{"id":"https://openalex.org/W4390188105","doi":"https://doi.org/10.1109/icdl55364.2023.10364473","title":"Goal Space Abstraction in Hierarchical Reinforcement Learning via Set-Based Reachability Analysis","display_name":"Goal Space Abstraction in Hierarchical Reinforcement Learning via Set-Based Reachability Analysis","publication_year":2023,"publication_date":"2023-11-09","ids":{"openalex":"https://openalex.org/W4390188105","doi":"https://doi.org/10.1109/icdl55364.2023.10364473"},"language":"en","primary_location":{"id":"doi:10.1109/icdl55364.2023.10364473","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdl55364.2023.10364473","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Development and Learning (ICDL)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://inria.hal.science/hal-04401878v1/file/Zadem2023ICDL.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5081747756","display_name":"Mehdi Zadem","orcid":null},"institutions":[{"id":"https://openalex.org/I142476485","display_name":"\u00c9cole Polytechnique","ror":"https://ror.org/05hy3tk52","country_code":"FR","type":"education","lineage":["https://openalex.org/I142476485","https://openalex.org/I4210145102"]},{"id":"https://openalex.org/I4210139461","display_name":"Laboratoire d'Informatique de l'\u00c9cole Polytechnique","ror":"https://ror.org/04afed728","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I142476485","https://openalex.org/I4210139461","https://openalex.org/I4210145102","https://openalex.org/I4210159245"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Mehdi Zadem","raw_affiliation_strings":["LIX, CNRS, École Polytechnique, Institut Polytechnique de Paris","LIX - Laboratoire d'informatique de l'\u00c9cole polytechnique [Palaiseau] (Route de Saclay 91128 PALAISEAU CEDEX - France)","U2IS - Unit\u00e9 d'Informatique et d'Ing\u00e9nierie des Syst\u00e8mes (828, boulevard des Mar\u00e9chaux, 91762 Palaiseau CEDEX - France)"],"affiliations":[{"raw_affiliation_string":"LIX, CNRS, École Polytechnique, Institut Polytechnique de Paris","institution_ids":["https://openalex.org/I1294671590"]},{"raw_affiliation_string":"LIX - Laboratoire d'informatique de l'\u00c9cole polytechnique [Palaiseau] (Route de Saclay 91128 PALAISEAU CEDEX - France)","institution_ids":["https://openalex.org/I4210139461","https://openalex.org/I142476485"]},{"raw_affiliation_string":"U2IS - Unit\u00e9 d'Informatique et d'Ing\u00e9nierie des Syst\u00e8mes (828, boulevard des Mar\u00e9chaux, 91762 Palaiseau CEDEX - France)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023894417","display_name":"Sergio Mover","orcid":"https://orcid.org/0000-0003-1029-9547"},"institutions":[{"id":"https://openalex.org/I142476485","display_name":"\u00c9cole Polytechnique","ror":"https://ror.org/05hy3tk52","country_code":"FR","type":"education","lineage":["https://openalex.org/I142476485","https://openalex.org/I4210145102"]},{"id":"https://openalex.org/I4210139461","display_name":"Laboratoire d'Informatique de l'\u00c9cole Polytechnique","ror":"https://ror.org/04afed728","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I142476485","https://openalex.org/I4210139461","https://openalex.org/I4210145102","https://openalex.org/I4210159245"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Sergio Mover","raw_affiliation_strings":["LIX, CNRS, École Polytechnique, Institut Polytechnique de Paris","LIX - Laboratoire d'informatique de l'\u00c9cole polytechnique [Palaiseau] (Route de Saclay 91128 PALAISEAU CEDEX - France)"],"affiliations":[{"raw_affiliation_string":"LIX, CNRS, École Polytechnique, Institut Polytechnique de Paris","institution_ids":["https://openalex.org/I1294671590"]},{"raw_affiliation_string":"LIX - Laboratoire d'informatique de l'\u00c9cole polytechnique [Palaiseau] (Route de Saclay 91128 PALAISEAU CEDEX - France)","institution_ids":["https://openalex.org/I4210139461","https://openalex.org/I142476485"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046094611","display_name":"Sao Mai Nguyen","orcid":"https://orcid.org/0000-0003-0929-0019"},"institutions":[{"id":"https://openalex.org/I161929037","display_name":"Universit\u00e9 de Bretagne Occidentale","ror":"https://ror.org/01b8h3982","country_code":"FR","type":"education","lineage":["https://openalex.org/I161929037"]},{"id":"https://openalex.org/I4210127572","display_name":"IMT Atlantique","ror":"https://ror.org/030hj3061","country_code":"FR","type":"education","lineage":["https://openalex.org/I205703379","https://openalex.org/I4210127572"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Sao Mai Nguyen","raw_affiliation_strings":["Flowers Team, U2IS, ENSTA Paris, Institut Polytechnique de Paris & Inria","U2IS - Unit\u00e9 d'Informatique et d'Ing\u00e9nierie des Syst\u00e8mes (828, boulevard des Mar\u00e9chaux, 91762 Palaiseau CEDEX - France)","IMT Atlantique - INFO - D\u00e9partement Informatique (IMT Atlantique - Campus de Brest - Technop\u00f4le Brest-Iroise CS 8381829238 BREST Cedex 3 - France)","Flowers - Flowing Epigenetic Robots and Systems (200, avenue de la Vieille Tour \r\n33405 Talence cedex - France)","Lab-STICC_RAMBO - Equipe Robot interaction, Ambient system, Machine learning, Behaviour, Optimization (France)"],"affiliations":[{"raw_affiliation_string":"Flowers Team, U2IS, ENSTA Paris, Institut Polytechnique de Paris & Inria","institution_ids":[]},{"raw_affiliation_string":"U2IS - Unit\u00e9 d'Informatique et d'Ing\u00e9nierie des Syst\u00e8mes (828, boulevard des Mar\u00e9chaux, 91762 Palaiseau CEDEX - France)","institution_ids":[]},{"raw_affiliation_string":"IMT Atlantique - INFO - D\u00e9partement Informatique (IMT Atlantique - Campus de Brest - Technop\u00f4le Brest-Iroise CS 8381829238 BREST Cedex 3 - France)","institution_ids":["https://openalex.org/I4210127572"]},{"raw_affiliation_string":"Flowers - Flowing Epigenetic Robots and Systems (200, avenue de la Vieille Tour \r\n33405 Talence cedex - France)","institution_ids":[]},{"raw_affiliation_string":"Lab-STICC_RAMBO - Equipe Robot interaction, Ambient system, Machine learning, Behaviour, Optimization (France)","institution_ids":["https://openalex.org/I161929037"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5081747756"],"corresponding_institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I142476485","https://openalex.org/I4210139461"],"apc_list":null,"apc_paid":null,"fwci":0.8832,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.80104333,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"423","last_page":"428"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.993399977684021,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9848999977111816,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.7987765073776245},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7570766806602478},{"id":"https://openalex.org/keywords/reachability","display_name":"Reachability","score":0.7474246025085449},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6627657413482666},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6370433568954468},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5516583919525146},{"id":"https://openalex.org/keywords/abstraction","display_name":"Abstraction","score":0.5364322066307068},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.5292717218399048},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4716970920562744},{"id":"https://openalex.org/keywords/knowledge-representation-and-reasoning","display_name":"Knowledge representation and reasoning","score":0.4577263295650482},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.4433113932609558},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.43162864446640015},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.42141205072402954},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.20157703757286072},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09910568594932556}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7987765073776245},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7570766806602478},{"id":"https://openalex.org/C136643341","wikidata":"https://www.wikidata.org/wiki/Q1361526","display_name":"Reachability","level":2,"score":0.7474246025085449},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6627657413482666},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6370433568954468},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5516583919525146},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.5364322066307068},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.5292717218399048},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4716970920562744},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.4577263295650482},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.4433113932609558},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.43162864446640015},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.42141205072402954},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.20157703757286072},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09910568594932556},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icdl55364.2023.10364473","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdl55364.2023.10364473","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Development and Learning (ICDL)","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-04401878v1","is_oa":true,"landing_page_url":"https://inria.hal.science/hal-04401878","pdf_url":"https://inria.hal.science/hal-04401878v1/file/Zadem2023ICDL.pdf","source":{"id":"https://openalex.org/S4406922461","display_name":"SPIRE - Sciences Po Institutional REpository","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"ICDL 2023 - 22nd IEEE International Conference on Development and Learning, Nov 2023, Macau, China. pp.423-428, ⟨10.1109/ICDL55364.2023.10364473⟩","raw_type":"Conference papers"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-04401878v1","is_oa":true,"landing_page_url":"https://inria.hal.science/hal-04401878","pdf_url":"https://inria.hal.science/hal-04401878v1/file/Zadem2023ICDL.pdf","source":{"id":"https://openalex.org/S4406922461","display_name":"SPIRE - Sciences Po Institutional REpository","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"ICDL 2023 - 22nd IEEE International Conference on Development and Learning, Nov 2023, Macau, China. pp.423-428, ⟨10.1109/ICDL55364.2023.10364473⟩","raw_type":"Conference papers"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/13","score":0.4000000059604645,"display_name":"Climate action"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4390188105.pdf","grobid_xml":"https://content.openalex.org/works/W4390188105.grobid-xml"},"referenced_works_count":44,"referenced_works":["https://openalex.org/W1498432697","https://openalex.org/W1592847719","https://openalex.org/W1673310716","https://openalex.org/W2068361557","https://openalex.org/W2109910161","https://openalex.org/W2441459262","https://openalex.org/W2521274174","https://openalex.org/W2794609696","https://openalex.org/W2895453875","https://openalex.org/W2899455150","https://openalex.org/W2949267040","https://openalex.org/W2950531002","https://openalex.org/W2950614095","https://openalex.org/W2963262099","https://openalex.org/W2963321092","https://openalex.org/W2963475757","https://openalex.org/W2963864421","https://openalex.org/W3036125317","https://openalex.org/W3037476194","https://openalex.org/W3105358648","https://openalex.org/W3128416529","https://openalex.org/W3139376843","https://openalex.org/W4205950066","https://openalex.org/W4288331462","https://openalex.org/W4289441014","https://openalex.org/W4298857966","https://openalex.org/W4390188105","https://openalex.org/W6616173779","https://openalex.org/W6637131181","https://openalex.org/W6637967152","https://openalex.org/W6683821272","https://openalex.org/W6684921986","https://openalex.org/W6703271639","https://openalex.org/W6726913060","https://openalex.org/W6734215269","https://openalex.org/W6752089545","https://openalex.org/W6754957883","https://openalex.org/W6755459604","https://openalex.org/W6756293349","https://openalex.org/W6762868464","https://openalex.org/W6764173040","https://openalex.org/W6779715229","https://openalex.org/W6790486821","https://openalex.org/W6791739513"],"related_works":["https://openalex.org/W2127267268","https://openalex.org/W2136512912","https://openalex.org/W2067910792","https://openalex.org/W2156446763","https://openalex.org/W2150194458","https://openalex.org/W2143461633","https://openalex.org/W4321471459","https://openalex.org/W2889071233","https://openalex.org/W2380814829","https://openalex.org/W2387511021"],"abstract_inverted_index":{"Open-ended":[0],"learning":[1],"benefits":[2],"immensely":[3],"from":[4],"the":[5,26,65,97,109,127,137,149],"use":[6],"of":[7,89,132],"symbolic":[8,35,53,119],"methods":[9],"for":[10,20,76,122],"goal":[11,45,54,77,110,138],"representation":[12,55,82,111,151],"as":[13,40,64],"they":[14,41],"offer":[15],"ways":[16],"to":[17,125,135],"structure":[18],"knowledge":[19],"efficient":[21,159],"and":[22,112,134,155],"transferable":[23],"learning.":[24,160],"However,":[25],"existing":[27],"Hierarchical":[28],"Reinforcement":[29],"Learning":[30],"(HRL)":[31],"approaches":[32],"relying":[33],"on":[34,144],"reasoning":[36],"are":[37],"often":[38],"limited":[39],"require":[42],"a":[43,52,73,101,113],"manual":[44],"representation.":[46,139],"The":[47,116],"challenge":[48],"in":[49,96,157],"autonomously":[50],"discovering":[51],"is":[56,152],"that":[57,83,92,105],"it":[58],"must":[59],"preserve":[60],"critical":[61],"information,":[62],"such":[63],"environment":[66,90],"dynamics.":[67],"In":[68],"this":[69],"paper,":[70],"we":[71],"propose":[72],"developmental":[74],"mechanism":[75],"discovery":[78],"via":[79],"an":[80],"emergent":[81],"abstracts":[84],"(i.e.,":[85],"groups":[86],"together)":[87],"sets":[88,131],"states":[91,133],"have":[93],"similar":[94],"roles":[95],"task.":[98],"We":[99,140],"introduce":[100],"Feudal":[102],"HRL":[103],"algorithm":[104,117],"concurrently":[106],"learns":[107],"both":[108],"hierarchical":[114],"policy.":[115],"uses":[118],"reachability":[120],"analysis":[121],"neural":[123],"networks":[124],"approximate":[126],"transition":[128],"relation":[129],"among":[130],"refine":[136],"evaluate":[141],"our":[142],"approach":[143],"complex":[145],"navigation":[146],"tasks,":[147],"showing":[148],"learned":[150],"interpretable,":[153],"transferrable":[154],"results":[156],"data":[158]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2026-03-14T08:43:22.919905","created_date":"2023-12-26T00:00:00"}