://openalex.org/C511693568","wikidata":"https://www.wikidata.org/wiki/Q37739","display_name":"Feudalism","level":3,"score":0.944508969783783},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8404952883720398},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.8002611398696899},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5826981067657471},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.5508829355239868},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5442128777503967},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4827391505241394},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.4476376175880432},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.44130146503448486},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.4169619381427765},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.3613656163215637},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34978818893432617},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19185706973075867},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.15077057480812073},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.14029014110565186},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.12290647625923157},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.09592130780220032},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.09360358119010925},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.09059417247772217},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3233/faia230290","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia230290","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA230290","source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"}],"best_oa_location":{"id":"doi:10.3233/faia230290","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia230290","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA230290","source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"sustainable_development_goals":[{"score":0.7300000190734863,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G2441341484","display_name":null,"funder_award_id":"UIDB/50021/2020","funder_id":"https://openalex.org/F4320334779","funder_display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia"},{"id":"https://openalex.org/G3272457656","display_name":null,"funder_award_id":"UIDB/","funder_id":"https://openalex.org/F4320334779","funder_display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia"},{"id":"https://openalex.org/G5454278309","display_name":null,"funder_award_id":"/2017","funder_id":"https://openalex.org/F4320334779","funder_display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia"},{"id":"https://openalex.org/G6299983296","display_name":null,"funder_award_id":"PTDC/","funder_id":"https://openalex.org/F4320334779","funder_display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia"}],"funders":[{"id":"https://openalex.org/F4320334779","display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia","ror":"https://ror.org/00snfqn58"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4387185546.pdf"},"referenced_works_count":56,"referenced_works":["https://openalex.org/W256201028","https://openalex.org/W1488730473","https://openalex.org/W1982678075","https://openalex.org/W2109910161","https://openalex.org/W2124175081","https://openalex.org/W2131600418","https://openalex.org/W2145339207","https://openalex.org/W2155027007","https://openalex.org/W2155968351","https://openalex.org/W2156737235","https://openalex.org/W2158548602","https://openalex.org/W2160371091","https://openalex.org/W2165131254","https://openalex.org/W2170192506","https://openalex.org/W2173248099","https://openalex.org/W2173564293","https://openalex.org/W2260756217","https://openalex.org/W2335959470","https://openalex.org/W2342662072","https://openalex.org/W2397240726","https://openalex.org/W2482498454","https://openalex.org/W2594829461","https://openalex.org/W2736601468","https://openalex.org/W2746553466","https://openalex.org/W2761873684","https://openalex.org/W2776126823","https://openalex.org/W2786036274","https://openalex.org/W2803281228","https://openalex.org/W2808418668","https://openalex.org/W2811374584","https://openalex.org/W2913654295","https://openalex.org/W2920215304","https://openalex.org/W2947287204","https://openalex.org/W2949267040","https://openalex.org/W2949604932","https://openalex.org/W2950614095","https://openalex.org/W2951725892","https://openalex.org/W2951799221","https://openalex.org/W2962686687","https://openalex.org/W2963262099","https://openalex.org/W2963864421","https://openalex.org/W2964043796","https://openalex.org/W2964227312","https://openalex.org/W2964836580","https://openalex.org/W2965291189","https://openalex.org/W3035868808","https://openalex.org/W3116006999","https://openalex.org/W3213249196","https://openalex.org/W4220880510","https://openalex.org/W4229060449","https://openalex.org/W4233061323","https://openalex.org/W4287756016","https://openalex.org/W4297797010","https://openalex.org/W4298023569","https://openalex.org/W4308716551","https://openalex.org/W4362203700"],"related_works":["https://openalex.org/W3096874164","https://openalex.org/W2937181779","https://openalex.org/W2386410636","https://openalex.org/W1985560493","https://openalex.org/W2357975469","https://openalex.org/W2145363145","https://openalex.org/W1626977535","https://openalex.org/W4284974072","https://openalex.org/W2341346307","https://openalex.org/W4225269853"],"abstract_inverted_index":{"Hierarchical":[0],"reinforcement":[1,133],"learning":[2,9,98,134],"is":[3,115],"an":[4],"increasingly":[5],"demanded":[6],"resource":[7],"for":[8,32,101,123],"to":[10,91],"make":[11],"sequential":[12],"decisions":[13],"towards":[14],"long":[15],"term":[16],"goals.":[17],"Feudal":[18],"hierarchies":[19,128],"are":[20,28],"among":[21],"the":[22,40,51,54,60,64,68,72,79,88,96,102,113,124],"most":[23],"deployed":[24],"frameworks.":[25],"However,":[26],"there":[27],"few":[29],"theoretical":[30,121],"results":[31,118],"hierarchical":[33],"structures.":[34],"In":[35],"this":[36],"work,":[37],"we":[38,74],"formalize":[39],"common":[41],"two-level":[42],"feudal":[43,127],"hierarchy":[44],"as":[45],"two":[46],"Markov":[47],"decision":[48],"processes,":[49],"with":[50,120,131],"one":[52],"on":[53,59,87],"high":[55],"level":[56],"being":[57],"dependent":[58],"policy":[61],"executed":[62],"at":[63,112,136],"low":[65,103],"level.":[66,138],"Despite":[67],"non-stationarity":[69],"raised":[70],"by":[71],"dependency,":[73],"show":[75,92],"that":[76],"each":[77,137],"of":[78,95,106,126],"processes":[80],"presents":[81],"stable":[82],"behavior.":[83],"We":[84],"then":[85],"build":[86],"first":[89],"result":[90],"that,":[93],"regardless":[94],"convergent":[97],"algorithm":[99],"used":[100],"level,":[104],"convergence":[105],"both":[107],"prediction":[108],"and":[109],"control":[110],"algorithms":[111],"high-level":[114],"guaranteed.":[116],"Our":[117],"contribute":[119],"support":[122],"use":[125],"in":[129],"combination":[130],"standard":[132],"methods":[135]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}
