{"id":"https://openalex.org/W1845972764","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/W1845972764","doi":"https://doi.org/10.5555/2789272.2886795","mag":"1845972764"},"language":"en","primary_location":{"id":"mag:1845972764","doi":null,"is_oa":false,"landing_page_url":"https://jmlr.csail.mit.edu/papers/volume16/garcia15a/garcia15a.pdf","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,"listed_in":["anvur-class-a","anvur-scientific","ccf-a","cwts-core","dongbi-a","jufo-3","ki-jl-2","norway-2","poland-140","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310315718","host_organization_name":"The MIT Press","host_organization_lineage":["https://openalex.org/P4310315718","https://openalex.org/P4310316440"],"host_organization_lineage_names":["The MIT Press","Massachusetts Institute of Technology"],"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},"parent_works":[],"lineage":["https://openalex.org/W1845972764"],"child_works_count":0,"type":"article","is_traditional":true,"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/A5100645872","display_name":"Javier Garc\u00eda","orcid":"https://orcid.org/0000-0002-5638-5240","observed_orcids":["https://orcid.org/0000-0002-5638-5240"]},"institutions":[{"id":"https://openalex.org/I50357001","display_name":"Universidad Carlos III de Madrid","ror":"https://ror.org/03ths8210","country_code":"ES","type":"education","lineage":["https://openalex.org/I50357001"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Javier Garc\u00eda","raw_affiliation_strings":["Universidad Carlos III de Madrid, Leganes, Madrid, Spain#TAB#"],"raw_orcid":"https://orcid.org/0000-0002-5638-5240","affiliations":[{"raw_affiliation_string":"Universidad Carlos III de Madrid, Leganes, Madrid, Spain#TAB#","institution_ids":["https://openalex.org/I50357001"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004703726","display_name":"Fernando Fern\u00e1ndez","orcid":"https://orcid.org/0000-0003-3801-6801","observed_orcids":["https://orcid.org/0000-0003-3801-6801"]},"institutions":[{"id":"https://openalex.org/I50357001","display_name":"Universidad Carlos III de Madrid","ror":"https://ror.org/03ths8210","country_code":"ES","type":"education","lineage":["https://openalex.org/I50357001"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Fernando Fern\u00e1ndez","raw_affiliation_strings":["Universidad Carlos III de Madrid, Leganes, Madrid, Spain#TAB#"],"raw_orcid":"https://orcid.org/0000-0003-3801-6801","affiliations":[{"raw_affiliation_string":"Universidad Carlos III de Madrid, Leganes, Madrid, Spain#TAB#","institution_ids":["https://openalex.org/I50357001"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I50357001"],"apc_list":null,"apc_paid":null,"fwci":22.0276,"has_fulltext":false,"cited_by_count":1201,"citation_normalized_percentile":{"value":0.99664105,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"16","issue":"1","first_page":"1437","last_page":"1480"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":1.0,"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":1.0,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.0,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.0,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/safe-reinforcement-learning","display_name":"safe reinforcement learning","score":0.9990000128746033},{"id":"https://openalex.org/keywords/safety-constraints","display_name":"safety constraints","score":0.8999999761581421},{"id":"https://openalex.org/keywords/safety-factor","display_name":"safety factor","score":0.7139999866485596},{"id":"https://openalex.org/keywords/exploration-guidance","display_name":"exploration guidance","score":0.6520000100135803},{"id":"https://openalex.org/keywords/risk-measures","display_name":"risk measures","score":0.7300000190734863},{"id":"https://openalex.org/keywords/external-knowledge","display_name":"external knowledge","score":0.7580000162124634},{"id":"https://openalex.org/keywords/policy-optimization","display_name":"policy optimization","score":0.4830000102519989},{"id":"https://openalex.org/keywords/literature-survey","display_name":"literature survey","score":0.39899998903274536}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8934261798858643},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.704834520816803},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6446173191070557},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.6336431503295898},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.6223631501197815},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5562188029289246},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5411964654922485},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4857107102870941},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48208194971084595},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.33236461877822876},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1456160545349121},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0912671685218811},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","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}],"mesh":[],"locations_count":2,"locations":[{"id":"mag:1845972764","doi":null,"is_oa":false,"landing_page_url":"https://jmlr.csail.mit.edu/papers/volume16/garcia15a/garcia15a.pdf","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,"listed_in":["anvur-class-a","anvur-scientific","ccf-a","cwts-core","dongbi-a","jufo-3","ki-jl-2","norway-2","poland-140","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310315718","host_organization_name":"The MIT Press","host_organization_lineage":["https://openalex.org/P4310315718","https://openalex.org/P4310316440"],"host_organization_lineage_names":["The MIT Press","Massachusetts Institute of Technology"],"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},{"id":"mag:3003931103","doi":"https://doi.org/10.5555/2789272.2886795","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,"listed_in":["anvur-class-a","anvur-scientific","ccf-a","cwts-core","dongbi-a","jufo-3","ki-jl-2","norway-2","poland-140","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310315718","host_organization_name":"The MIT Press","host_organization_lineage":["https://openalex.org/P4310315718","https://openalex.org/P4310316440"],"host_organization_lineage_names":["The MIT Press","Massachusetts Institute of Technology"],"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}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":109,"referenced_works":["https://openalex.org/W15411808","https://openalex.org/W50296447","https://openalex.org/W60181528","https://openalex.org/W120804890","https://openalex.org/W121023703","https://openalex.org/W124618424","https://openalex.org/W134786152","https://openalex.org/W285078413","https://openalex.org/W393220884","https://openalex.org/W1487478277","https://openalex.org/W1497976081","https://openalex.org/W1505937442","https://openalex.org/W1506085041","https://openalex.org/W1506285364","https://openalex.org/W1515851193","https://openalex.org/W1529522829","https://openalex.org/W1539975474","https://openalex.org/W1556500232","https://openalex.org/W1564754565","https://openalex.org/W1575081350","https://openalex.org/W1581437610","https://openalex.org/W1585546346","https://openalex.org/W1585575029","https://openalex.org/W1589064538","https://openalex.org/W1717272517","https://openalex.org/W1840625103","https://openalex.org/W1917437102","https://openalex.org/W1964262340","https://openalex.org/W1965878388","https://openalex.org/W1968902264","https://openalex.org/W1969028245","https://openalex.org/W1983497631","https://openalex.org/W1984151138","https://openalex.org/W1986014385","https://openalex.org/W1986998777","https://openalex.org/W1988562801","https://openalex.org/W1990437501","https://openalex.org/W1992154527","https://openalex.org/W1996625075","https://openalex.org/W2011231614","https://openalex.org/W2013406658","https://openalex.org/W2019619977","https://openalex.org/W2031727428","https://openalex.org/W2038398071","https://openalex.org/W2042459810","https://openalex.org/W2054226461","https://openalex.org/W2056584142","https://openalex.org/W2060248504","https://openalex.org/W2070301851","https://openalex.org/W2074602376","https://openalex.org/W2079659517","https://openalex.org/W2081348312","https://openalex.org/W2088413745","https://openalex.org/W2096615883","https://openalex.org/W2097381042","https://openalex.org/W2097797606","https://openalex.org/W2097900976","https://openalex.org/W2101075098","https://openalex.org/W2102288976","https://openalex.org/W2102512214","https://openalex.org/W2104269165","https://openalex.org/W2105885785","https://openalex.org/W2106907982","https://openalex.org/W2108888882","https://openalex.org/W2110030749","https://openalex.org/W2111492941","https://openalex.org/W2116157560","https://openalex.org/W2117964625","https://openalex.org/W2119409989","https://openalex.org/W2119567691","https://openalex.org/W2121110499","https://openalex.org/W2121863487","https://openalex.org/W2122982548","https://openalex.org/W2129659607","https://openalex.org/W2129670787","https://openalex.org/W2130178506","https://openalex.org/W2133040789","https://openalex.org/W2133219138","https://openalex.org/W2133632477","https://openalex.org/W2134491302","https://openalex.org/W2136074593","https://openalex.org/W2136462844","https://openalex.org/W2138091476","https://openalex.org/W2138497321","https://openalex.org/W2139914196","https://openalex.org/W2140584963","https://openalex.org/W2141559645","https://openalex.org/W2145341417","https://openalex.org/W2147871016","https://openalex.org/W2151237105","https://openalex.org/W2153353285","https://openalex.org/W2154018708","https://openalex.org/W2156734147","https://openalex.org/W2156869222","https://openalex.org/W2165622730","https://openalex.org/W2168565265","https://openalex.org/W2169619645","https://openalex.org/W2197493596","https://openalex.org/W2223493585","https://openalex.org/W2262174858","https://openalex.org/W2312609093","https://openalex.org/W2404786126","https://openalex.org/W2416364697","https://openalex.org/W2489939061","https://openalex.org/W2566307933","https://openalex.org/W2896027395","https://openalex.org/W2964108826","https://openalex.org/W3011120880","https://openalex.org/W3147321350"],"related_works":["https://openalex.org/W4401023546","https://openalex.org/W4415237758","https://openalex.org/W3168575058","https://openalex.org/W3210140370","https://openalex.org/W7208747777","https://openalex.org/W4206485356","https://openalex.org/W3214770989","https://openalex.org/W4388692115","https://openalex.org/W7124869572","https://openalex.org/W7213313928"],"abstract_inverted_index":{"Safe":[0,48,112],"Reinforcement":[1,49,113],"Learning":[2],"can":[3],"be":[4],"defined":[5],"as":[6,105,107],"the":[7,14,17,36,56,59,62,76,79,83,89,97,102],"process":[8,81],"of":[9,16,47,58,78,85,91],"learning":[10,37],"policies":[11],"that":[12],"maximize":[13],"expectation":[15],"return":[18],"in":[19,21],"problems":[20],"which":[22],"it":[23],"is":[24,53,73],"important":[25],"to":[26,100],"ensure":[27],"reasonable":[28],"system":[29],"performance":[30],"and/or":[31,38],"respect":[32],"safety":[33,69],"constraints":[34],"during":[35],"deployment":[39],"processes.":[40],"We":[41,95],"categorize":[42],"and":[43],"analyze":[44],"two":[45],"approaches":[46],"Learning.":[50,114],"The":[51,71],"first":[52],"based":[54,74],"on":[55,75],"modification":[57,77],"optimality":[60],"criterion,":[61],"classic":[63],"discounted":[64],"finite/infinite":[65],"horizon,":[66],"with":[67],"a":[68,92],"factor.":[70],"second":[72],"exploration":[80],"through":[82],"incorporation":[84],"external":[86],"knowledge":[87],"or":[88],"guidance":[90],"risk":[93],"metric.":[94],"use":[96],"proposed":[98],"classification":[99],"survey":[101],"existing":[103],"literature,":[104],"well":[106],"suggesting":[108],"future":[109],"directions":[110],"for":[111]},"counts_by_year":[{"year":2026,"cited_by_count":18},{"year":2025,"cited_by_count":84},{"year":2024,"cited_by_count":150},{"year":2023,"cited_by_count":187},{"year":2022,"cited_by_count":169},{"year":2021,"cited_by_count":226},{"year":2020,"cited_by_count":151},{"year":2019,"cited_by_count":117},{"year":2018,"cited_by_count":63},{"year":2017,"cited_by_count":28},{"year":2016,"cited_by_count":8}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2016-06-24T00:00:00"}