{"id":"https://openalex.org/W4415427904","doi":"https://doi.org/10.3233/faia251392","title":"Data-Efficient Safe Policy Improvement Using Parametric Structure","display_name":"Data-Efficient Safe Policy Improvement Using Parametric Structure","publication_year":2025,"publication_date":"2025-10-21","ids":{"openalex":"https://openalex.org/W4415427904","doi":"https://doi.org/10.3233/faia251392"},"language":null,"primary_location":{"id":"doi:10.3233/faia251392","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia251392","pdf_url":null,"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://doi.org/10.3233/faia251392","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5091926319","display_name":"Kasper Engelen","orcid":"https://orcid.org/0000-0001-8986-9949"},"institutions":[{"id":"https://openalex.org/I4210116480","display_name":"Flanders Make (Belgium)","ror":"https://ror.org/02ndjfz59","country_code":"BE","type":"company","lineage":["https://openalex.org/I4210116480"]}],"countries":["BE"],"is_corresponding":true,"raw_author_name":"Kasper Engelen","raw_affiliation_strings":["University of Antwerp \u2013 Flanders Make"],"affiliations":[{"raw_affiliation_string":"University of Antwerp \u2013 Flanders Make","institution_ids":["https://openalex.org/I4210116480"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053423392","display_name":"Guillermo A. P\u00e9rez","orcid":"https://orcid.org/0000-0002-1200-4952"},"institutions":[{"id":"https://openalex.org/I4210116480","display_name":"Flanders Make (Belgium)","ror":"https://ror.org/02ndjfz59","country_code":"BE","type":"company","lineage":["https://openalex.org/I4210116480"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Guillermo A. P\u00e9rez","raw_affiliation_strings":["University of Antwerp \u2013 Flanders Make"],"affiliations":[{"raw_affiliation_string":"University of Antwerp \u2013 Flanders Make","institution_ids":["https://openalex.org/I4210116480"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5119736674","display_name":"Marnix Suilen","orcid":"https://orcid.org/0000-0003-2163-3504"},"institutions":[{"id":"https://openalex.org/I4210116480","display_name":"Flanders Make (Belgium)","ror":"https://ror.org/02ndjfz59","country_code":"BE","type":"company","lineage":["https://openalex.org/I4210116480"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Marnix Suilen","raw_affiliation_strings":["University of Antwerp \u2013 Flanders Make"],"affiliations":[{"raw_affiliation_string":"University of Antwerp \u2013 Flanders Make","institution_ids":["https://openalex.org/I4210116480"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5091926319"],"corresponding_institution_ids":["https://openalex.org/I4210116480"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.67674144,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"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/T10400","display_name":"Network Security and Intrusion Detection","score":0.6419000029563904,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10400","display_name":"Network Security and Intrusion Detection","score":0.6419000029563904,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T12423","display_name":"Software Reliability and Analysis Research","score":0.6031000018119812,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/T10734","display_name":"Information and Cyber Security","score":0.5975000262260437,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/markov-decision-process","display_name":"Markov decision process","score":0.6987000107765198},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.5795999765396118},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.5690000057220459},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5670999884605408},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.5407000184059143},{"id":"https://openalex.org/keywords/formalism","display_name":"Formalism (music)","score":0.5116999745368958},{"id":"https://openalex.org/keywords/modulo","display_name":"Modulo","score":0.4397999942302704},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.43320000171661377},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.41780000925064087}],"concepts":[{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6987000107765198},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6812999844551086},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.5795999765396118},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.5690000057220459},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5670999884605408},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.5407000184059143},{"id":"https://openalex.org/C73301696","wikidata":"https://www.wikidata.org/wiki/Q5469984","display_name":"Formalism (music)","level":3,"score":0.5116999745368958},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.47620001435279846},{"id":"https://openalex.org/C54732982","wikidata":"https://www.wikidata.org/wiki/Q1415345","display_name":"Modulo","level":2,"score":0.4397999942302704},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.43320000171661377},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.41780000925064087},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.41370001435279846},{"id":"https://openalex.org/C168773769","wikidata":"https://www.wikidata.org/wiki/Q1350299","display_name":"Satisfiability","level":2,"score":0.39719998836517334},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.39640000462532043},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.3837999999523163},{"id":"https://openalex.org/C164155591","wikidata":"https://www.wikidata.org/wiki/Q2067766","display_name":"Satisfiability modulo theories","level":2,"score":0.38029998540878296},{"id":"https://openalex.org/C102366305","wikidata":"https://www.wikidata.org/wiki/Q1097688","display_name":"Nonparametric statistics","level":2,"score":0.3555999994277954},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.31139999628067017},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.3091000020503998},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.3077999949455261},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.303600013256073},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2912999987602234},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.29089999198913574},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.28679999709129333},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.2833000123500824},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.28040000796318054},{"id":"https://openalex.org/C28901747","wikidata":"https://www.wikidata.org/wiki/Q177571","display_name":"Decision theory","level":2,"score":0.27630001306533813},{"id":"https://openalex.org/C84839998","wikidata":"https://www.wikidata.org/wiki/Q5249245","display_name":"Decision rule","level":2,"score":0.2547000050544739},{"id":"https://openalex.org/C10551718","wikidata":"https://www.wikidata.org/wiki/Q5227332","display_name":"Data pre-processing","level":2,"score":0.2538999915122986},{"id":"https://openalex.org/C122123141","wikidata":"https://www.wikidata.org/wiki/Q176623","display_name":"Random variable","level":2,"score":0.2515999972820282},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.2508000135421753}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3233/faia251392","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia251392","pdf_url":null,"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"}],"best_oa_location":{"id":"doi:10.3233/faia251392","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia251392","pdf_url":null,"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":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Safe":[0],"policy":[1,14,20],"improvement":[2],"(SPI)":[3],"is":[4,66],"an":[5,143],"offline":[6],"reinforcement":[7],"learning":[8],"problem":[9],"in":[10,47,54,62],"which":[11],"a":[12,30,81,105,116,121],"new":[13],"that":[15,85,108,133,147],"reliably":[16],"outperforms":[17],"the":[18,33,41,55,63,95,99,113,151,163],"behavior":[19,34],"with":[21],"high":[22],"confidence":[23],"needs":[24],"to":[25,91,138],"be":[26],"computed":[27],"using":[28,98],"only":[29],"dataset":[31],"and":[32,119,142],"policy.":[35],"Markov":[36],"decision":[37],"processes":[38],"(MDPs)":[39],"are":[40],"standard":[42],"formalism":[43],"for":[44],"modeling":[45],"environments":[46],"SPI.":[48],"In":[49],"many":[50],"applications,":[51],"additional":[52],"information":[53],"form":[56],"of":[57,102,154,159],"parametric":[58,82],"dependencies":[59,76],"between":[60,89],"distributions":[61,90],"transition":[64,96],"dynamics":[65,97],"available.":[67],"We":[68],"make":[69],"SPI":[70,83,155],"more":[71,92,122,136],"data-efficient":[72],"by":[73,156],"leveraging":[74],"these":[75],"through":[77,115],"three":[78],"contributions:":[79],"(1)":[80],"algorithm":[84],"exploits":[86],"known":[87],"correlations":[88],"accurately":[93],"estimate":[94],"same":[100,164],"amount":[101],"data;":[103],"(2)":[104],"preprocessing":[106,124],"technique":[107],"prunes":[109],"redundant":[110],"actions":[111,137],"from":[112],"environment":[114],"game-based":[117],"abstraction;":[118],"(3)":[120],"advanced":[123],"technique,":[125],"based":[126],"on":[127],"satisfiability":[128],"modulo":[129],"theory":[130],"(SMT)":[131],"solving,":[132],"can":[134],"identify":[135],"prune.":[139],"Empirical":[140],"results":[141],"ablation":[144],"study":[145],"show":[146],"our":[148],"techniques":[149],"increase":[150],"data":[152],"efficiency":[153],"multiple":[157],"orders":[158],"magnitude":[160],"while":[161],"maintaining":[162],"reliability":[165],"guarantees.":[166]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-24T00:00:00"}