{"id":"https://openalex.org/W4387185415","doi":"https://doi.org/10.3233/faia230598","title":"Reinforcement Learning by Guided Safe Exploration","display_name":"Reinforcement Learning by Guided Safe Exploration","publication_year":2023,"publication_date":"2023-09-28","ids":{"openalex":"https://openalex.org/W4387185415","doi":"https://doi.org/10.3233/faia230598"},"language":"en","primary_location":{"id":"doi:10.3233/faia230598","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia230598","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA230598","source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA230598","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5070497551","display_name":"Qisong Yang","orcid":"https://orcid.org/0000-0002-9686-2697"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Qisong Yang","raw_affiliation_strings":["Delft University of Technology \u2013 The Netherlands"],"affiliations":[{"raw_affiliation_string":"Delft University of Technology \u2013 The Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035570774","display_name":"Thiago D. Sim\u00e3o","orcid":"https://orcid.org/0000-0002-3568-9464"},"institutions":[{"id":"https://openalex.org/I145872427","display_name":"Radboud University Nijmegen","ror":"https://ror.org/016xsfp80","country_code":"NL","type":"education","lineage":["https://openalex.org/I145872427"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Thiago\u00a0D. Sim\u00e3o","raw_affiliation_strings":["Radboud University, Nijmegen \u2013 The Netherlands"],"affiliations":[{"raw_affiliation_string":"Radboud University, Nijmegen \u2013 The Netherlands","institution_ids":["https://openalex.org/I145872427"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012669709","display_name":"Nils Jansen","orcid":"https://orcid.org/0000-0003-1318-8973"},"institutions":[{"id":"https://openalex.org/I145872427","display_name":"Radboud University Nijmegen","ror":"https://ror.org/016xsfp80","country_code":"NL","type":"education","lineage":["https://openalex.org/I145872427"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Nils Jansen","raw_affiliation_strings":["Radboud University, Nijmegen \u2013 The Netherlands"],"affiliations":[{"raw_affiliation_string":"Radboud University, Nijmegen \u2013 The Netherlands","institution_ids":["https://openalex.org/I145872427"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087480106","display_name":"Simon H. Tindemans","orcid":"https://orcid.org/0000-0001-8369-7568"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Simon\u00a0H. Tindemans","raw_affiliation_strings":["Delft University of Technology \u2013 The Netherlands"],"affiliations":[{"raw_affiliation_string":"Delft University of Technology \u2013 The Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075395956","display_name":"Matthijs T. J. Spaan","orcid":"https://orcid.org/0009-0002-2858-8611"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Matthijs\u00a0T.\u00a0J. Spaan","raw_affiliation_strings":["Delft University of Technology \u2013 The Netherlands"],"affiliations":[{"raw_affiliation_string":"Delft University of Technology \u2013 The Netherlands","institution_ids":["https://openalex.org/I98358874"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5070497551"],"corresponding_institution_ids":["https://openalex.org/I98358874"],"apc_list":null,"apc_paid":null,"fwci":3.2068,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.93088142,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":98},"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.8651999831199646,"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":0.8651999831199646,"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/T10809","display_name":"Occupational Health and Safety Research","score":0.8169999718666077,"subfield":{"id":"https://openalex.org/subfields/3614","display_name":"Radiological and Ultrasound Technology"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T11810","display_name":"Complex Systems and Decision Making","score":0.7462999820709229,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8514522314071655},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7696458101272583},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6756515502929688},{"id":"https://openalex.org/keywords/train","display_name":"Train","score":0.6015889644622803},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.5901475548744202},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.4929521083831787},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.45942237973213196},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.4293186366558075},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40369701385498047},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.37926679849624634},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1761758029460907},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.14078405499458313},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.07353433966636658}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8514522314071655},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7696458101272583},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6756515502929688},{"id":"https://openalex.org/C190839683","wikidata":"https://www.wikidata.org/wiki/Q2448197","display_name":"Train","level":2,"score":0.6015889644622803},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.5901475548744202},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.4929521083831787},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.45942237973213196},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.4293186366558075},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40369701385498047},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.37926679849624634},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1761758029460907},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.14078405499458313},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.07353433966636658},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3233/faia230598","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia230598","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA230598","source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},{"id":"pmh:oai:tudelft.nl:uuid:65bcb73a-e4f6-4e35-9ab5-975461fd2466","is_oa":true,"landing_page_url":"http://resolver.tudelft.nl/uuid:65bcb73a-e4f6-4e35-9ab5-975461fd2466","pdf_url":null,"source":{"id":"https://openalex.org/S4306400906","display_name":"Research Repository (Delft University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I98358874","host_organization_name":"Delft University of Technology","host_organization_lineage":["https://openalex.org/I98358874"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"conference paper"}],"best_oa_location":{"id":"doi:10.3233/faia230598","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia230598","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA230598","source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2039356335","display_name":null,"funder_award_id":"1160.18.238","funder_id":"https://openalex.org/F4320321800","funder_display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek"},{"id":"https://openalex.org/G3914140545","display_name":null,"funder_award_id":"160.18.238","funder_id":"https://openalex.org/F4320321800","funder_display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek"},{"id":"https://openalex.org/G4371345817","display_name":null,"funder_award_id":"NWA.1160.18.238","funder_id":"https://openalex.org/F4320321800","funder_display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek"},{"id":"https://openalex.org/G5365867299","display_name":null,"funder_award_id":"Grant","funder_id":"https://openalex.org/F4320321800","funder_display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek"}],"funders":[{"id":"https://openalex.org/F4320321800","display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek","ror":"https://ror.org/04jsz6e67"},{"id":"https://openalex.org/F4320323230","display_name":"Xidian University","ror":"https://ror.org/05s92vm98"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387185415.pdf"},"referenced_works_count":75,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W64088143","https://openalex.org/W1518931405","https://openalex.org/W1547925194","https://openalex.org/W1669104078","https://openalex.org/W1845972764","https://openalex.org/W1984120922","https://openalex.org/W2070570138","https://openalex.org/W2097381042","https://openalex.org/W2120034667","https://openalex.org/W2145339207","https://openalex.org/W2192829189","https://openalex.org/W2397240726","https://openalex.org/W2468354762","https://openalex.org/W2594103415","https://openalex.org/W2604763608","https://openalex.org/W2751422670","https://openalex.org/W2781726626","https://openalex.org/W2788741142","https://openalex.org/W2804791273","https://openalex.org/W2902298341","https://openalex.org/W2904246096","https://openalex.org/W2912924301","https://openalex.org/W2947766526","https://openalex.org/W2949561945","https://openalex.org/W2953326529","https://openalex.org/W2963438456","https://openalex.org/W2963575966","https://openalex.org/W2972522277","https://openalex.org/W2994712737","https://openalex.org/W2996001434","https://openalex.org/W3007553593","https://openalex.org/W3023426586","https://openalex.org/W3029641972","https://openalex.org/W3035611392","https://openalex.org/W3037804676","https://openalex.org/W3043774672","https://openalex.org/W3085267010","https://openalex.org/W3090570651","https://openalex.org/W3096918561","https://openalex.org/W3097059970","https://openalex.org/W3115913119","https://openalex.org/W3118409705","https://openalex.org/W3121342653","https://openalex.org/W3126230687","https://openalex.org/W3128176255","https://openalex.org/W3131871335","https://openalex.org/W3133498163","https://openalex.org/W3135724079","https://openalex.org/W3150718622","https://openalex.org/W3152923668","https://openalex.org/W3162902207","https://openalex.org/W3166557699","https://openalex.org/W3168682563","https://openalex.org/W3174132892","https://openalex.org/W3176452384","https://openalex.org/W3177370066","https://openalex.org/W3180964409","https://openalex.org/W3205284056","https://openalex.org/W3206023733","https://openalex.org/W4220757391","https://openalex.org/W4226205215","https://openalex.org/W4226220005","https://openalex.org/W4226429284","https://openalex.org/W4287144552","https://openalex.org/W4287273849","https://openalex.org/W4287326330","https://openalex.org/W4287629996","https://openalex.org/W4287759108","https://openalex.org/W4293257530","https://openalex.org/W4293545785","https://openalex.org/W4297781264","https://openalex.org/W4382202993","https://openalex.org/W4382318502","https://openalex.org/W4383112908"],"related_works":["https://openalex.org/W2372803315","https://openalex.org/W3074294383","https://openalex.org/W4221165949","https://openalex.org/W2937603438","https://openalex.org/W3158304547","https://openalex.org/W4206669594","https://openalex.org/W2959276766","https://openalex.org/W4295941380","https://openalex.org/W4379662533","https://openalex.org/W4379983844"],"abstract_inverted_index":{"Safety":[0],"is":[1,56,79,99,110,136],"critical":[2],"to":[3,40,50,70,112],"broadening":[4],"the":[5,28,32,48,54,60,74,92,96,108,131,134,141,144,163,166],"application":[6],"of":[7,143],"reinforcement":[8],"learning":[9,160],"(RL).":[10],"Often,":[11],"we":[12,122],"train":[13],"RL":[14,43],"agents":[15],"in":[16,27,81],"a":[17,22,82,114,125],"controlled":[18,83],"environment,":[19,84],"such":[20],"as":[21,146],"laboratory,":[23],"before":[24],"deploying":[25],"them":[26],"real":[29],"world.":[30],"However,":[31],"real-world":[33],"target":[34,97,126,167],"task":[35,98,168],"might":[36],"be":[37],"unknown":[38],"prior":[39],"deployment.":[41],"Reward-free":[42],"trains":[44],"an":[45,65],"agent":[46,66,78],"without":[47,73],"reward":[49,55,75],"adapt":[51],"quickly":[52],"once":[53],"revealed.":[57],"We":[58],"consider":[59],"constrained":[61],"reward-free":[62],"setting,":[63],"where":[64],"(the":[67,128],"guide)":[68],"learns":[69],"explore":[71],"safely":[72],"signal.":[76,94],"This":[77],"trained":[80],"which":[85],"allows":[86],"unsafe":[87],"interactions":[88],"and":[89,138,161],"still":[90],"provides":[91],"safety":[93,101],"After":[95],"revealed,":[100],"violations":[102],"are":[103],"not":[104],"allowed":[105],"anymore.":[106],"Thus,":[107],"guide":[109,132,145],"leveraged":[111],"compose":[113],"safe":[115,158],"behaviour":[116],"policy.":[117],"Drawing":[118],"from":[119],"transfer":[120,159],"learning,":[121],"also":[123],"regularize":[124],"policy":[127],"student)":[129],"towards":[130],"while":[133],"student":[135,164],"unreliable":[137],"gradually":[139],"eliminate":[140],"influence":[142],"training":[147],"progresses.":[148],"The":[149],"empirical":[150],"analysis":[151],"shows":[152],"that":[153],"this":[154],"method":[155],"can":[156],"achieve":[157],"helps":[162],"solve":[165],"faster.":[169]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":5}],"updated_date":"2026-03-12T08:34:05.389933","created_date":"2025-10-10T00:00:00"}