{"id":"https://openalex.org/W3003931103","doi":"https://doi.org/10.5555/2789272.2886795","title":"A comprehensive survey on safe reinforcement learning","display_name":"A comprehensive survey on safe reinforcement learning","publication_year":2015,"publication_date":"2015-01-01","ids":{"openalex":"https://openalex.org/W3003931103","doi":"https://doi.org/10.5555/2789272.2886795","mag":"3003931103"},"language":"en","primary_location":{"id":"mag:3003931103","is_oa":false,"landing_page_url":"https://dl.acm.org/doi/10.5555/2789272.2886795","pdf_url":null,"source":{"id":"https://openalex.org/S118988714","display_name":"Journal of Machine Learning Research","issn_l":"1532-4435","issn":["1532-4435","1533-7928"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310315718","host_organization_name":"The MIT Press","host_organization_lineage":["https://openalex.org/P4310315718"],"host_organization_lineage_names":["The MIT Press"],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Journal of Machine Learning Research","raw_type":null},"type":"article","indexed_in":[],"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/A5058348129","display_name":"Garc\u00edaJavier","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Garc\u00edaJavier","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5000445261","display_name":"Fern\u00e1ndezFernando","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fern\u00e1ndezFernando","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.0258,"has_fulltext":false,"cited_by_count":63,"citation_normalized_percentile":{"value":0.8336076,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10763","display_name":"Digital Transformation in Industry","score":0.5253999829292297,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10763","display_name":"Digital Transformation in Industry","score":0.5253999829292297,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10876","display_name":"Fault Detection and Control Systems","score":0.498199999332428,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.46230000257492065,"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":0.876004695892334},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6108341813087463},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5657066702842712},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4875456690788269},{"id":"https://openalex.org/keywords/error-driven-learning","display_name":"Error-driven learning","score":0.4819931089878082},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48047390580177307},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.45247095823287964},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.14630505442619324}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.876004695892334},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6108341813087463},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5657066702842712},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4875456690788269},{"id":"https://openalex.org/C47932503","wikidata":"https://www.wikidata.org/wiki/Q5395689","display_name":"Error-driven learning","level":3,"score":0.4819931089878082},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48047390580177307},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45247095823287964},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14630505442619324},{"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":"mag:3003931103","is_oa":false,"landing_page_url":"https://dl.acm.org/doi/10.5555/2789272.2886795","pdf_url":null,"source":{"id":"https://openalex.org/S118988714","display_name":"Journal of Machine Learning Research","issn_l":"1532-4435","issn":["1532-4435","1533-7928"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310315718","host_organization_name":"The MIT Press","host_organization_lineage":["https://openalex.org/P4310315718"],"host_organization_lineage_names":["The MIT Press"],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":"Journal of Machine Learning Research","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.4000000059604645,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W1977655452","https://openalex.org/W2946429108","https://openalex.org/W2163552273","https://openalex.org/W338891512","https://openalex.org/W1989152715","https://openalex.org/W2051917381","https://openalex.org/W3010690134","https://openalex.org/W1988572204","https://openalex.org/W2409592036","https://openalex.org/W2300592876","https://openalex.org/W2242928290","https://openalex.org/W2101646335","https://openalex.org/W2176458122","https://openalex.org/W3193843587","https://openalex.org/W1511408843","https://openalex.org/W3134056703","https://openalex.org/W2094958646","https://openalex.org/W2921689829","https://openalex.org/W2043681375","https://openalex.org/W2768039001"],"abstract_inverted_index":{"Safe":[0],"Reinforcement":[1],"Learning":[2],"can":[3],"be":[4],"defined":[5],"as":[6],"the":[7,14,17],"process":[8],"of":[9,16],"learning":[10],"policies":[11],"that":[12],"maximize":[13],"expectation":[15],"return":[18],"in":[19,21],"problems":[20],"which":[22],"it":[23],"is":[24],"important":[25],"to":[26],"ensure":[27],"reasonable":[28],"system":[29],"performan...":[30]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":13},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}