{"id":"https://openalex.org/W4212996499","doi":"https://doi.org/10.3390/make4010009","title":"Hierarchical Reinforcement Learning: A Survey and Open Research Challenges","display_name":"Hierarchical Reinforcement Learning: A Survey and Open Research Challenges","publication_year":2022,"publication_date":"2022-02-17","ids":{"openalex":"https://openalex.org/W4212996499","doi":"https://doi.org/10.3390/make4010009"},"language":"en","primary_location":{"id":"doi:10.3390/make4010009","is_oa":true,"landing_page_url":"https://doi.org/10.3390/make4010009","pdf_url":"https://www.mdpi.com/2504-4990/4/1/9/pdf?version=1645768480","source":{"id":"https://openalex.org/S4210213891","display_name":"Machine Learning and Knowledge Extraction","issn_l":"2504-4990","issn":["2504-4990"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning and Knowledge Extraction","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2504-4990/4/1/9/pdf?version=1645768480","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5046724185","display_name":"Matthias Hutsebaut-Buysse","orcid":"https://orcid.org/0000-0001-6091-294X"},"institutions":[{"id":"https://openalex.org/I149213910","display_name":"University of Antwerp","ror":"https://ror.org/008x57b05","country_code":"BE","type":"education","lineage":["https://openalex.org/I149213910"]}],"countries":["BE"],"is_corresponding":true,"raw_author_name":"Matthias Hutsebaut-Buysse","raw_affiliation_strings":["Department of Computer Science, University of Antwerp\u2014imec, Sint-Pietersvliet 7, 2000 Antwerp, Belgium"],"raw_orcid":"https://orcid.org/0000-0001-6091-294X","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Antwerp\u2014imec, Sint-Pietersvliet 7, 2000 Antwerp, Belgium","institution_ids":["https://openalex.org/I149213910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084961388","display_name":"Kevin Mets","orcid":"https://orcid.org/0000-0002-4812-4841"},"institutions":[{"id":"https://openalex.org/I149213910","display_name":"University of Antwerp","ror":"https://ror.org/008x57b05","country_code":"BE","type":"education","lineage":["https://openalex.org/I149213910"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Kevin Mets","raw_affiliation_strings":["Department of Computer Science, University of Antwerp\u2014imec, Sint-Pietersvliet 7, 2000 Antwerp, Belgium"],"raw_orcid":"https://orcid.org/0000-0002-4812-4841","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Antwerp\u2014imec, Sint-Pietersvliet 7, 2000 Antwerp, Belgium","institution_ids":["https://openalex.org/I149213910"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049021976","display_name":"Steven Latr\u00e9","orcid":"https://orcid.org/0000-0003-0351-1714"},"institutions":[{"id":"https://openalex.org/I149213910","display_name":"University of Antwerp","ror":"https://ror.org/008x57b05","country_code":"BE","type":"education","lineage":["https://openalex.org/I149213910"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Steven Latr\u00e9","raw_affiliation_strings":["Department of Computer Science, University of Antwerp\u2014imec, Sint-Pietersvliet 7, 2000 Antwerp, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Antwerp\u2014imec, Sint-Pietersvliet 7, 2000 Antwerp, Belgium","institution_ids":["https://openalex.org/I149213910"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5046724185"],"corresponding_institution_ids":["https://openalex.org/I149213910"],"apc_list":{"value":1400,"currency":"CHF","value_usd":1559},"apc_paid":{"value":1400,"currency":"CHF","value_usd":1559},"fwci":11.1313,"has_fulltext":true,"cited_by_count":116,"citation_normalized_percentile":{"value":0.98778986,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"4","issue":"1","first_page":"172","last_page":"221"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9983999729156494,"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":0.9983999729156494,"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":0.9868000149726868,"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/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.9652000069618225,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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":0.8593701124191284},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.822769045829773},{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.7902863621711731},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.6405245065689087},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6143083572387695},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.595024049282074},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5554550290107727},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5330774784088135},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4501282870769501},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.4219483733177185},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.417595237493515},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.35309678316116333},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09166130423545837}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8593701124191284},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.822769045829773},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.7902863621711731},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.6405245065689087},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6143083572387695},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.595024049282074},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5554550290107727},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5330774784088135},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4501282870769501},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4219483733177185},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.417595237493515},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.35309678316116333},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09166130423545837},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3390/make4010009","is_oa":true,"landing_page_url":"https://doi.org/10.3390/make4010009","pdf_url":"https://www.mdpi.com/2504-4990/4/1/9/pdf?version=1645768480","source":{"id":"https://openalex.org/S4210213891","display_name":"Machine Learning and Knowledge Extraction","issn_l":"2504-4990","issn":["2504-4990"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning and Knowledge Extraction","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:540fdb71884e45e6b5b548b45efc01e3","is_oa":false,"landing_page_url":"https://doaj.org/article/540fdb71884e45e6b5b548b45efc01e3","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Machine Learning and Knowledge Extraction, Vol 4, Iss 1, Pp 172-221 (2022)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/2504-4990/4/1/9/","is_oa":true,"landing_page_url":"https://dx.doi.org/10.3390/make4010009","pdf_url":null,"source":{"id":"https://openalex.org/S4306400947","display_name":"MDPI (MDPI AG)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210097602","host_organization_name":"Multidisciplinary Digital Publishing Institute (Switzerland)","host_organization_lineage":["https://openalex.org/I4210097602"],"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":"Machine Learning and Knowledge Extraction; Volume 4; Issue 1; Pages: 172-221","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/make4010009","is_oa":true,"landing_page_url":"https://doi.org/10.3390/make4010009","pdf_url":"https://www.mdpi.com/2504-4990/4/1/9/pdf?version=1645768480","source":{"id":"https://openalex.org/S4210213891","display_name":"Machine Learning and Knowledge Extraction","issn_l":"2504-4990","issn":["2504-4990"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning and Knowledge Extraction","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.8100000023841858,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320324595","display_name":"Universiteit Antwerpen","ror":"https://ror.org/008x57b05"},{"id":"https://openalex.org/F4320327336","display_name":"Vlaamse regering","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4212996499.pdf","grobid_xml":"https://content.openalex.org/works/W4212996499.grobid-xml"},"referenced_works_count":212,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W139620917","https://openalex.org/W141456974","https://openalex.org/W142462678","https://openalex.org/W189510620","https://openalex.org/W1433129784","https://openalex.org/W1494114146","https://openalex.org/W1507087299","https://openalex.org/W1536680647","https://openalex.org/W1536990779","https://openalex.org/W1540462738","https://openalex.org/W1556824961","https://openalex.org/W1569296262","https://openalex.org/W1592847719","https://openalex.org/W1598052524","https://openalex.org/W1678414046","https://openalex.org/W1777239053","https://openalex.org/W1786044565","https://openalex.org/W1845972764","https://openalex.org/W1849277567","https://openalex.org/W1905882502","https://openalex.org/W1931877416","https://openalex.org/W1933349210","https://openalex.org/W1968768508","https://openalex.org/W1976268573","https://openalex.org/W1977655452","https://openalex.org/W1979071892","https://openalex.org/W1981627423","https://openalex.org/W1986014385","https://openalex.org/W2012036715","https://openalex.org/W2017611213","https://openalex.org/W2034806191","https://openalex.org/W2056354534","https://openalex.org/W2056653303","https://openalex.org/W2064675550","https://openalex.org/W2073266192","https://openalex.org/W2076063813","https://openalex.org/W2090170171","https://openalex.org/W2091565802","https://openalex.org/W2097117768","https://openalex.org/W2098774185","https://openalex.org/W2100495367","https://openalex.org/W2101355568","https://openalex.org/W2107628283","https://openalex.org/W2107726111","https://openalex.org/W2108535023","https://openalex.org/W2108734173","https://openalex.org/W2109910161","https://openalex.org/W2110119381","https://openalex.org/W2111020392","https://openalex.org/W2111625828","https://openalex.org/W2112739286","https://openalex.org/W2112796928","https://openalex.org/W2113501460","https://openalex.org/W2114580749","https://openalex.org/W2116341502","https://openalex.org/W2119717200","https://openalex.org/W2120346334","https://openalex.org/W2120501001","https://openalex.org/W2121517924","https://openalex.org/W2129670787","https://openalex.org/W2130535800","https://openalex.org/W2132622533","https://openalex.org/W2133458291","https://openalex.org/W2137766593","https://openalex.org/W2141559645","https://openalex.org/W2143435603","https://openalex.org/W2143958939","https://openalex.org/W2145339207","https://openalex.org/W2149933564","https://openalex.org/W2150468603","https://openalex.org/W2153385324","https://openalex.org/W2153668164","https://openalex.org/W2153947321","https://openalex.org/W2155007355","https://openalex.org/W2155027007","https://openalex.org/W2157331557","https://openalex.org/W2158782408","https://openalex.org/W2160815625","https://openalex.org/W2161252410","https://openalex.org/W2163605009","https://openalex.org/W2167590754","https://openalex.org/W2173248099","https://openalex.org/W2173564293","https://openalex.org/W2174803659","https://openalex.org/W2194775991","https://openalex.org/W2251007294","https://openalex.org/W2257979135","https://openalex.org/W2260756217","https://openalex.org/W2295582178","https://openalex.org/W2296073425","https://openalex.org/W2334782222","https://openalex.org/W2335959470","https://openalex.org/W2342662072","https://openalex.org/W2480004914","https://openalex.org/W2498991332","https://openalex.org/W2546571074","https://openalex.org/W2551887912","https://openalex.org/W2554984891","https://openalex.org/W2559108640","https://openalex.org/W2560647685","https://openalex.org/W2592215206","https://openalex.org/W2592929672","https://openalex.org/W2594103415","https://openalex.org/W2594829461","https://openalex.org/W2604763608","https://openalex.org/W2605102581","https://openalex.org/W2606433045","https://openalex.org/W2624614404","https://openalex.org/W2739473244","https://openalex.org/W2746553466","https://openalex.org/W2751325639","https://openalex.org/W2754517384","https://openalex.org/W2761873684","https://openalex.org/W2765302304","https://openalex.org/W2765308067","https://openalex.org/W2766354286","https://openalex.org/W2766736793","https://openalex.org/W2771734675","https://openalex.org/W2780057514","https://openalex.org/W2781726626","https://openalex.org/W2785342287","https://openalex.org/W2785998395","https://openalex.org/W2788781499","https://openalex.org/W2790979755","https://openalex.org/W2796206912","https://openalex.org/W2796290181","https://openalex.org/W2803281228","https://openalex.org/W2810602713","https://openalex.org/W2877093712","https://openalex.org/W2890803796","https://openalex.org/W2894605519","https://openalex.org/W2896457183","https://openalex.org/W2900928600","https://openalex.org/W2903181768","https://openalex.org/W2905101140","https://openalex.org/W2905915491","https://openalex.org/W2907502844","https://openalex.org/W2919115771","https://openalex.org/W2932075841","https://openalex.org/W2948978827","https://openalex.org/W2951725892","https://openalex.org/W2962736495","https://openalex.org/W2962764167","https://openalex.org/W2962826786","https://openalex.org/W2962977206","https://openalex.org/W2962991582","https://openalex.org/W2963037989","https://openalex.org/W2963142324","https://openalex.org/W2963305465","https://openalex.org/W2963523627","https://openalex.org/W2963830168","https://openalex.org/W2963847595","https://openalex.org/W2963871073","https://openalex.org/W2963920537","https://openalex.org/W2964118262","https://openalex.org/W2964227312","https://openalex.org/W2964350391","https://openalex.org/W2964915587","https://openalex.org/W2971273232","https://openalex.org/W2973049979","https://openalex.org/W2982316857","https://openalex.org/W2995058766","https://openalex.org/W2995363872","https://openalex.org/W2995894173","https://openalex.org/W3006702859","https://openalex.org/W3041202696","https://openalex.org/W3097026541","https://openalex.org/W3099518626","https://openalex.org/W3100366369","https://openalex.org/W3100789280","https://openalex.org/W3104515094","https://openalex.org/W4299335686","https://openalex.org/W6616173779","https://openalex.org/W6629881138","https://openalex.org/W6630044934","https://openalex.org/W6630103346","https://openalex.org/W6635516443","https://openalex.org/W6638018090","https://openalex.org/W6639118987","https://openalex.org/W6640963894","https://openalex.org/W6676560026","https://openalex.org/W6676893594","https://openalex.org/W6679671054","https://openalex.org/W6681439324","https://openalex.org/W6681745991","https://openalex.org/W6682753738","https://openalex.org/W6682849425","https://openalex.org/W6683033130","https://openalex.org/W6683195989","https://openalex.org/W6683443546","https://openalex.org/W6683821272","https://openalex.org/W6685664872","https://openalex.org/W6712173889","https://openalex.org/W6718092244","https://openalex.org/W6730111887","https://openalex.org/W6739193204","https://openalex.org/W6740092555","https://openalex.org/W6741200461","https://openalex.org/W6744935223","https://openalex.org/W6744991969","https://openalex.org/W6748687944","https://openalex.org/W6748972340","https://openalex.org/W6751720535","https://openalex.org/W6753925943","https://openalex.org/W6754957883","https://openalex.org/W6754978010","https://openalex.org/W6760015939","https://openalex.org/W6760755450","https://openalex.org/W6767084887","https://openalex.org/W6780170931","https://openalex.org/W6785613663"],"related_works":["https://openalex.org/W2905433371","https://openalex.org/W2888392564","https://openalex.org/W4310278675","https://openalex.org/W4225571923","https://openalex.org/W3212257828","https://openalex.org/W2999580272","https://openalex.org/W4297873223","https://openalex.org/W3009457412","https://openalex.org/W2350784623","https://openalex.org/W2126211886"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,50,153],"(RL)":[2],"allows":[3,131],"an":[4,14,40],"agent":[5],"to":[6,60,95,118,133,142,157],"solve":[7],"sequential":[8],"decision-making":[9],"problems":[10],"by":[11],"interacting":[12],"with":[13,45,163],"environment":[15],"in":[16,58,93,100,136],"a":[17,85,112,137,171],"trial-and-error":[18],"fashion.":[19],"When":[20],"these":[21,62],"environments":[22],"are":[23],"very":[24,36],"complex,":[25],"pure":[26],"random":[27],"exploration":[28],"of":[29,43,54,75,87,147,151,173],"possible":[30],"solutions":[31],"often":[32,97],"fails,":[33],"or":[34],"is":[35],"sample":[37],"inefficient,":[38],"requiring":[39],"unreasonable":[41],"amount":[42],"interaction":[44,162],"the":[46,67,107,127,145],"environment.":[47],"Hierarchical":[48],"reinforcement":[49],"(HRL)":[51],"utilizes":[52],"forms":[53],"temporal-":[55],"and":[56,72,121,155],"state-abstractions":[57],"order":[59,141],"tackle":[61],"challenges,":[63],"while":[64],"simultaneously":[65,152],"paving":[66],"road":[68],"for":[69],"behavior":[70],"reuse":[71],"increased":[73],"interpretability":[74],"RL":[76],"systems.":[77],"In":[78,140],"this":[79],"survey":[80],"paper":[81],"we":[82,125,168],"first":[83],"introduce":[84,106,126],"selection":[86],"problem-specific":[88],"approaches,":[89],"which":[90,110,130],"provided":[91],"insight":[92],"how":[94,156],"utilize":[96],"handcrafted":[98],"abstractions":[99,117,154],"specific":[101],"task":[102],"settings.":[103],"We":[104],"then":[105],"Options":[108],"framework,":[109],"provides":[111],"more":[113],"generic":[114],"approach,":[115,129],"allowing":[116],"be":[119,134],"discovered":[120],"learned":[122],"semi-automatically.":[123],"Afterwards":[124],"goal-conditional":[128],"sub-behaviors":[132],"embedded":[135],"continuous":[138],"space.":[139],"further":[143],"advance":[144],"development":[146],"HRL":[148],"agents,":[149],"capable":[150],"use":[158],"them,":[159],"solely":[160],"from":[161],"complex":[164],"high":[165],"dimensional":[166],"environments,":[167],"also":[169],"identify":[170],"set":[172],"promising":[174],"research":[175],"directions.":[176]},"counts_by_year":[{"year":2026,"cited_by_count":20},{"year":2025,"cited_by_count":43},{"year":2024,"cited_by_count":28},{"year":2023,"cited_by_count":20},{"year":2022,"cited_by_count":5}],"updated_date":"2026-08-12T21:12:35.861297","created_date":"2025-10-10T00:00:00"}