{"id":"https://openalex.org/W6927441928","doi":"https://doi.org/10.34727/2021/isbn.978-3-85448-046-4_28","title":"Towards Scalable Verification of Deep Reinforcement Learning","display_name":"Towards Scalable Verification of Deep Reinforcement Learning","publication_year":2021,"publication_date":"2021-10-01","ids":{"openalex":"https://openalex.org/W6927441928","doi":"https://doi.org/10.34727/2021/isbn.978-3-85448-046-4_28"},"language":"en","primary_location":{"id":"doi:10.34727/2021/isbn.978-3-85448-046-4_28","is_oa":true,"landing_page_url":"https://doi.org/10.34727/2021/isbn.978-3-85448-046-4_28","pdf_url":null,"source":{"id":"https://openalex.org/S4306400493","display_name":"reposiTUm (TU Wien)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I145847075","host_organization_name":"TU Wien","host_organization_lineage":["https://openalex.org/I145847075"],"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":"Other"},"type":"other","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.34727/2021/isbn.978-3-85448-046-4_28","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Amir, Guy","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Amir, Guy","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Schapira, Michael","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Schapira, Michael","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Katz, Guy","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Katz, Guy","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":null,"topics":[],"keywords":[{"id":"https://openalex.org/keywords/liveness","display_name":"Liveness","score":0.8521000146865845},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8190000057220459},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.7192999720573425},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7067999839782715},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.5774000287055969},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5490999817848206},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.49950000643730164},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.4503999948501587}],"concepts":[{"id":"https://openalex.org/C15569618","wikidata":"https://www.wikidata.org/wiki/Q3561421","display_name":"Liveness","level":2,"score":0.8521000146865845},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8190000057220459},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7635999917984009},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7192999720573425},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7067999839782715},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5942999720573425},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.5774000287055969},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5490999817848206},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.49950000643730164},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4902999997138977},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.4503999948501587},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.43209999799728394},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.3700000047683716},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.36390000581741333},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.35420000553131104},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3431999981403351},{"id":"https://openalex.org/C2780586970","wikidata":"https://www.wikidata.org/wiki/Q1357284","display_name":"Popularity","level":2,"score":0.3260999917984009},{"id":"https://openalex.org/C111498074","wikidata":"https://www.wikidata.org/wiki/Q173326","display_name":"Formal verification","level":2,"score":0.2955999970436096},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.29179999232292175},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2824000120162964},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.27720001339912415}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.34727/2021/isbn.978-3-85448-046-4_28","is_oa":true,"landing_page_url":"https://doi.org/10.34727/2021/isbn.978-3-85448-046-4_28","pdf_url":null,"source":{"id":"https://openalex.org/S4306400493","display_name":"reposiTUm (TU Wien)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I145847075","host_organization_name":"TU Wien","host_organization_lineage":["https://openalex.org/I145847075"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Other"}],"best_oa_location":{"id":"doi:10.34727/2021/isbn.978-3-85448-046-4_28","is_oa":true,"landing_page_url":"https://doi.org/10.34727/2021/isbn.978-3-85448-046-4_28","pdf_url":null,"source":{"id":"https://openalex.org/S4306400493","display_name":"reposiTUm (TU Wien)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I145847075","host_organization_name":"TU Wien","host_organization_lineage":["https://openalex.org/I145847075"],"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":"Other"},"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":{"Deep":[0],"neural":[1],"networks":[2,84],"(DNNs)":[3],"have":[4,87],"gained":[5],"significant":[6],"popularity":[7],"in":[8,17],"recent":[9],"years,":[10],"becoming":[11],"the":[12,15,50,70,82,139,155,159],"state":[13],"of":[14,20,42,63,72,95,142,161],"art":[16],"a":[18,56],"variety":[19],"domains.":[21],"In":[22,45],"particular,":[23],"deep":[24],"reinforcement":[25],"learning":[26],"(DRL)":[27],"has":[28],"recently":[29,88],"been":[30,89],"employed":[31],"to":[32,78,91,135,138],"train":[33],"DNNs":[34],"that":[35,86,102,131],"realize":[36],"control":[37],"policies":[38],"for":[39,59,65,105,111,125],"various":[40],"types":[41],"real-world":[43],"systems.":[44,67,163],"this":[46],"work,":[47],"we":[48,75,146],"present":[49],"whiRL":[51,73,164],"2.0":[52,165],"tool,":[53],"which":[54,99],"implements":[55],"new":[57],"approach":[58],"verifying":[60],"complex":[61],"properties":[62,130],"interest":[64],"DRL":[66,96,162],"To":[68],"demonstrate":[69],"benefits":[71],"2.0,":[74],"apply":[76],"it":[77],"case":[79],"studies":[80],"from":[81],"communication":[83],"domain":[85],"used":[90],"motivate":[92],"formal":[93],"verification":[94],"systems,":[97,120],"and":[98,114,121,128,158],"exhibit":[100],"characteristics":[101],"are":[103],"conducive":[104],"scalable":[106],"verification.":[107],"We":[108],"propose":[109],"techniques":[110,124,151],"performing":[112],"k-induction":[113],"semi-automated":[115],"invariant":[116],"inference":[117],"on":[118],"such":[119],"leverage":[122],"these":[123],"proving":[126],"safety":[127],"liveness":[129],"were":[132],"previously":[133],"impossible":[134],"verify":[136],"due":[137],"scalability":[140],"barriers":[141],"prior":[143],"approaches.":[144],"Furthermore,":[145],"show":[147],"how":[148],"our":[149],"proposed":[150],"provide":[152],"insights":[153],"into":[154],"inner":[156],"workings":[157],"generalizability":[160],"is":[166],"publicly":[167],"available":[168],"online.":[169]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2025-10-10T00:00:00"}