{"id":"https://openalex.org/W3003712948","doi":"https://doi.org/10.1109/iros40897.2019.8968252","title":"Graph-Based Design of Hierarchical Reinforcement Learning Agents","display_name":"Graph-Based Design of Hierarchical Reinforcement Learning Agents","publication_year":2019,"publication_date":"2019-11-01","ids":{"openalex":"https://openalex.org/W3003712948","doi":"https://doi.org/10.1109/iros40897.2019.8968252","mag":"3003712948"},"language":"en","primary_location":{"id":"doi:10.1109/iros40897.2019.8968252","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros40897.2019.8968252","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/11311/1156734","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5001304610","display_name":"Davide Tateo","orcid":"https://orcid.org/0000-0002-7193-923X"},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Davide Tateo","raw_affiliation_strings":["Informazione e Bioingegneria, Politecnico di Milano Piazza Leonardo da Vinci 32,Dipartimento di Elettronica,Milano,Italy,20133","Dipartimento di Elettronica, Informazione e Bioingegneria, Politecnico di Milano Piazza Leonardo da Vinci 32, Milano, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Informazione e Bioingegneria, Politecnico di Milano Piazza Leonardo da Vinci 32,Dipartimento di Elettronica,Milano,Italy,20133","institution_ids":["https://openalex.org/I93860229"]},{"raw_affiliation_string":"Dipartimento di Elettronica, Informazione e Bioingegneria, Politecnico di Milano Piazza Leonardo da Vinci 32, Milano, Italy","institution_ids":["https://openalex.org/I93860229"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019176108","display_name":"Idil Su Erdenlig","orcid":null},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"\u0130dil Su Erdenli\u011f","raw_affiliation_strings":["Informazione e Bioingegneria, Politecnico di Milano Piazza Leonardo da Vinci 32,Dipartimento di Elettronica,Milano,Italy,20133","Dipartimento di Elettronica, Informazione e Bioingegneria, Politecnico di Milano Piazza Leonardo da Vinci 32, Milano, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Informazione e Bioingegneria, Politecnico di Milano Piazza Leonardo da Vinci 32,Dipartimento di Elettronica,Milano,Italy,20133","institution_ids":["https://openalex.org/I93860229"]},{"raw_affiliation_string":"Dipartimento di Elettronica, Informazione e Bioingegneria, Politecnico di Milano Piazza Leonardo da Vinci 32, Milano, Italy","institution_ids":["https://openalex.org/I93860229"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060263666","display_name":"Andrea Bonarini","orcid":"https://orcid.org/0000-0002-4880-4521"},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Andrea Bonarini","raw_affiliation_strings":["Informazione e Bioingegneria, Politecnico di Milano Piazza Leonardo da Vinci 32,Dipartimento di Elettronica,Milano,Italy,20133","Dipartimento di Elettronica, Informazione e Bioingegneria, Politecnico di Milano Piazza Leonardo da Vinci 32, Milano, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Informazione e Bioingegneria, Politecnico di Milano Piazza Leonardo da Vinci 32,Dipartimento di Elettronica,Milano,Italy,20133","institution_ids":["https://openalex.org/I93860229"]},{"raw_affiliation_string":"Dipartimento di Elettronica, Informazione e Bioingegneria, Politecnico di Milano Piazza Leonardo da Vinci 32, Milano, Italy","institution_ids":["https://openalex.org/I93860229"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I93860229"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1003","last_page":"1009"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9991000294685364,"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":0.9991000294685364,"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/T10621","display_name":"Gene Regulatory Network Analysis","score":0.9800000190734863,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10639","display_name":"Advanced Software Engineering Methodologies","score":0.9674999713897705,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.9064175486564636},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.719866156578064},{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.7196630835533142},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6433463096618652},{"id":"https://openalex.org/keywords/hierarchical-control-system","display_name":"Hierarchical control system","score":0.49254998564720154},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4713767468929291},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4361773133277893},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.43399083614349365},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.41525959968566895},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.2454451322555542}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9064175486564636},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.719866156578064},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.7196630835533142},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6433463096618652},{"id":"https://openalex.org/C124527596","wikidata":"https://www.wikidata.org/wiki/Q17029359","display_name":"Hierarchical control system","level":3,"score":0.49254998564720154},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4713767468929291},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4361773133277893},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.43399083614349365},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.41525959968566895},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2454451322555542},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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":2,"locations":[{"id":"doi:10.1109/iros40897.2019.8968252","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros40897.2019.8968252","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},{"id":"pmh:oai:re.public.polimi.it:11311/1156734","is_oa":true,"landing_page_url":"http://hdl.handle.net/11311/1156734","pdf_url":null,"source":{"id":"https://openalex.org/S4306400312","display_name":"Virtual Community of Pathological Anatomy (University of Castilla La Mancha)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79189158","host_organization_name":"University of Castilla-La Mancha","host_organization_lineage":["https://openalex.org/I79189158"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:re.public.polimi.it:11311/1156734","is_oa":true,"landing_page_url":"http://hdl.handle.net/11311/1156734","pdf_url":null,"source":{"id":"https://openalex.org/S4306400312","display_name":"Virtual Community of Pathological Anatomy (University of Castilla La Mancha)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79189158","host_organization_name":"University of Castilla-La Mancha","host_organization_lineage":["https://openalex.org/I79189158"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1499669280","https://openalex.org/W1771410628","https://openalex.org/W2012587148","https://openalex.org/W2109910161","https://openalex.org/W2121517924","https://openalex.org/W2137104525","https://openalex.org/W2139394304","https://openalex.org/W2144446635","https://openalex.org/W2158548602","https://openalex.org/W2160371091","https://openalex.org/W2606433045","https://openalex.org/W2736601468","https://openalex.org/W2739330054","https://openalex.org/W2774343553","https://openalex.org/W2949267040","https://openalex.org/W2964001908","https://openalex.org/W2964227312","https://openalex.org/W3103182070","https://openalex.org/W4205513846","https://openalex.org/W4300799055","https://openalex.org/W6629881138","https://openalex.org/W6638018090","https://openalex.org/W6680606377","https://openalex.org/W6683443546","https://openalex.org/W6683821272","https://openalex.org/W6727349600","https://openalex.org/W6734215269","https://openalex.org/W6736368053","https://openalex.org/W6740801417","https://openalex.org/W6741002519","https://openalex.org/W6746722632"],"related_works":["https://openalex.org/W2905433371","https://openalex.org/W2888392564","https://openalex.org/W4310278675","https://openalex.org/W4388422664","https://openalex.org/W4390569940","https://openalex.org/W4361193272","https://openalex.org/W2963326959","https://openalex.org/W4388685194","https://openalex.org/W4312407344","https://openalex.org/W2894289927"],"abstract_inverted_index":{"There":[0],"is":[1,34,71,108,117],"an":[2,174],"increasing":[3],"interest":[4,40],"in":[5,18,102,121,173],"Reinforcement":[6,44,52,82,130,162],"Learning":[7,53,83,131,163],"to":[8,73,112,155,169],"solve":[9],"new":[10],"and":[11,20,31,69,97],"more":[12],"challenging":[13],"problems,":[14],"as":[15],"those":[16],"emerging":[17],"robotics":[19],"unmanned":[21],"autonomous":[22],"vehicles.":[23],"To":[24],"face":[25],"these":[26,89],"complex":[27],"systems,":[28],"a":[29,57,127,160],"hierarchical":[30,136,176],"multi-scale":[32],"representation":[33,151],"crucial.":[35],"This":[36],"has":[37],"brought":[38],"the":[39,105,122,135,148,157,167],"on":[41,134],"Hierarchical":[42,81,129,161],"Deep":[43,51],"learning":[45],"systems.":[46],"Despite":[47],"their":[48,78],"successful":[49],"application,":[50],"systems":[54,154],"suffer":[55],"from":[56,88],"variety":[58],"of":[59,67,104,140,152,159],"drawbacks:":[60],"they":[61,65],"are":[62,91],"data":[63],"hungry,":[64],"lack":[66],"interpretability,":[68],"it":[70],"difficult":[72],"derive":[74],"theoretical":[75],"properties":[76],"about":[77],"behavior.":[79],"Classical":[80],"approaches,":[84],"while":[85],"not":[86],"suffering":[87],"drawbacks,":[90],"often":[92,118],"suited":[93],"for":[94],"finite":[95,98],"actions,":[96],"states,":[99],"only.":[100],"Furthermore,":[101],"most":[103],"works,":[106],"there":[107],"no":[109],"systematic":[110],"way":[111],"represent":[113],"domain":[114,171],"knowledge,":[115],"which":[116],"only":[119],"embedded":[120],"reward":[123],"function.":[124],"We":[125,143],"present":[126],"novel":[128],"framework":[132,146],"based":[133],"design":[137],"approach":[138],"typical":[139],"control":[141,153],"theory.":[142],"developed":[144],"our":[145],"extending":[147],"block":[149],"diagram":[150],"fit":[156],"needs":[158],"scenario,":[164],"thus":[165],"giving":[166],"possibility":[168],"integrate":[170],"knowledge":[172],"effective":[175],"architecture.":[177]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2020-02-07T00:00:00"}