{"id":"https://openalex.org/W4382318502","doi":"https://doi.org/10.1609/aaai.v37i12.26723","title":"Safe Reinforcement Learning via Shielding under Partial Observability","display_name":"Safe Reinforcement Learning via Shielding under Partial Observability","publication_year":2023,"publication_date":"2023-06-26","ids":{"openalex":"https://openalex.org/W4382318502","doi":"https://doi.org/10.1609/aaai.v37i12.26723"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v37i12.26723","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v37i12.26723","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/26723/26495","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/26723/26495","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5036255260","display_name":"Steven A. Carr","orcid":"https://orcid.org/0000-0002-7203-4299"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Steven Carr","raw_affiliation_strings":["University of Texas at Austin"],"affiliations":[{"raw_affiliation_string":"University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]}]},{"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"],"affiliations":[{"raw_affiliation_string":"Radboud University Nijmegen","institution_ids":["https://openalex.org/I145872427"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018941708","display_name":"Sebastian Junges","orcid":"https://orcid.org/0000-0003-0978-8466"},"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":"Sebastian Junges","raw_affiliation_strings":["Radboud University Nijmegen"],"affiliations":[{"raw_affiliation_string":"Radboud University Nijmegen","institution_ids":["https://openalex.org/I145872427"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068441112","display_name":"Ufuk Topcu","orcid":"https://orcid.org/0000-0003-0819-9985"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ufuk Topcu","raw_affiliation_strings":["University of Texas at Austin"],"affiliations":[{"raw_affiliation_string":"University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5036255260"],"corresponding_institution_ids":["https://openalex.org/I86519309"],"apc_list":null,"apc_paid":null,"fwci":3.8091,"has_fulltext":true,"cited_by_count":35,"citation_normalized_percentile":{"value":0.94536082,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"37","issue":"12","first_page":"14748","last_page":"14756"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9883000254631042,"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":0.9883000254631042,"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":0.9650999903678894,"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":0.8787218928337097},{"id":"https://openalex.org/keywords/observability","display_name":"Observability","score":0.8748075366020203},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6808139681816101},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5401709079742432},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5129244327545166},{"id":"https://openalex.org/keywords/shield","display_name":"Shield","score":0.505212128162384},{"id":"https://openalex.org/keywords/risk-analysis","display_name":"Risk analysis (engineering)","score":0.4662553071975708},{"id":"https://openalex.org/keywords/electromagnetic-shielding","display_name":"Electromagnetic shielding","score":0.462673157453537},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.41758596897125244},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4153093695640564},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3942376375198364},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1821366846561432},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.11234012246131897},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09564507007598877},{"id":"https://openalex.org/keywords/business","display_name":"Business","score":0.072838693857193}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8787218928337097},{"id":"https://openalex.org/C36299963","wikidata":"https://www.wikidata.org/wiki/Q1369844","display_name":"Observability","level":2,"score":0.8748075366020203},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6808139681816101},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5401709079742432},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5129244327545166},{"id":"https://openalex.org/C138081364","wikidata":"https://www.wikidata.org/wiki/Q852013","display_name":"Shield","level":2,"score":0.505212128162384},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.4662553071975708},{"id":"https://openalex.org/C2265751","wikidata":"https://www.wikidata.org/wiki/Q332007","display_name":"Electromagnetic shielding","level":2,"score":0.462673157453537},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.41758596897125244},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4153093695640564},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3942376375198364},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1821366846561432},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.11234012246131897},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09564507007598877},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.072838693857193},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"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/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C5900021","wikidata":"https://www.wikidata.org/wiki/Q163082","display_name":"Petrology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v37i12.26723","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v37i12.26723","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/26723/26495","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:repository.ubn.ru.nl:2066/294801","is_oa":true,"landing_page_url":"https://hdl.handle.net/2066/294801","pdf_url":"https://repository.ubn.ru.nl//bitstream/handle/2066/294801/294801.pdf","source":{"id":"https://openalex.org/S4306401067","display_name":"Radboud Repository (Radboud University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I145872427","host_organization_name":"Radboud University Nijmegen","host_organization_lineage":["https://openalex.org/I145872427"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article / Letter to editor"}],"best_oa_location":{"id":"doi:10.1609/aaai.v37i12.26723","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v37i12.26723","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/26723/26495","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.4000000059604645}],"awards":[{"id":"https://openalex.org/G1633690903","display_name":null,"funder_award_id":"00014-20","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G2336166159","display_name":null,"funder_award_id":"4-20-","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G4720003262","display_name":null,"funder_award_id":"N00014-22","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G6563777096","display_name":null,"funder_award_id":"N00014-22-1-2254","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G6925521478","display_name":null,"funder_award_id":"N00014-20-1-2115","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G7034037648","display_name":null,"funder_award_id":"4-20-1-","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G7452299184","display_name":null,"funder_award_id":"W911NF","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"},{"id":"https://openalex.org/G8817840310","display_name":null,"funder_award_id":"W911NF-20-1-0140","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"},{"id":"https://openalex.org/G8876996369","display_name":null,"funder_award_id":"N00014","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G8998121839","display_name":null,"funder_award_id":"911NF","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"}],"funders":[{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"},{"id":"https://openalex.org/F4320338281","display_name":"Army Research Office","ror":"https://ror.org/05epdh915"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4382318502.pdf"},"referenced_works_count":67,"referenced_works":["https://openalex.org/W96584974","https://openalex.org/W1482467703","https://openalex.org/W1482748162","https://openalex.org/W1493096714","https://openalex.org/W1532688806","https://openalex.org/W1563965851","https://openalex.org/W1662842982","https://openalex.org/W1769460679","https://openalex.org/W1845972764","https://openalex.org/W1977655452","https://openalex.org/W2011495999","https://openalex.org/W2023808162","https://openalex.org/W2069888227","https://openalex.org/W2106923343","https://openalex.org/W2119717200","https://openalex.org/W2121092017","https://openalex.org/W2127107099","https://openalex.org/W2134802714","https://openalex.org/W2145339207","https://openalex.org/W2155968351","https://openalex.org/W2168359464","https://openalex.org/W2170665731","https://openalex.org/W2171084228","https://openalex.org/W2198357760","https://openalex.org/W2222789563","https://openalex.org/W2257979135","https://openalex.org/W2274143274","https://openalex.org/W2593267253","https://openalex.org/W2594877703","https://openalex.org/W2604176721","https://openalex.org/W2736601468","https://openalex.org/W2746553466","https://openalex.org/W2763611255","https://openalex.org/W2787908307","https://openalex.org/W2910597635","https://openalex.org/W2938272992","https://openalex.org/W2963575966","https://openalex.org/W2981037657","https://openalex.org/W3006844914","https://openalex.org/W3088952667","https://openalex.org/W3100944043","https://openalex.org/W3163453895","https://openalex.org/W3185890095","https://openalex.org/W3215640983","https://openalex.org/W4214717370","https://openalex.org/W4226380042","https://openalex.org/W4230563027","https://openalex.org/W4288372726","https://openalex.org/W4297780563","https://openalex.org/W4298857966","https://openalex.org/W4300395467","https://openalex.org/W6628719960","https://openalex.org/W6629282427","https://openalex.org/W6629784141","https://openalex.org/W6637967152","https://openalex.org/W6644813291","https://openalex.org/W6656255003","https://openalex.org/W6677916085","https://openalex.org/W6678927950","https://openalex.org/W6679977494","https://openalex.org/W6682367392","https://openalex.org/W6703110798","https://openalex.org/W6741002519","https://openalex.org/W6743563064","https://openalex.org/W6757645165","https://openalex.org/W6774143879","https://openalex.org/W6780637199"],"related_works":["https://openalex.org/W2046459260","https://openalex.org/W2967463586","https://openalex.org/W2765830098","https://openalex.org/W1971989957","https://openalex.org/W2517338020","https://openalex.org/W2019398180","https://openalex.org/W1558419416","https://openalex.org/W2790618745","https://openalex.org/W2367689620","https://openalex.org/W2012502436"],"abstract_inverted_index":{"Safe":[0],"exploration":[1],"is":[2],"a":[3,37,114,136,153,160],"common":[4],"problem":[5,29],"in":[6,33,66,104,152],"reinforcement":[7],"learning":[8,151],"(RL)":[9],"that":[10,113,135],"aims":[11],"to":[12,27,43,58,141,158],"prevent":[13],"agents":[14],"from":[15],"making":[16],"disastrous":[17],"decisions":[18],"while":[19],"exploring":[20],"their":[21],"environment.":[22],"A":[23,51],"family":[24],"of":[25,36,40,48,80,89,129],"approaches":[26],"this":[28,41],"assume":[30],"domain":[31],"knowledge":[32],"the":[34,46,55,78,87,123],"form":[35],"(partial)":[38],"model":[39],"environment":[42],"decide":[44],"upon":[45],"safety":[47,74,119],"an":[49,100],"action.":[50],"so-called":[52],"shield":[53,117,137,164],"forces":[54],"RL":[56,81,130,144],"agent":[57],"select":[59],"only":[60],"safe":[61,148],"actions.":[62],"However,":[63],"for":[64],"adoption":[65],"various":[67],"applications,":[68],"one":[69],"must":[70],"look":[71],"beyond":[72],"enforcing":[73],"and":[75,98,120,126],"also":[76],"ensure":[77],"applicability":[79,88],"with":[82,94],"good":[83],"performance.":[84],"We":[85,111,132],"extend":[86],"shields":[90],"via":[91],"tight":[92],"integration":[93],"state-of-the-art":[95,143],"deep":[96],"RL,":[97],"provide":[99],"extensive,":[101],"empirical":[102],"study":[103],"challenging,":[105],"sparse-reward":[106],"environments":[107],"under":[108],"partial":[109],"observability.":[110],"show":[112,134],"carefully":[115],"integrated":[116],"ensures":[118],"can":[121,138],"improve":[122],"convergence":[124],"rate":[125],"final":[127],"performance":[128],"agents.":[131],"furthermore":[133],"be":[139],"used":[140],"bootstrap":[142],"agents:":[145],"they":[146],"remain":[147],"after":[149],"initial":[150],"shielded":[154],"setting,":[155],"allowing":[156],"us":[157],"disable":[159],"potentially":[161],"too":[162],"conservative":[163],"eventually.":[165]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":12}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}