{"id":"https://openalex.org/W4320915428","doi":"https://doi.org/10.1007/978-981-99-0272-9_15","title":"Hierarchical Policies of\u00a0Subgoals for\u00a0Safe Deep Reinforcement Learning","display_name":"Hierarchical Policies of\u00a0Subgoals for\u00a0Safe Deep Reinforcement Learning","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4320915428","doi":"https://doi.org/10.1007/978-981-99-0272-9_15"},"language":"en","primary_location":{"id":"doi:10.1007/978-981-99-0272-9_15","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-981-99-0272-9_15","pdf_url":null,"source":{"id":"https://openalex.org/S2764900261","display_name":"Communications in computer and information science","issn_l":"1865-0929","issn":["1865-0929","1865-0937"],"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":"Communications in Computer and Information 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/A5055843324","display_name":"Fumin Yu","orcid":"https://orcid.org/0000-0003-4812-0549"},"institutions":[{"id":"https://openalex.org/I173759888","display_name":"Hunan Normal University","ror":"https://ror.org/053w1zy07","country_code":"CN","type":"education","lineage":["https://openalex.org/I173759888"]},{"id":"https://openalex.org/I3130607311","display_name":"Changsha Normal University","ror":"https://ror.org/02sqk3z62","country_code":"CN","type":"education","lineage":["https://openalex.org/I3130607311"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fumin Yu","raw_affiliation_strings":["College of Information Science and Engineering, Hunan Normal University, Changsha, 410081, China"],"raw_orcid":"https://orcid.org/0000-0003-4812-0549","affiliations":[{"raw_affiliation_string":"College of Information Science and Engineering, Hunan Normal University, Changsha, 410081, China","institution_ids":["https://openalex.org/I3130607311","https://openalex.org/I173759888"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101534260","display_name":"Feng Gao","orcid":"https://orcid.org/0000-0002-1240-100X"},"institutions":[{"id":"https://openalex.org/I173759888","display_name":"Hunan Normal University","ror":"https://ror.org/053w1zy07","country_code":"CN","type":"education","lineage":["https://openalex.org/I173759888"]},{"id":"https://openalex.org/I3130607311","display_name":"Changsha Normal University","ror":"https://ror.org/02sqk3z62","country_code":"CN","type":"education","lineage":["https://openalex.org/I3130607311"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Gao","raw_affiliation_strings":["College of Information Science and Engineering, Hunan Normal University, Changsha, 410081, China"],"raw_orcid":"https://orcid.org/0000-0002-1240-100X","affiliations":[{"raw_affiliation_string":"College of Information Science and Engineering, Hunan Normal University, Changsha, 410081, China","institution_ids":["https://openalex.org/I3130607311","https://openalex.org/I173759888"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068307497","display_name":"Yuan Yao","orcid":"https://orcid.org/0000-0002-1174-940X"},"institutions":[{"id":"https://openalex.org/I173759888","display_name":"Hunan Normal University","ror":"https://ror.org/053w1zy07","country_code":"CN","type":"education","lineage":["https://openalex.org/I173759888"]},{"id":"https://openalex.org/I3130607311","display_name":"Changsha Normal University","ror":"https://ror.org/02sqk3z62","country_code":"CN","type":"education","lineage":["https://openalex.org/I3130607311"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yao Yuan","raw_affiliation_strings":["College of Information Science and Engineering, Hunan Normal University, Changsha, 410081, China"],"raw_orcid":"https://orcid.org/0000-0002-1174-940X","affiliations":[{"raw_affiliation_string":"College of Information Science and Engineering, Hunan Normal University, Changsha, 410081, China","institution_ids":["https://openalex.org/I3130607311","https://openalex.org/I173759888"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059251513","display_name":"Xiaofei Xing","orcid":"https://orcid.org/0000-0002-2486-8379"},"institutions":[{"id":"https://openalex.org/I37987034","display_name":"Guangzhou University","ror":"https://ror.org/05ar8rn06","country_code":"CN","type":"education","lineage":["https://openalex.org/I37987034"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaofei Xing","raw_affiliation_strings":["School of Computer Science and Cyber Engineering, Guangzhou University, Guangzhou, 510006, China"],"raw_orcid":"https://orcid.org/0000-0002-2486-8379","affiliations":[{"raw_affiliation_string":"School of Computer Science and Cyber Engineering, Guangzhou University, Guangzhou, 510006, China","institution_ids":["https://openalex.org/I37987034"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003296429","display_name":"Yinglong Dai","orcid":"https://orcid.org/0000-0001-5913-8774"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yinglong Dai","raw_affiliation_strings":["College of Liberal Arts and Sciences, National University of Defense Technology, Changsha, 410073, China","Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing, Changsha, 410081, China"],"raw_orcid":"https://orcid.org/0000-0001-5913-8774","affiliations":[{"raw_affiliation_string":"College of Liberal Arts and Sciences, National University of Defense Technology, Changsha, 410073, China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing, Changsha, 410081, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5003296429"],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.04193155,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"220","last_page":"232"},"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.987500011920929,"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":0.9835000038146973,"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":0.8946026563644409},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.83256995677948},{"id":"https://openalex.org/keywords/safer","display_name":"SAFER","score":0.8106653094291687},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7554106712341309},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6058129072189331},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.566839873790741},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5078828930854797},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.43493491411209106},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.10345464944839478},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10202518105506897}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8946026563644409},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.83256995677948},{"id":"https://openalex.org/C2776654903","wikidata":"https://www.wikidata.org/wiki/Q2601463","display_name":"SAFER","level":2,"score":0.8106653094291687},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7554106712341309},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6058129072189331},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.566839873790741},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5078828930854797},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43493491411209106},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.10345464944839478},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10202518105506897},{"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/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-981-99-0272-9_15","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-981-99-0272-9_15","pdf_url":null,"source":{"id":"https://openalex.org/S2764900261","display_name":"Communications in computer and information science","issn_l":"1865-0929","issn":["1865-0929","1865-0937"],"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":"Communications in Computer and Information Science","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.8100000023841858}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W2145339207","https://openalex.org/W2257979135","https://openalex.org/W2769883686","https://openalex.org/W2788781499","https://openalex.org/W2799544270","https://openalex.org/W3102899483","https://openalex.org/W4214485088","https://openalex.org/W4214630528","https://openalex.org/W4214702410","https://openalex.org/W4214760433","https://openalex.org/W6740801417"],"related_works":["https://openalex.org/W2953205341","https://openalex.org/W2092643327","https://openalex.org/W235065745","https://openalex.org/W2029935773","https://openalex.org/W2787754950","https://openalex.org/W1572215850","https://openalex.org/W1985775355","https://openalex.org/W2352115286","https://openalex.org/W2476350415","https://openalex.org/W4256172809"],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
