{"id":"https://openalex.org/W4405276987","doi":"https://doi.org/10.1007/s00521-024-10596-2","title":"Int-HRL: towards intention-based hierarchical reinforcement learning","display_name":"Int-HRL: towards intention-based hierarchical reinforcement learning","publication_year":2024,"publication_date":"2024-12-11","ids":{"openalex":"https://openalex.org/W4405276987","doi":"https://doi.org/10.1007/s00521-024-10596-2","pmid":"https://pubmed.ncbi.nlm.nih.gov/40756565"},"language":"en","primary_location":{"id":"doi:10.1007/s00521-024-10596-2","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00521-024-10596-2","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00521-024-10596-2.pdf","source":{"id":"https://openalex.org/S147897268","display_name":"Neural Computing and Applications","issn_l":"0941-0643","issn":["0941-0643","1433-3058"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Computing and Applications","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s00521-024-10596-2.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5017634512","display_name":"Anna Penzkofer","orcid":"https://orcid.org/0009-0006-8570-0007"},"institutions":[{"id":"https://openalex.org/I100066346","display_name":"University of Stuttgart","ror":"https://ror.org/04vnq7t77","country_code":"DE","type":"education","lineage":["https://openalex.org/I100066346"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Anna Penzkofer","raw_affiliation_strings":["Institute for Visualisation and Interactive Systems, University of Stuttgart, Pfaffenwaldring 5A, 70569 Stuttgart, Germany","Institute for Visualisation and Interactive Systems, University of Stuttgart, Pfaffenwaldring 5A, 70569, Stuttgart, Germany"],"raw_orcid":"https://orcid.org/0009-0006-8570-0007","affiliations":[{"raw_affiliation_string":"Institute for Visualisation and Interactive Systems, University of Stuttgart, Pfaffenwaldring 5A, 70569 Stuttgart, Germany","institution_ids":["https://openalex.org/I100066346"]},{"raw_affiliation_string":"Institute for Visualisation and Interactive Systems, University of Stuttgart, Pfaffenwaldring 5A, 70569, Stuttgart, Germany","institution_ids":["https://openalex.org/I100066346"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078912326","display_name":"Simon Schaefer","orcid":"https://orcid.org/0000-0001-7289-6000"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Simon Schaefer","raw_affiliation_strings":["Machine Learning for Robotics, Technical University of Munich, Boltzmannstrasse 3, 85748 Munich, Germany","Machine Learning for Robotics, Technical University of Munich, Boltzmannstrasse 3, 85748, Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Machine Learning for Robotics, Technical University of Munich, Boltzmannstrasse 3, 85748 Munich, Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Machine Learning for Robotics, Technical University of Munich, Boltzmannstrasse 3, 85748, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069798532","display_name":"Florian Strohm","orcid":"https://orcid.org/0000-0002-3787-3062"},"institutions":[{"id":"https://openalex.org/I100066346","display_name":"University of Stuttgart","ror":"https://ror.org/04vnq7t77","country_code":"DE","type":"education","lineage":["https://openalex.org/I100066346"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Florian Strohm","raw_affiliation_strings":["Institute for Visualisation and Interactive Systems, University of Stuttgart, Pfaffenwaldring 5A, 70569 Stuttgart, Germany","Institute for Visualisation and Interactive Systems, University of Stuttgart, Pfaffenwaldring 5A, 70569, Stuttgart, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Visualisation and Interactive Systems, University of Stuttgart, Pfaffenwaldring 5A, 70569 Stuttgart, Germany","institution_ids":["https://openalex.org/I100066346"]},{"raw_affiliation_string":"Institute for Visualisation and Interactive Systems, University of Stuttgart, Pfaffenwaldring 5A, 70569, Stuttgart, Germany","institution_ids":["https://openalex.org/I100066346"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064650339","display_name":"Mihai B\u00e2ce","orcid":"https://orcid.org/0000-0002-1446-379X"},"institutions":[{"id":"https://openalex.org/I99464096","display_name":"KU Leuven","ror":"https://ror.org/05f950310","country_code":"BE","type":"education","lineage":["https://openalex.org/I99464096"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Mihai B\u00e2ce","raw_affiliation_strings":["Department of Computer Science, KU Leuven, Andreas Vesaliusstraat 13, box 2600, 3000 Leuven, Belgium","Department of Computer Science, KU Leuven, Andreas Vesaliusstraat 13,  box 2600, 3000, Leuven, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, KU Leuven, Andreas Vesaliusstraat 13, box 2600, 3000 Leuven, Belgium","institution_ids":["https://openalex.org/I99464096"]},{"raw_affiliation_string":"Department of Computer Science, KU Leuven, Andreas Vesaliusstraat 13,  box 2600, 3000, Leuven, Belgium","institution_ids":["https://openalex.org/I99464096"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006726091","display_name":"Stefan Leutenegger","orcid":"https://orcid.org/0000-0002-7998-3737"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Stefan Leutenegger","raw_affiliation_strings":["Machine Learning for Robotics, Technical University of Munich, Boltzmannstrasse 3, 85748 Munich, Germany","Machine Learning for Robotics, Technical University of Munich, Boltzmannstrasse 3, 85748, Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Machine Learning for Robotics, Technical University of Munich, Boltzmannstrasse 3, 85748 Munich, Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Machine Learning for Robotics, Technical University of Munich, Boltzmannstrasse 3, 85748, Munich, Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073661463","display_name":"Andreas Bulling","orcid":"https://orcid.org/0000-0001-6317-7303"},"institutions":[{"id":"https://openalex.org/I100066346","display_name":"University of Stuttgart","ror":"https://ror.org/04vnq7t77","country_code":"DE","type":"education","lineage":["https://openalex.org/I100066346"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Andreas Bulling","raw_affiliation_strings":["Institute for Visualisation and Interactive Systems, University of Stuttgart, Pfaffenwaldring 5A, 70569 Stuttgart, Germany","Institute for Visualisation and Interactive Systems, University of Stuttgart, Pfaffenwaldring 5A, 70569, Stuttgart, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Visualisation and Interactive Systems, University of Stuttgart, Pfaffenwaldring 5A, 70569 Stuttgart, Germany","institution_ids":["https://openalex.org/I100066346"]},{"raw_affiliation_string":"Institute for Visualisation and Interactive Systems, University of Stuttgart, Pfaffenwaldring 5A, 70569, Stuttgart, Germany","institution_ids":["https://openalex.org/I100066346"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5017634512"],"corresponding_institution_ids":["https://openalex.org/I100066346"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":{"value":2390,"currency":"EUR","value_usd":2990},"fwci":0.2977,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.67151208,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"37","issue":"23","first_page":"18823","last_page":"18834"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9990000128746033,"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":0.9990000128746033,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9821000099182129,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9567999839782715,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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/computational-science-and-engineering","display_name":"Computational Science and Engineering","score":0.8586245775222778},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7902783155441284},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6371366381645203},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.533764123916626},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4166320562362671},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2503221035003662},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.20033562183380127},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.0654321014881134}],"concepts":[{"id":"https://openalex.org/C68597687","wikidata":"https://www.wikidata.org/wiki/Q362601","display_name":"Computational Science and Engineering","level":2,"score":0.8586245775222778},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7902783155441284},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6371366381645203},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.533764123916626},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4166320562362671},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2503221035003662},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.20033562183380127},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0654321014881134}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1007/s00521-024-10596-2","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00521-024-10596-2","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00521-024-10596-2.pdf","source":{"id":"https://openalex.org/S147897268","display_name":"Neural Computing and Applications","issn_l":"0941-0643","issn":["0941-0643","1433-3058"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Computing and Applications","raw_type":"journal-article"},{"id":"pmid:40756565","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40756565","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural computing & applications","raw_type":null},{"id":"pmh:oai:europepmc.org:11126313","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/12313806","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC12313806/pdf/521_2024_Article_10596.pdf","source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1007/s00521-024-10596-2","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00521-024-10596-2","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00521-024-10596-2.pdf","source":{"id":"https://openalex.org/S147897268","display_name":"Neural Computing and Applications","issn_l":"0941-0643","issn":["0941-0643","1433-3058"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Computing and Applications","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.7799999713897705,"id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G4260872415","display_name":"Anticipatory Human-Computer Interaction","funder_award_id":"801708","funder_id":"https://openalex.org/F4320338335","funder_display_name":"H2020 European Research Council"},{"id":"https://openalex.org/G5543094940","display_name":null,"funder_award_id":"EXC 2075 -390740016","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G5643887040","display_name":null,"funder_award_id":"EXC 2075 - 390740016","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G7249683039","display_name":null,"funder_award_id":"EXC 2075","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G8350989610","display_name":"Attention Sensing in the Workplace: Towards the New Future of Work","funder_award_id":"214434","funder_id":"https://openalex.org/F4320320924","funder_display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung"},{"id":"https://openalex.org/G8784604414","display_name":"EXC 2075: Datenintegrierte Simulationswissenschaft (SimTech)","funder_award_id":"390740016","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320315885","display_name":"Australian Government","ror":"https://ror.org/0314h5y94"},{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"},{"id":"https://openalex.org/F4320320924","display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung","ror":"https://ror.org/00yjd3n13"},{"id":"https://openalex.org/F4320321114","display_name":"Bundesministerium f\u00fcr Bildung und Forschung","ror":"https://ror.org/04pz7b180"},{"id":"https://openalex.org/F4320325850","display_name":"Universit\u00e4t Stuttgart","ror":"https://ror.org/04vnq7t77"},{"id":"https://openalex.org/F4320338335","display_name":"H2020 European Research Council","ror":"https://ror.org/0472cxd90"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4405276987.pdf","grobid_xml":"https://content.openalex.org/works/W4405276987.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W1494114146","https://openalex.org/W1976152465","https://openalex.org/W2133105703","https://openalex.org/W2150468603","https://openalex.org/W2746553466","https://openalex.org/W2752455899","https://openalex.org/W2805623918","https://openalex.org/W2904157920","https://openalex.org/W2963871073","https://openalex.org/W2982316857","https://openalex.org/W2997423597","https://openalex.org/W2997502107","https://openalex.org/W3014274848","https://openalex.org/W3022565501","https://openalex.org/W3038500004","https://openalex.org/W3129981047","https://openalex.org/W4246078117","https://openalex.org/W4281262066","https://openalex.org/W4287209565","https://openalex.org/W4287863982","https://openalex.org/W4298857966","https://openalex.org/W6603944243","https://openalex.org/W6631495455","https://openalex.org/W6637642161"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856"],"abstract_inverted_index":{"Abstract":[0],"While":[1],"deep":[2],"reinforcement":[3],"learning":[4,59],"(RL)":[5],"agents":[6],"outperform":[7],"humans":[8],"on":[9],"an":[10,150],"increasing":[11],"number":[12],"of":[13,22,40,48,65,71,88,91],"tasks,":[14],"training":[15],"them":[16],"requires":[17],"data":[18],"equivalent":[19],"to":[20,37,50,149],"decades":[21],"human":[23,66,115,135],"gameplay.":[24],"Recent":[25],"hierarchical":[26],"RL":[27,95,107],"methods":[28],"have":[29],"increased":[30],"sample":[31,157],"efficiency":[32],"by":[33,134],"incorporating":[34],"information":[35],"inherent":[36],"the":[38,41,46,58,69,83,92,98,128],"structure":[39],"decision":[42],"problem":[43],"but":[44],"at":[45],"cost":[47],"having":[49],"discover":[51],"or":[52],"use":[53],"human-annotated":[54],"sub-goals":[55,110,143],"that":[56,63,111,140,153],"guide":[57],"process.":[60],"We":[61,102],"show":[62,139],"intentions":[64,147],"players,":[67],"i.e.":[68],"precursor":[70],"goal-oriented":[72],"decisions,":[73],"can":[74],"be":[75],"robustly":[76],"predicted":[77],"from":[78,114],"eye":[79,116],"gaze":[80],"even":[81],"for":[82,130],"long-horizon":[84],"sparse":[85],"rewards":[86],"task":[87],"Montezuma\u2019s":[89],"Revenge\u2013one":[90],"most":[93],"challenging":[94],"tasks":[96],"in":[97],"Atari2600":[99],"game":[100],"suite.":[101],"propose":[103],"Int-HRL":[104],":":[105],"Hierarchical":[106],"with":[108,144],"intention-based":[109],"are":[112],"inferred":[113],"gaze.":[117],"Our":[118,137],"novel":[119],"sub-goal":[120,132],"extraction":[121],"pipeline":[122],"is":[123,154],"fully":[124],"automatic":[125],"and":[126],"replaces":[127],"need":[129],"manual":[131],"annotation":[133],"experts.":[136],"evaluations":[138],"replacing":[141],"hand-crafted":[142],"automatically":[145],"extracted":[146],"leads":[148],"HRL":[151],"agent":[152],"significantly":[155],"more":[156],"efficient":[158],"than":[159],"previous":[160],"methods.":[161]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-28T08:01:55.173337","created_date":"2025-10-10T00:00:00"}