{"id":"https://openalex.org/W3187158686","doi":"https://doi.org/10.24963/ijcai.2021/681","title":"Deep Reinforcement Learning with Hierarchical Structures","display_name":"Deep Reinforcement Learning with Hierarchical Structures","publication_year":2021,"publication_date":"2021-08-01","ids":{"openalex":"https://openalex.org/W3187158686","doi":"https://doi.org/10.24963/ijcai.2021/681","mag":"3187158686"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2021/681","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2021/681","pdf_url":"https://www.ijcai.org/proceedings/2021/0681.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2021/0681.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100406610","display_name":"Siyuan Li","orcid":"https://orcid.org/0000-0001-7158-2376"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Siyuan Li","raw_affiliation_strings":["Institute for Interdisciplinary Information Sciences, Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Interdisciplinary Information Sciences, Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5100406610"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4899","last_page":"4900"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9873999953269958,"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/T10603","display_name":"Smart Grid Energy Management","score":0.9781000018119812,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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/reinforcement-learning","display_name":"Reinforcement learning","score":0.9254260063171387},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7715128064155579},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5490666627883911},{"id":"https://openalex.org/keywords/horizon","display_name":"Horizon","score":0.5069897174835205},{"id":"https://openalex.org/keywords/work","display_name":"Work (physics)","score":0.44218647480010986},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.41577237844467163},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3519742488861084},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1253809928894043},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06773197650909424}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9254260063171387},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7715128064155579},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5490666627883911},{"id":"https://openalex.org/C159176650","wikidata":"https://www.wikidata.org/wiki/Q43261","display_name":"Horizon","level":2,"score":0.5069897174835205},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.44218647480010986},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.41577237844467163},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3519742488861084},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1253809928894043},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06773197650909424},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2021/681","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2021/681","pdf_url":"https://www.ijcai.org/proceedings/2021/0681.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2021/681","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2021/681","pdf_url":"https://www.ijcai.org/proceedings/2021/0681.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/8","score":0.4300000071525574,"display_name":"Decent work and economic growth"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3187158686.pdf","grobid_xml":"https://content.openalex.org/works/W3187158686.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W1974043469","https://openalex.org/W2109910161","https://openalex.org/W2133040789","https://openalex.org/W2157364932","https://openalex.org/W2158782408","https://openalex.org/W2523728418","https://openalex.org/W2575705757","https://openalex.org/W2606433045","https://openalex.org/W2760355785","https://openalex.org/W2807238303","https://openalex.org/W2950614095","https://openalex.org/W2963065769","https://openalex.org/W2963438456","https://openalex.org/W2963761387","https://openalex.org/W2964227312","https://openalex.org/W3013618273","https://openalex.org/W3034956653","https://openalex.org/W3128416529","https://openalex.org/W3170298552","https://openalex.org/W4288093623","https://openalex.org/W4288289109","https://openalex.org/W4289441014","https://openalex.org/W6755854181","https://openalex.org/W6803771590"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W3084456289","https://openalex.org/W2024136090","https://openalex.org/W4391331176","https://openalex.org/W2031695474","https://openalex.org/W2586732548","https://openalex.org/W3049728571"],"abstract_inverted_index":{"Hierarchical":[0],"reinforcement":[1],"learning":[2],"(HRL),":[3],"which":[4],"enables":[5],"control":[6],"at":[7],"multiple":[8],"time":[9],"scales,":[10],"is":[11],"a":[12],"promising":[13],"paradigm":[14],"to":[15],"solve":[16],"challenging":[17],"and":[18,31,34],"long-horizon":[19],"tasks.":[20],"In":[21],"this":[22],"paper,":[23],"we":[24],"briefly":[25],"introduce":[26],"our":[27],"work":[28],"in":[29],"bottom-up":[30],"top-down":[32],"HRL":[33],"outline":[35],"the":[36],"directions":[37],"for":[38],"future":[39],"work.":[40]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}