{"id":"https://openalex.org/W4285274398","doi":"https://doi.org/10.1007/978-3-031-05936-0_30","title":"Safe Offline Reinforcement Learning Through Hierarchical Policies","display_name":"Safe Offline Reinforcement Learning Through Hierarchical Policies","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4285274398","doi":"https://doi.org/10.1007/978-3-031-05936-0_30"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-031-05936-0_30","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-031-05936-0_30","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"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":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5066867197","display_name":"Shaofan Liu","orcid":"https://orcid.org/0000-0002-2705-7117"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shaofan Liu","raw_affiliation_strings":["School of Computer Science and Technology, East China Normal University, 3663 North Zhongshan Road, Shanghai, 200062, People\u2019s Republic of China","School of Computer Science and Technology, East China Normal University, 3663 North Zhongshan Road, Shanghai, 200062, People's Republic of China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, East China Normal University, 3663 North Zhongshan Road, Shanghai, 200062, People\u2019s Republic of China","institution_ids":["https://openalex.org/I66867065"]},{"raw_affiliation_string":"School of Computer Science and Technology, East China Normal University, 3663 North Zhongshan Road, Shanghai, 200062, People's Republic of China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047846625","display_name":"Shiliang Sun","orcid":"https://orcid.org/0000-0001-7069-3752"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiliang Sun","raw_affiliation_strings":["School of Computer Science and Technology, East China Normal University, 3663 North Zhongshan Road, Shanghai, 200062, People\u2019s Republic of China","School of Computer Science and Technology, East China Normal University, 3663 North Zhongshan Road, Shanghai, 200062, People's Republic of China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, East China Normal University, 3663 North Zhongshan Road, Shanghai, 200062, People\u2019s Republic of China","institution_ids":["https://openalex.org/I66867065"]},{"raw_affiliation_string":"School of Computer Science and Technology, East China Normal University, 3663 North Zhongshan Road, Shanghai, 200062, People's Republic of China","institution_ids":["https://openalex.org/I66867065"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5066867197"],"corresponding_institution_ids":["https://openalex.org/I66867065"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17386265,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"380","last_page":"391"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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":0.9998999834060669,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9901000261306763,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.989799976348877,"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":0.7115010023117065},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.48735982179641724},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.43830406665802},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3301353454589844},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.28341811895370483},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.09835949540138245}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7115010023117065},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.48735982179641724},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.43830406665802},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3301353454589844},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.28341811895370483},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.09835949540138245}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-031-05936-0_30","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-031-05936-0_30","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"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":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W192920577","https://openalex.org/W2064675550","https://openalex.org/W2109910161","https://openalex.org/W2158782408","https://openalex.org/W2594829461","https://openalex.org/W2809290718","https://openalex.org/W2964227312","https://openalex.org/W2997985982","https://openalex.org/W6600728650","https://openalex.org/W6601881253","https://openalex.org/W6602430163","https://openalex.org/W6603732165","https://openalex.org/W6702088316"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2920061524","https://openalex.org/W4310083477","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W1987513656","https://openalex.org/W2072376847","https://openalex.org/W2089013912"],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}