{"id":"https://openalex.org/W4385764501","doi":"https://doi.org/10.24963/ijcai.2023/637","title":"Safe Reinforcement Learning via Probabilistic Logic Shields","display_name":"Safe Reinforcement Learning via Probabilistic Logic Shields","publication_year":2023,"publication_date":"2023-08-01","ids":{"openalex":"https://openalex.org/W4385764501","doi":"https://doi.org/10.24963/ijcai.2023/637"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2023/637","doi":"https://doi.org/10.24963/ijcai.2023/637","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2023/637","pdf_url":"https://www.ijcai.org/proceedings/2023/0637.pdf","source":{"id":"https://openalex.org/S4306419999","display_name":"International Joint Conference on Artificial Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://www.ijcai.org/proceedings/2023/0637.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101587770","display_name":"Wen-Chi Yang","orcid":"https://orcid.org/0000-0002-5340-3829","observed_orcids":["https://orcid.org/0000-0002-5340-3829"]},"institutions":[{"id":"https://openalex.org/I99464096","display_name":"KU Leuven","ror":"https://ror.org/05f950310","country_code":"BE","type":"education","lineage":["https://openalex.org/I99464096"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Wen-Chi Yang","raw_affiliation_strings":["Leuven AI, KU Leuven, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Leuven AI, KU Leuven, Belgium","institution_ids":["https://openalex.org/I99464096"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005466305","display_name":"Giuseppe Marra","orcid":"https://orcid.org/0000-0001-5940-9562","observed_orcids":["https://orcid.org/0000-0001-5940-9562"]},"institutions":[{"id":"https://openalex.org/I99464096","display_name":"KU Leuven","ror":"https://ror.org/05f950310","country_code":"BE","type":"education","lineage":["https://openalex.org/I99464096"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Giuseppe Marra","raw_affiliation_strings":["Leuven AI, KU Leuven, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Leuven AI, KU Leuven, Belgium","institution_ids":["https://openalex.org/I99464096"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078111090","display_name":"Gavin Rens","orcid":"https://orcid.org/0000-0003-2950-9962","observed_orcids":["https://orcid.org/0000-0003-2950-9962"]},"institutions":[{"id":"https://openalex.org/I26092322","display_name":"Stellenbosch University","ror":"https://ror.org/05bk57929","country_code":"ZA","type":"education","lineage":["https://openalex.org/I26092322"]}],"countries":["ZA"],"is_corresponding":false,"raw_author_name":"Gavin Rens","raw_affiliation_strings":["Stellenbosch University, South Africa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stellenbosch University, South Africa","institution_ids":["https://openalex.org/I26092322"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078136609","display_name":"Luc De Raedt","orcid":"https://orcid.org/0000-0002-6860-6303","observed_orcids":["https://orcid.org/0000-0002-6860-6303"]},"institutions":[{"id":"https://openalex.org/I26437253","display_name":"\u00d6rebro University","ror":"https://ror.org/05kytsw45","country_code":"SE","type":"education","lineage":["https://openalex.org/I26437253"]},{"id":"https://openalex.org/I99464096","display_name":"KU Leuven","ror":"https://ror.org/05f950310","country_code":"BE","type":"education","lineage":["https://openalex.org/I99464096"]}],"countries":["BE","SE"],"is_corresponding":false,"raw_author_name":"Luc De Raedt","raw_affiliation_strings":["Centre for Applied Autonomous Sensor Systems, \u00d6rebro University, Sweden","Leuven AI, KU Leuven, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Applied Autonomous Sensor Systems, \u00d6rebro University, Sweden","institution_ids":["https://openalex.org/I26437253"]},{"raw_affiliation_string":"Leuven AI, KU Leuven, Belgium","institution_ids":["https://openalex.org/I99464096"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.007,"has_fulltext":true,"cited_by_count":53,"citation_normalized_percentile":{"value":0.97559356,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"5739","last_page":"5749"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994999766349792,"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":0.9994999766349792,"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/T10142","display_name":"Formal Methods in Verification","score":0.0,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/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":0.9980000257492065},{"id":"https://openalex.org/keywords/shielding","display_name":"shielding","score":0.7400000095367432},{"id":"https://openalex.org/keywords/probabilistic-logic-programming","display_name":"probabilistic logic programming","score":0.972000002861023},{"id":"https://openalex.org/keywords/policy-gradient","display_name":"policy gradient","score":0.6240000128746033},{"id":"https://openalex.org/keywords/model-based-reinforcement-learning","display_name":"model-based reinforcement learning","score":0.7549999952316284}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8102147579193115},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.7651259899139404},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6896520853042603},{"id":"https://openalex.org/C2776654903","wikidata":"https://www.wikidata.org/wiki/Q2601463","display_name":"SAFER","level":2,"score":0.6181550621986389},{"id":"https://openalex.org/C202615002","wikidata":"https://www.wikidata.org/wiki/Q783507","display_name":"Differentiable function","level":2,"score":0.6069103479385376},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5194689631462097},{"id":"https://openalex.org/C52063229","wikidata":"https://www.wikidata.org/wiki/Q7246845","display_name":"Probabilistic CTL","level":4,"score":0.5089247226715088},{"id":"https://openalex.org/C2265751","wikidata":"https://www.wikidata.org/wiki/Q332007","display_name":"Electromagnetic shielding","level":2,"score":0.4705299139022827},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3911247253417969},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.14790290594100952},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14207231998443604},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11766317486763},{"id":"https://openalex.org/C24404364","wikidata":"https://www.wikidata.org/wiki/Q7246846","display_name":"Probabilistic analysis of algorithms","level":3,"score":0.10762524604797363},{"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.24963/ijcai.2023/637","doi":"https://doi.org/10.24963/ijcai.2023/637","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2023/637","pdf_url":"https://www.ijcai.org/proceedings/2023/0637.pdf","source":{"id":"https://openalex.org/S4306419999","display_name":"International Joint Conference on Artificial Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2303.03226","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2303.03226","pdf_url":"https://arxiv.org/pdf/2303.03226","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:lirias2repo.kuleuven.be:20.500.12942/724059","doi":null,"is_oa":true,"landing_page_url":"https://lirias.kuleuven.be/handle/20.500.12942/724059","pdf_url":"https://lirias.kuleuven.be/retrieve/9d2d42ca-a6d0-467a-bb83-24ae3b4f126f","source":{"id":"https://openalex.org/S4306401954","display_name":"Lirias (KU Leuven)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I99464096","host_organization_name":"KU Leuven","host_organization_lineage":["https://openalex.org/I99464096"],"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":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence (IJCAI), Macao, SAR, 19-25 August 2023","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:lirias2repo.kuleuven.be:20.500.12942/731605","doi":null,"is_oa":true,"landing_page_url":"https://lirias.kuleuven.be/handle/20.500.12942/731605","pdf_url":"https://lirias.kuleuven.be/retrieve/acd2fc3c-ffc1-4e1a-96a4-30d1677d143f","source":{"id":"https://openalex.org/S7407055369","display_name":"Lirias","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Neural-Symbolic Learning and Reasoning 2023, La Certosa di Pontignano, Siena, Italy, 3-5 July 2023","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"doi:10.48550/arxiv.2303.03226","doi":"https://doi.org/10.48550/arxiv.2303.03226","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2303.03226","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2023/637","doi":"https://doi.org/10.24963/ijcai.2023/637","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2023/637","pdf_url":"https://www.ijcai.org/proceedings/2023/0637.pdf","source":{"id":"https://openalex.org/S4306419999","display_name":"International Joint Conference on Artificial Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G393622248","display_name":"Deep Statistical Relational Learning","funder_award_id":"1239422N","funder_id":"https://openalex.org/F4320321730","funder_display_name":"Fonds Wetenschappelijk Onderzoek"}],"funders":[{"id":"https://openalex.org/F4320321730","display_name":"Fonds Wetenschappelijk Onderzoek","ror":"https://ror.org/03qtxy027"},{"id":"https://openalex.org/F4320322308","display_name":"KU Leuven","ror":"https://ror.org/05f950310"},{"id":"https://openalex.org/F4320327336","display_name":"Vlaamse regering","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385764501.pdf","grobid_xml":"https://content.openalex.org/works/W4385764501.grobid-xml"},"referenced_works_count":43,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W811924890","https://openalex.org/W958993015","https://openalex.org/W1191599655","https://openalex.org/W1771410628","https://openalex.org/W1845972764","https://openalex.org/W1985093013","https://openalex.org/W2031727428","https://openalex.org/W2102506621","https://openalex.org/W2139546855","https://openalex.org/W2151237105","https://openalex.org/W2155027007","https://openalex.org/W2260756217","https://openalex.org/W2320648065","https://openalex.org/W2341971562","https://openalex.org/W2600009170","https://openalex.org/W2616964725","https://openalex.org/W2736601468","https://openalex.org/W2772282934","https://openalex.org/W2784465508","https://openalex.org/W2804791273","https://openalex.org/W2921596426","https://openalex.org/W2963293747","https://openalex.org/W2963575966","https://openalex.org/W2964514675","https://openalex.org/W2966537673","https://openalex.org/W2982032257","https://openalex.org/W2998561324","https://openalex.org/W3011250830","https://openalex.org/W3039045514","https://openalex.org/W3039939986","https://openalex.org/W3047548613","https://openalex.org/W3088154658","https://openalex.org/W3091691175","https://openalex.org/W3102039646","https://openalex.org/W3121448578","https://openalex.org/W3133533407","https://openalex.org/W3133870857","https://openalex.org/W4220904784","https://openalex.org/W4226046600","https://openalex.org/W4294982428","https://openalex.org/W7053112967","https://openalex.org/W7133234068"],"related_works":["https://openalex.org/W4409347226","https://openalex.org/W2963575966","https://openalex.org/W4415354090","https://openalex.org/W7168923911","https://openalex.org/W3037396281","https://openalex.org/W7162240794","https://openalex.org/W7160943380","https://openalex.org/W4391582476","https://openalex.org/W7163330199","https://openalex.org/W4382318502"],"abstract_inverted_index":{"Safe":[0,17,64],"Reinforcement":[1],"learning":[2,7],"(Safe":[3],"RL)":[4],"aims":[5],"at":[6],"optimal":[8],"policies":[9,110],"while":[10,91],"staying":[11],"safe.":[12],"A":[13],"popular":[14],"solution":[15],"to":[16,27,42,72,86,112],"RL":[18,30,48,65],"is":[19,61],"shielding,":[20],"which":[21],"uses":[22,68],"a":[23,62],"logical":[24,74],"safety":[25,75],"specification":[26],"prevent":[28],"an":[29],"agent":[31],"from":[32],"taking":[33],"unsafe":[34],"actions.":[35],"However,":[36],"traditional":[37],"shielding":[38,115],"techniques":[39],"are":[40],"difficult":[41],"integrate":[43],"with":[44],"continuous,":[45],"end-to-end":[46],"deep":[47],"methods.":[49],"To":[50],"this":[51],"end,":[52],"we":[53,101],"introduce":[54],"Probabilistic":[55],"Logic":[56],"Policy":[57],"Gradient":[58],"(PLPG).":[59],"PLPG":[60,81,104],"model-based":[63],"technique":[66],"that":[67,103],"probabilistic":[69],"logic":[70],"programming":[71],"model":[73],"constraints":[76],"as":[77],"differentiable":[78],"functions.":[79],"Therefore,":[80],"can":[82],"be":[83],"seamlessly":[84],"applied":[85],"any":[87],"policy":[88],"gradient":[89],"algorithm":[90],"still":[92],"providing":[93],"the":[94],"same":[95],"convergence":[96],"guarantees.":[97],"In":[98],"our":[99],"experiments,":[100],"show":[102],"learns":[105],"safer":[106],"and":[107],"more":[108],"rewarding":[109],"compared":[111],"other":[113],"state-of-the-art":[114],"techniques.":[116]},"counts_by_year":[{"year":2026,"cited_by_count":22},{"year":2025,"cited_by_count":17},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":5}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2023-08-12T00:00:00"}