{"id":"https://openalex.org/W2925153779","doi":"https://doi.org/10.24963/ijcai.2019/768","title":"Counterexample-Guided Strategy Improvement for POMDPs Using Recurrent Neural Networks","display_name":"Counterexample-Guided Strategy Improvement for POMDPs Using Recurrent Neural Networks","publication_year":2019,"publication_date":"2019-07-28","ids":{"openalex":"https://openalex.org/W2925153779","doi":"https://doi.org/10.24963/ijcai.2019/768","mag":"2925153779"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2019/768","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/768","pdf_url":"https://www.ijcai.org/proceedings/2019/0768.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2019/0768.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051915018","display_name":"Steven Carr","orcid":"https://orcid.org/0000-0002-5661-3768"},"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":"Steven Carr","raw_affiliation_strings":["The University of Texas at Austin","the University of Texas at, Austin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]},{"raw_affiliation_string":"the 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, The Netherlands","Radboud University, Nijmegen The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Radboud University, Nijmegen, The Netherlands","institution_ids":["https://openalex.org/I145872427"]},{"raw_affiliation_string":"Radboud University, Nijmegen The Netherlands","institution_ids":["https://openalex.org/I145872427"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047238602","display_name":"Ralf Wimmer","orcid":"https://orcid.org/0000-0003-4973-7479"},"institutions":[{"id":"https://openalex.org/I161046081","display_name":"University of Freiburg","ror":"https://ror.org/0245cg223","country_code":"DE","type":"education","lineage":["https://openalex.org/I161046081"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ralf Wimmer","raw_affiliation_strings":["Albert-Ludwigs-Universit\u00e4t Freiburg, Freiburg im Breisgau, Germany","Concept Engineering GmbH, Freiburg im Breisgau, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Albert-Ludwigs-Universit\u00e4t Freiburg, Freiburg im Breisgau, Germany","institution_ids":["https://openalex.org/I161046081"]},{"raw_affiliation_string":"Concept Engineering GmbH, Freiburg im Breisgau, Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103821604","display_name":"Alexandru Constantin Serban","orcid":null},"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":"Alexandru Serban","raw_affiliation_strings":["Radboud University, Nijmegen, The Netherlands","Radboud University, Nijmegen The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Radboud University, Nijmegen, The Netherlands","institution_ids":["https://openalex.org/I145872427"]},{"raw_affiliation_string":"Radboud University, Nijmegen The Netherlands","institution_ids":["https://openalex.org/I145872427"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038861833","display_name":"Bernd Becker","orcid":"https://orcid.org/0000-0003-4031-3258"},"institutions":[{"id":"https://openalex.org/I161046081","display_name":"University of Freiburg","ror":"https://ror.org/0245cg223","country_code":"DE","type":"education","lineage":["https://openalex.org/I161046081"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Bernd Becker","raw_affiliation_strings":["Albert-Ludwigs-Universit\u00e4t Freiburg, Freiburg im Breisgau, Germany","Albert-Ludwigs-Universit\u00e4t-Freiburg, Freiburg im Breisgau, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Albert-Ludwigs-Universit\u00e4t Freiburg, Freiburg im Breisgau, Germany","institution_ids":["https://openalex.org/I161046081"]},{"raw_affiliation_string":"Albert-Ludwigs-Universit\u00e4t-Freiburg, Freiburg im Breisgau, Germany","institution_ids":["https://openalex.org/I161046081"]}]},{"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":["The University of Texas at Austin","the University of Texas at, Austin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]},{"raw_affiliation_string":"the University of Texas at, Austin","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2185,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.48936695,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"5532","last_page":"5539"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.9976000189781189,"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/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.9976000189781189,"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":0.9954000115394592,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9915000200271606,"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/partially-observable-markov-decision-process","display_name":"Partially observable Markov decision process","score":0.8508529663085938},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.7969098091125488},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7584162950515747},{"id":"https://openalex.org/keywords/counterexample","display_name":"Counterexample","score":0.7461405992507935},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.6585193872451782},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.589472234249115},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5182966589927673},{"id":"https://openalex.org/keywords/model-checking","display_name":"Model checking","score":0.4806974530220032},{"id":"https://openalex.org/keywords/temporal-logic","display_name":"Temporal logic","score":0.4555351734161377},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.4511047601699829},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.41455280780792236},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4043714702129364},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.36244192719459534},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.3109973967075348},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.26391369104385376},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.25690189003944397},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13165196776390076}],"concepts":[{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.8508529663085938},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.7969098091125488},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7584162950515747},{"id":"https://openalex.org/C162838799","wikidata":"https://www.wikidata.org/wiki/Q596077","display_name":"Counterexample","level":2,"score":0.7461405992507935},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6585193872451782},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.589472234249115},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5182966589927673},{"id":"https://openalex.org/C110251889","wikidata":"https://www.wikidata.org/wiki/Q1569697","display_name":"Model checking","level":2,"score":0.4806974530220032},{"id":"https://openalex.org/C25016198","wikidata":"https://www.wikidata.org/wiki/Q781833","display_name":"Temporal logic","level":2,"score":0.4555351734161377},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.4511047601699829},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.41455280780792236},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4043714702129364},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.36244192719459534},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.3109973967075348},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.26391369104385376},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.25690189003944397},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13165196776390076},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.24963/ijcai.2019/768","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/768","pdf_url":"https://www.ijcai.org/proceedings/2019/0768.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1903.08428","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1903.08428","pdf_url":"https://arxiv.org/pdf/1903.08428","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,"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:2925153779","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/1903.08428","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,"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"pmh:oai:repository.ubn.ru.nl:2066/207631","is_oa":false,"landing_page_url":"https://hdl.handle.net/2066/207631","pdf_url":null,"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 in monograph or in proceedings"},{"id":"pmh:ru:oai:repository.ubn.ru.nl:2066/207631","is_oa":true,"landing_page_url":"http://hdl.handle.net/2066/207631","pdf_url":null,"source":{"id":"https://openalex.org/S4306401843","display_name":"Data Archiving and Networked Services (DANS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1322597698","host_organization_name":"Royal Netherlands Academy of Arts and Sciences","host_organization_lineage":["https://openalex.org/I1322597698"],"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":"Kraus, S. (ed.), IJCAI 2019: International Joint Conferences on Artificial Intelligence, Macao, P.R. China from August 10-16, 2019, 5532 - 5539. S.l. : IJCAI","raw_type":"info:eu-repo/semantics/article"},{"id":"doi:10.48550/arxiv.1903.08428","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1903.08428","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,"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2019/768","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/768","pdf_url":"https://www.ijcai.org/proceedings/2019/0768.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.7599999904632568,"display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G4641987079","display_name":null,"funder_award_id":"N00014-18-1-2829","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G4908315546","display_name":null,"funder_award_id":"D19AP00004","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"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"}],"funders":[{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2925153779.pdf","grobid_xml":"https://content.openalex.org/works/W2925153779.grobid-xml"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W1498432697","https://openalex.org/W1522308973","https://openalex.org/W1563965851","https://openalex.org/W1640774615","https://openalex.org/W1662842982","https://openalex.org/W1862398452","https://openalex.org/W2032100464","https://openalex.org/W2161521419","https://openalex.org/W2168359464","https://openalex.org/W2171084228","https://openalex.org/W2593267253","https://openalex.org/W2594877703","https://openalex.org/W2604176721","https://openalex.org/W2809011908","https://openalex.org/W2962938178","https://openalex.org/W2962946825"],"related_works":["https://openalex.org/W3006002788","https://openalex.org/W2787942347","https://openalex.org/W2945268470","https://openalex.org/W3019187101","https://openalex.org/W2946624434","https://openalex.org/W2962910777","https://openalex.org/W1553175366","https://openalex.org/W3158874672","https://openalex.org/W2045460737","https://openalex.org/W2604855040","https://openalex.org/W2903683378","https://openalex.org/W3156635476","https://openalex.org/W2026315107","https://openalex.org/W2211790881","https://openalex.org/W2099873296","https://openalex.org/W47969833","https://openalex.org/W1510020026","https://openalex.org/W87773692","https://openalex.org/W1539054658","https://openalex.org/W1483935885"],"abstract_inverted_index":{"We":[0,34,123],"study":[1],"strategy":[2,83,88,130],"synthesis":[3],"for":[4,63],"partially":[5],"observable":[6],"Markov":[7,100],"decision":[8],"processes":[9],"(POMDPs).":[10],"The":[11,60],"particular":[12],"problem":[13,27],"is":[14,28,116],"to":[15,21,56,69,84,127,154],"determine":[16],"strategies":[17],"that":[18,39,139],"provably":[19],"adhere":[20],"(probabilistic)":[22],"temporal":[23,110],"logic":[24,111],"constraints.":[25],"This":[26],"computationally":[29],"intractable":[30],"and":[31,45,89,164],"theoretically":[32],"hard.":[33],"propose":[35],"a":[36,51,76,86,93],"novel":[37],"method":[38,142],"combines":[40],"techniques":[41,105],"from":[42],"machine":[43],"learning":[44],"formal":[46,103],"verification.":[47],"First,":[48],"we":[49,79],"train":[50],"recurrent":[52],"neural":[53],"network":[54],"(RNN)":[55],"encode":[57],"POMDP":[58,150],"strategies.":[59],"RNN":[61],"accounts":[62],"memory-based":[64],"decisions":[65],"without":[66],"the":[67,71,81,97,114,129,134,140,144,147],"need":[68],"expand":[70],"full":[72],"belief":[73],"space":[74],"of":[75,146,157,161],"POMDP.":[77,95],"Secondly,":[78],"restrict":[80],"RNN-based":[82],"represent":[85],"finite-memory":[87],"implement":[90],"it":[91],"on":[92],"specific":[94],"For":[96],"resulting":[98],"finite":[99],"chain,":[101],"efficient":[102],"verification":[104],"provide":[106],"provable":[107],"guarantees":[108],"against":[109],"specifications.":[112],"If":[113],"specification":[115],"not":[117],"satisfied,":[118],"counterexamples":[119],"supply":[120],"diagnostic":[121],"information.":[122],"use":[124],"this":[125],"information":[126],"improve":[128],"by":[131,152],"iteratively":[132],"training":[133],"RNN.":[135],"Numerical":[136],"experiments":[137],"show":[138],"proposed":[141],"elevates":[143],"state":[145],"art":[148],"in":[149,159],"solving":[151,162],"up":[153],"three":[155],"orders":[156],"magnitude":[158],"terms":[160],"times":[163],"model":[165],"sizes.":[166]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}