{"id":"https://openalex.org/W4387171936","doi":"https://doi.org/10.3233/faia230357","title":"Approximate Model-Based Shielding for Safe Reinforcement Learning","display_name":"Approximate Model-Based Shielding for Safe Reinforcement Learning","publication_year":2023,"publication_date":"2023-09-28","ids":{"openalex":"https://openalex.org/W4387171936","doi":"https://doi.org/10.3233/faia230357"},"language":"en","primary_location":{"id":"doi:10.3233/faia230357","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia230357","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA230357","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/FAIA230357","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5035327010","display_name":"Alexander W. Goodall","orcid":"https://orcid.org/0000-0003-4659-5241"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Alexander W. Goodall","raw_affiliation_strings":["Imperial College London"],"affiliations":[{"raw_affiliation_string":"Imperial College London","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055883955","display_name":"Francesco Belardinelli","orcid":"https://orcid.org/0000-0002-7768-1794"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Francesco Belardinelli","raw_affiliation_strings":["Imperial College London"],"affiliations":[{"raw_affiliation_string":"Imperial College London","institution_ids":["https://openalex.org/I47508984"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5035327010"],"corresponding_institution_ids":["https://openalex.org/I47508984"],"apc_list":null,"apc_paid":null,"fwci":0.5312,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.68770862,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9975000023841858,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9975000023841858,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9824000000953674,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9667999744415283,"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":0.8923524618148804},{"id":"https://openalex.org/keywords/electromagnetic-shielding","display_name":"Electromagnetic shielding","score":0.8139474391937256},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6423928141593933},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6323357820510864},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.5758130550384521},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.4654543995857239},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3993043899536133},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39784520864486694},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.18383190035820007},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16804474592208862},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.0924791693687439},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.0810275673866272},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.058373600244522095}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8923524618148804},{"id":"https://openalex.org/C2265751","wikidata":"https://www.wikidata.org/wiki/Q332007","display_name":"Electromagnetic shielding","level":2,"score":0.8139474391937256},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6423928141593933},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6323357820510864},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.5758130550384521},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.4654543995857239},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3993043899536133},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39784520864486694},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.18383190035820007},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16804474592208862},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0924791693687439},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0810275673866272},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.058373600244522095},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3233/faia230357","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia230357","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA230357","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:spiral.imperial.ac.uk:10044/1/107172","is_oa":true,"landing_page_url":"http://hdl.handle.net/10044/1/107172","pdf_url":null,"source":{"id":"https://openalex.org/S4306401396","display_name":"Spiral (Imperial College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I47508984","host_organization_name":"Imperial College London","host_organization_lineage":["https://openalex.org/I47508984"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ECAI 2023 - 26th European Conference on Artificial Intelligence","raw_type":"Conference Paper"}],"best_oa_location":{"id":"doi:10.3233/faia230357","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia230357","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA230357","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":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.7300000190734863}],"awards":[{"id":"https://openalex.org/G4269887845","display_name":null,"funder_award_id":"EP/S023356/1","funder_id":"https://openalex.org/F4320314731","funder_display_name":"UK Research and Innovation"}],"funders":[{"id":"https://openalex.org/F4320314731","display_name":"UK Research and Innovation","ror":"https://ror.org/001aqnf71"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387171936.pdf"},"referenced_works_count":56,"referenced_works":["https://openalex.org/W15411808","https://openalex.org/W41554520","https://openalex.org/W152055444","https://openalex.org/W1498432697","https://openalex.org/W1896363143","https://openalex.org/W1980035368","https://openalex.org/W2096630263","https://openalex.org/W2103012681","https://openalex.org/W2462906003","https://openalex.org/W2751422670","https://openalex.org/W2754879180","https://openalex.org/W2761873684","https://openalex.org/W2781585732","https://openalex.org/W2787938642","https://openalex.org/W2803308811","https://openalex.org/W2890208753","https://openalex.org/W2900152462","https://openalex.org/W2905342215","https://openalex.org/W2913300629","https://openalex.org/W2941355526","https://openalex.org/W2950624398","https://openalex.org/W2952032963","https://openalex.org/W2952509347","https://openalex.org/W2963403143","https://openalex.org/W2963575966","https://openalex.org/W2979211489","https://openalex.org/W2982256055","https://openalex.org/W2992977009","https://openalex.org/W2994712737","https://openalex.org/W2995298643","https://openalex.org/W2998619042","https://openalex.org/W3017367030","https://openalex.org/W3091507139","https://openalex.org/W3103780890","https://openalex.org/W3122690883","https://openalex.org/W3135206495","https://openalex.org/W3190791531","https://openalex.org/W3212961045","https://openalex.org/W4211049957","https://openalex.org/W4221144242","https://openalex.org/W4221161274","https://openalex.org/W4225921229","https://openalex.org/W4233413206","https://openalex.org/W4287028738","https://openalex.org/W4287373626","https://openalex.org/W4288319859","https://openalex.org/W4289294484","https://openalex.org/W4293545785","https://openalex.org/W4301014524","https://openalex.org/W4315706776","https://openalex.org/W4319991909","https://openalex.org/W4321020553","https://openalex.org/W4365601008","https://openalex.org/W4366850568","https://openalex.org/W4385964994","https://openalex.org/W6789161987"],"related_works":["https://openalex.org/W3074294383","https://openalex.org/W4206669594","https://openalex.org/W2959276766","https://openalex.org/W4295941380","https://openalex.org/W260766989","https://openalex.org/W3139193008","https://openalex.org/W3111983280","https://openalex.org/W3164468573","https://openalex.org/W4387171936","https://openalex.org/W4385964994"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1],"(RL)":[2],"has":[3],"shown":[4],"great":[5],"potential":[6],"for":[7,60,103],"solving":[8],"complex":[9],"tasks":[10],"in":[11,22,82],"a":[12,55,69,99,114],"variety":[13],"of":[14,64,71,90,94,116],"domains.":[15],"However,":[16],"applying":[17],"RL":[18,37,66],"to":[19,109],"safety-critical":[20],"systems":[21],"the":[23,35,62,91,95],"real-world":[24],"is":[25],"not":[26,86],"easy":[27],"as":[28],"many":[29],"algorithms":[30],"are":[31],"sample-inefficient":[32],"and":[33,105],"maximising":[34],"standard":[36],"objective":[38],"comes":[39],"with":[40,119],"no":[41],"guarantees":[42],"on":[43,113],"worst-case":[44],"performance.":[45],"In":[46],"this":[47],"paper":[48],"we":[49],"propose":[50],"approximate":[51],"model-based":[52],"shielding":[53,58,80],"(AMBS),":[54],"principled":[56],"look-ahead":[57],"algorithm":[59,76],"verifying":[61],"performance":[63,108],"learned":[65],"policies":[67],"w.r.t.":[68],"set":[70,115],"given":[72],"safety":[73],"constraints.":[74],"Our":[75],"differs":[77],"from":[78],"other":[79,110],"approaches":[81,112],"that":[83],"it":[84],"does":[85],"require":[87],"prior":[88],"knowledge":[89],"safety-relevant":[92],"dynamics":[93],"system.":[96],"We":[97],"provide":[98],"strong":[100],"theoretical":[101],"justification":[102],"AMBS":[104],"demonstrate":[106],"superior":[107],"safety-aware":[111],"Atari":[117],"games":[118],"state-dependent":[120],"safety-labels.":[121]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}