{"id":"https://openalex.org/W4386317039","doi":"https://doi.org/10.1145/3607835","title":"Formal Specification and Testing for Reinforcement Learning","display_name":"Formal Specification and Testing for Reinforcement Learning","publication_year":2023,"publication_date":"2023-08-30","ids":{"openalex":"https://openalex.org/W4386317039","doi":"https://doi.org/10.1145/3607835"},"language":"en","primary_location":{"id":"doi:10.1145/3607835","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3607835","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3607835","source":{"id":"https://openalex.org/S4210216081","display_name":"Proceedings of the ACM on Programming Languages","issn_l":"2475-1421","issn":["2475-1421"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Programming Languages","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3607835","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5036805687","display_name":"Mahsa Varshosaz","orcid":"https://orcid.org/0000-0002-4776-883X"},"institutions":[{"id":"https://openalex.org/I83467386","display_name":"IT University of Copenhagen","ror":"https://ror.org/02309jg23","country_code":"DK","type":"education","lineage":["https://openalex.org/I83467386"]}],"countries":["DK"],"is_corresponding":true,"raw_author_name":"Mahsa Varshosaz","raw_affiliation_strings":["IT University of Copenhagen, Denmark"],"raw_orcid":"https://orcid.org/0000-0002-4776-883X","affiliations":[{"raw_affiliation_string":"IT University of Copenhagen, Denmark","institution_ids":["https://openalex.org/I83467386"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088284921","display_name":"Mohsen Ghaffari","orcid":"https://orcid.org/0000-0002-1939-9053"},"institutions":[{"id":"https://openalex.org/I83467386","display_name":"IT University of Copenhagen","ror":"https://ror.org/02309jg23","country_code":"DK","type":"education","lineage":["https://openalex.org/I83467386"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Mohsen Ghaffari","raw_affiliation_strings":["IT University of Copenhagen, Denmark"],"raw_orcid":"https://orcid.org/0000-0002-1939-9053","affiliations":[{"raw_affiliation_string":"IT University of Copenhagen, Denmark","institution_ids":["https://openalex.org/I83467386"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039414480","display_name":"Einar Broch Johnsen","orcid":"https://orcid.org/0000-0001-5382-3949"},"institutions":[{"id":"https://openalex.org/I184942183","display_name":"University of Oslo","ror":"https://ror.org/01xtthb56","country_code":"NO","type":"education","lineage":["https://openalex.org/I184942183"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Einar Broch Johnsen","raw_affiliation_strings":["University of Oslo, Norway"],"raw_orcid":"https://orcid.org/0000-0001-5382-3949","affiliations":[{"raw_affiliation_string":"University of Oslo, Norway","institution_ids":["https://openalex.org/I184942183"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056755949","display_name":"Andrzej W\u0105sowski","orcid":"https://orcid.org/0000-0003-0532-2685"},"institutions":[{"id":"https://openalex.org/I83467386","display_name":"IT University of Copenhagen","ror":"https://ror.org/02309jg23","country_code":"DK","type":"education","lineage":["https://openalex.org/I83467386"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Andrzej W\u0105sowski","raw_affiliation_strings":["IT University of Copenhagen, Denmark"],"raw_orcid":"https://orcid.org/0000-0003-0532-2685","affiliations":[{"raw_affiliation_string":"IT University of Copenhagen, Denmark","institution_ids":["https://openalex.org/I83467386"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5036805687"],"corresponding_institution_ids":["https://openalex.org/I83467386"],"apc_list":null,"apc_paid":null,"fwci":3.1389,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.92878305,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"7","issue":"ICFP","first_page":"125","last_page":"158"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9976000189781189,"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"}},"topics":[{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9976000189781189,"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"}},{"id":"https://openalex.org/T10743","display_name":"Software Testing and Debugging Techniques","score":0.9955999851226807,"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/T10142","display_name":"Formal Methods in Verification","score":0.9936000108718872,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8014914989471436},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.790432333946228},{"id":"https://openalex.org/keywords/oracle","display_name":"Oracle","score":0.6365525722503662},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.5369925498962402},{"id":"https://openalex.org/keywords/test-suite","display_name":"Test suite","score":0.5288081169128418},{"id":"https://openalex.org/keywords/active-learning","display_name":"Active learning (machine learning)","score":0.5006358623504639},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.495929092168808},{"id":"https://openalex.org/keywords/programmer","display_name":"Programmer","score":0.48668962717056274},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3524165749549866},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.3475375771522522},{"id":"https://openalex.org/keywords/test-case","display_name":"Test case","score":0.21439138054847717}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8014914989471436},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.790432333946228},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.6365525722503662},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.5369925498962402},{"id":"https://openalex.org/C151552104","wikidata":"https://www.wikidata.org/wiki/Q7705809","display_name":"Test suite","level":4,"score":0.5288081169128418},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.5006358623504639},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.495929092168808},{"id":"https://openalex.org/C2778514511","wikidata":"https://www.wikidata.org/wiki/Q1374194","display_name":"Programmer","level":2,"score":0.48668962717056274},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3524165749549866},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.3475375771522522},{"id":"https://openalex.org/C128942645","wikidata":"https://www.wikidata.org/wiki/Q1568346","display_name":"Test case","level":3,"score":0.21439138054847717},{"id":"https://openalex.org/C152877465","wikidata":"https://www.wikidata.org/wiki/Q208042","display_name":"Regression analysis","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3607835","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3607835","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3607835","source":{"id":"https://openalex.org/S4210216081","display_name":"Proceedings of the ACM on Programming Languages","issn_l":"2475-1421","issn":["2475-1421"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Programming Languages","raw_type":"journal-article"},{"id":"pmh:oai:pure.atira.dk:publications/e1a419da-e1e2-4370-82df-ef6d760dcef4","is_oa":true,"landing_page_url":"https://pure.itu.dk/portal/da/publications/e1a419da-e1e2-4370-82df-ef6d760dcef4","pdf_url":"https://pure.itu.dk/ws/files/102788488/23-icfp.pdf","source":{"id":"https://openalex.org/S4377196680","display_name":"IT University Of Copenhagen (IT University of Copenhagen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I83467386","host_organization_name":"IT University of Copenhagen","host_organization_lineage":["https://openalex.org/I83467386"],"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":"Varshosaz, M, Ghaffari, M, Broch Johnsen, E & Wasowski, A 2023, 'Formal Specification and Testing for Reinforcement Learning', Proceedings of the ACM on Programming Languages, vol. 7, no. Issue ICFP, 193, pp. 125-158. https://doi.org/10.1145/3607835","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:www.duo.uio.no:10852/108921","is_oa":true,"landing_page_url":"http://hdl.handle.net/10852/108921","pdf_url":null,"source":{"id":"https://openalex.org/S4306401717","display_name":"Duo Research Archive (University of Oslo)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184942183","host_organization_name":"University of Oslo","host_organization_lineage":["https://openalex.org/I184942183"],"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":"2475-1421","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1145/3607835","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3607835","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3607835","source":{"id":"https://openalex.org/S4210216081","display_name":"Proceedings of the ACM on Programming Languages","issn_l":"2475-1421","issn":["2475-1421"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Programming Languages","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320313796","display_name":"Innovationsfonden","ror":"https://ror.org/00daj4111"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4386317039.pdf","grobid_xml":"https://content.openalex.org/works/W4386317039.grobid-xml"},"referenced_works_count":50,"referenced_works":["https://openalex.org/W1999060469","https://openalex.org/W2026926213","https://openalex.org/W2049695835","https://openalex.org/W2050509196","https://openalex.org/W2100677568","https://openalex.org/W2100752967","https://openalex.org/W2107726111","https://openalex.org/W2108557864","https://openalex.org/W2222789563","https://openalex.org/W2593237273","https://openalex.org/W2725449579","https://openalex.org/W2736601468","https://openalex.org/W2787908307","https://openalex.org/W2869036160","https://openalex.org/W2912757393","https://openalex.org/W2941205169","https://openalex.org/W2949103145","https://openalex.org/W2951147613","https://openalex.org/W2963575966","https://openalex.org/W2963913218","https://openalex.org/W2990138404","https://openalex.org/W3003931103","https://openalex.org/W3021958118","https://openalex.org/W3102039646","https://openalex.org/W3104303413","https://openalex.org/W3122478777","https://openalex.org/W3135560598","https://openalex.org/W3163745263","https://openalex.org/W3165292502","https://openalex.org/W3179011554","https://openalex.org/W3193448347","https://openalex.org/W3198594207","https://openalex.org/W3200467243","https://openalex.org/W3206959716","https://openalex.org/W3208792968","https://openalex.org/W3217518341","https://openalex.org/W4206624744","https://openalex.org/W4225756091","https://openalex.org/W4232976691","https://openalex.org/W4242126179","https://openalex.org/W4282580266","https://openalex.org/W4284682097","https://openalex.org/W4285601900","https://openalex.org/W4287393098","https://openalex.org/W4289874473","https://openalex.org/W4312510909","https://openalex.org/W4313547546","https://openalex.org/W4313563646","https://openalex.org/W4367016230","https://openalex.org/W6931977479"],"related_works":["https://openalex.org/W2379153735","https://openalex.org/W2046172023","https://openalex.org/W2972896947","https://openalex.org/W2170146914","https://openalex.org/W2355105570","https://openalex.org/W2083974823","https://openalex.org/W2072751097","https://openalex.org/W4237177615","https://openalex.org/W2914522629","https://openalex.org/W2133845513"],"abstract_inverted_index":{"The":[0,91],"development":[1,38,93],"process":[2],"for":[3,74,115,124,159],"reinforcement":[4,40,49,79,181],"learning":[5,41,50,80,182],"applications":[6,21,81],"is":[7,94,151],"still":[8],"exploratory":[9,14],"rather":[10],"than":[11],"systematic.":[12],"This":[13,30],"nature":[15],"reduces":[16],"reuse":[17],"of":[18,26,39,48,78,131,138,161,168],"specifications":[19,103],"between":[20],"and":[22,52,62,89,104,111,140],"increases":[23],"the":[24,37,129,193],"chances":[25],"introducing":[27],"programming":[28,98],"errors.":[29],"paper":[31],"takes":[32],"a":[33,45,55,71,75,116,121,136],"step":[34],"towards":[35],"systematizing":[36],"applications.":[42],"We":[43,68,127,145],"introduce":[44],"formal":[46],"specification":[47],"problems":[51],"algorithms,":[53],"with":[54,101,108,142],"particular":[56],"focus":[57],"on":[58,83,135],"temporal":[59,84],"difference":[60,85],"methods":[61],"their":[63],"definitions":[64],"in":[65,96,153],"backup":[66],"diagrams.":[67],"further":[69],"develop":[70],"test":[72,122,149],"harness":[73],"large":[76],"class":[77],"based":[82],"learning,":[86],"including":[87],"SARSA":[88],"Q-learning.":[90],"entire":[92],"rooted":[95],"functional":[97],"methods;":[99],"starting":[100],"pure":[102],"denotational":[105],"semantics,":[106],"ending":[107],"property-based":[109],"testing":[110,133],"using":[112,185],"compositional":[113],"interpreters":[114],"domain-specific":[117],"term":[118],"language":[119],"as":[120],"oracle":[123],"concrete":[125],"implementations.":[126],"demonstrate":[128],"usefulness":[130],"this":[132],"method":[134],"number":[137],"examples,":[139],"evaluate":[141],"mutation":[143],"testing.":[144],"show":[146],"that":[147,177],"our":[148,186],"suite":[150],"effective":[152],"killing":[154],"mutants":[155,157,170],"(90%":[156],"killed":[158,172],"75%":[160],"subject":[162],"agents).":[163],"More":[164],"importantly,":[165],"almost":[166],"half":[167],"all":[169],"are":[171],"by":[173],"generic":[174],"write-once-use-everywhere":[175],"tests":[176],"apply":[178],"to":[179],"any":[180,189],"problem":[183],"modeled":[184],"library,":[187],"without":[188],"additional":[190],"effort":[191],"from":[192],"programmer.":[194]},"counts_by_year":[{"year":2025,"cited_by_count":7}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}