{"id":"https://openalex.org/W2156734147","doi":"https://doi.org/10.1109/adprl.2011.5967356","title":"Safe reinforcement learning in high-risk tasks through policy improvement","display_name":"Safe reinforcement learning in high-risk tasks through policy improvement","publication_year":2011,"publication_date":"2011-04-01","ids":{"openalex":"https://openalex.org/W2156734147","doi":"https://doi.org/10.1109/adprl.2011.5967356","mag":"2156734147"},"language":"en","primary_location":{"id":"doi:10.1109/adprl.2011.5967356","is_oa":false,"landing_page_url":"https://doi.org/10.1109/adprl.2011.5967356","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL)","raw_type":"proceedings-article"},"type":"conference-paper","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":null,"display_name":"Francisco Javier Garcia Polo","orcid":null},"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":"Francisco Javier Garcia Polo","raw_affiliation_strings":["Computer Science Department, Universidad Carlos III de Madrid, Madrid, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department, Universidad Carlos III de Madrid, Madrid, Spain","institution_ids":["https://openalex.org/I50357001"]}]},{"author_position":"last","author":{"id":null,"display_name":"Fernando Fernandez Rebollo","orcid":null},"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 Fernandez Rebollo","raw_affiliation_strings":["Computer Science Department, Universidad Carlos III de Madrid, Madrid, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department, Universidad Carlos III de Madrid, Madrid, Spain","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":null,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"76","last_page":"83"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9979000091552734,"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":0.9979000091552734,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.984499990940094,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9843999743461609,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8828846216201782},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7395467758178711},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6635326743125916},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6246207356452942},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.6109864711761475},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4929056167602539},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.48827624320983887},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47845029830932617},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4716353118419647},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.45607665181159973},{"id":"https://openalex.org/keywords/damages","display_name":"Damages","score":0.4507933259010315},{"id":"https://openalex.org/keywords/risk-analysis","display_name":"Risk analysis (engineering)","score":0.41429266333580017},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.376110315322876},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13812735676765442},{"id":"https://openalex.org/keywords/law","display_name":"Law","score":0.06446632742881775}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8828846216201782},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7395467758178711},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6635326743125916},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6246207356452942},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.6109864711761475},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4929056167602539},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.48827624320983887},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47845029830932617},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4716353118419647},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.45607665181159973},{"id":"https://openalex.org/C2777381055","wikidata":"https://www.wikidata.org/wiki/Q308922","display_name":"Damages","level":2,"score":0.4507933259010315},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.41429266333580017},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.376110315322876},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13812735676765442},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.06446632742881775},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/adprl.2011.5967356","is_oa":false,"landing_page_url":"https://doi.org/10.1109/adprl.2011.5967356","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6100000143051147,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320323770","display_name":"Universidad Carlos III de Madrid","ror":"https://ror.org/03ths8210"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W15411808","https://openalex.org/W138448397","https://openalex.org/W1557760016","https://openalex.org/W1562009532","https://openalex.org/W1584208524","https://openalex.org/W1914583973","https://openalex.org/W1975318316","https://openalex.org/W1983497631","https://openalex.org/W1986014385","https://openalex.org/W1994056022","https://openalex.org/W2067098334","https://openalex.org/W2096157014","https://openalex.org/W2101075098","https://openalex.org/W2101539915","https://openalex.org/W2108734173","https://openalex.org/W2110304639","https://openalex.org/W2121863487","https://openalex.org/W2126385963","https://openalex.org/W2148112459","https://openalex.org/W2150818585","https://openalex.org/W2154633587","https://openalex.org/W2277201334","https://openalex.org/W2312609093","https://openalex.org/W3106238320","https://openalex.org/W4214717370","https://openalex.org/W6605695547","https://openalex.org/W6633217410","https://openalex.org/W6633625186"],"related_works":["https://openalex.org/W4205240985","https://openalex.org/W2912415823","https://openalex.org/W4225571923","https://openalex.org/W3212257828","https://openalex.org/W2999580272","https://openalex.org/W4297873223","https://openalex.org/W2350784623","https://openalex.org/W2126211886","https://openalex.org/W3009457412","https://openalex.org/W2992629954"],"abstract_inverted_index":{"Reinforcement":[0],"Learning":[1],"(RL)":[2],"methods":[3],"are":[4,15],"widely":[5],"used":[6],"for":[7,143],"dynamic":[8],"control":[9,148],"tasks.":[10],"In":[11,36,97],"many":[12,38],"cases,":[13],"these":[14,40],"high":[16],"risk":[17,105],"tasks":[18,41],"where":[19],"the":[20,49,61,83,86,92,102,108,114,155,159,166,171],"trial":[21],"and":[22,45,53,69,106,146,150],"error":[23],"process":[24],"may":[25],"select":[26],"actions":[27],"which":[28],"execution":[29],"from":[30,154,158,170],"unsafe":[31],"states":[32,125],"can":[33,79,127],"be":[34],"catastrophic.":[35],"addition,":[37],"of":[39,85,104,110,116,120],"have":[42],"continuous":[43,144],"state":[44,145],"action":[46,147],"spaces,":[47],"making":[48],"learning":[50,93],"problem":[51,109],"harder":[52],"unapproachable":[54],"with":[55,66,124],"conventional":[56],"RL":[57,172],"algorithms.":[58],"So,":[59],"when":[60],"agent":[62],"begins":[63],"to":[64,129],"interact":[65],"a":[67],"risky":[68],"large":[70],"state-action":[71,87],"space":[72,88],"environment,":[73],"an":[74,134],"important":[75],"question":[76],"arises:":[77],"how":[78],"we":[80,100,132],"avoid":[81],"that":[82,126,136,151],"exploration":[84,112],"causes":[89],"damages":[90],"in":[91,113],"(or":[94],"other)":[95],"systems.":[96],"this":[98],"paper,":[99],"define":[101],"concept":[103],"address":[107],"safe":[111],"context":[115],"RL.":[117],"Our":[118],"notion":[119],"safety":[121],"is":[122],"concerned":[123],"lead":[128],"damage.":[130],"Moreover,":[131],"introduce":[133],"algorithm":[135],"safely":[137],"improves":[138],"suboptimal":[139],"but":[140],"robust":[141],"behaviors":[142],"tasks,":[149],"learns":[152],"efficiently":[153],"experience":[156],"gathered":[157],"environment.":[160],"We":[161],"report":[162],"experimental":[163],"results":[164],"using":[165],"helicopter":[167],"hovering":[168],"task":[169],"Competition.":[173]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}