{"id":"https://openalex.org/W7125902681","doi":"https://doi.org/10.1145/3744706","title":"Specification-Guided Reinforcement Learning","display_name":"Specification-Guided Reinforcement Learning","publication_year":2026,"publication_date":"2026-01-28","ids":{"openalex":"https://openalex.org/W7125902681","doi":"https://doi.org/10.1145/3744706"},"language":"en","primary_location":{"id":"doi:10.1145/3744706","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3744706","pdf_url":null,"source":{"id":"https://openalex.org/S103482838","display_name":"Communications of the ACM","issn_l":"0001-0782","issn":["0001-0782","1557-7317"],"is_oa":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Communications of the ACM","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5110227759","display_name":"Rajeev Alur","orcid":null},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rajeev Alur","raw_affiliation_strings":["University of Pennsylvania, Philadelphia, Pennsylvania, United States"],"raw_orcid":"https://orcid.org/0000-0003-1733-7083","affiliations":[{"raw_affiliation_string":"University of Pennsylvania, Philadelphia, Pennsylvania, United States","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063106552","display_name":"Suguman Bansal","orcid":"https://orcid.org/0000-0002-0405-073X"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Suguman Bansal","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, Georgia, United States"],"raw_orcid":"https://orcid.org/0000-0002-0405-073X","affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, Georgia, United States","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Osbert Bastani","orcid":"https://orcid.org/0000-0001-9990-7566"},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Osbert Bastani","raw_affiliation_strings":["University of Pennsylvania, Philadelphia, Pennsylvania, United States"],"raw_orcid":"https://orcid.org/0000-0001-9990-7566","affiliations":[{"raw_affiliation_string":"University of Pennsylvania, Philadelphia, Pennsylvania, United States","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055988569","display_name":"Kishor Jothimurugan","orcid":"https://orcid.org/0000-0003-1448-2947"},"institutions":[{"id":"https://openalex.org/I4210139661","display_name":"Two Sigma Investments (United States)","ror":"https://ror.org/04gjcva23","country_code":"US","type":"company","lineage":["https://openalex.org/I4210139661"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kishor Jothimurugan","raw_affiliation_strings":["Two Sigma Investments, LP, New York, New York, United States"],"raw_orcid":"https://orcid.org/0000-0003-1448-2947","affiliations":[{"raw_affiliation_string":"Two Sigma Investments, LP, New York, New York, United States","institution_ids":["https://openalex.org/I4210139661"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.09938924,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"69","issue":"2","first_page":"80","last_page":"87"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.2937999963760376,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.2937999963760376,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.20440000295639038,"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":0.11400000005960464,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7055000066757202},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.6786999702453613},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.3262999951839447},{"id":"https://openalex.org/keywords/logical-conjunction","display_name":"Logical conjunction","score":0.24729999899864197},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.24500000476837158}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7422999739646912},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7055000066757202},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.6786999702453613},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5297999978065491},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3402999937534332},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.3262999951839447},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.29750001430511475},{"id":"https://openalex.org/C21847791","wikidata":"https://www.wikidata.org/wiki/Q191081","display_name":"Logical conjunction","level":2,"score":0.24729999899864197},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.24500000476837158},{"id":"https://openalex.org/C47932503","wikidata":"https://www.wikidata.org/wiki/Q5395689","display_name":"Error-driven learning","level":3,"score":0.23819999396800995}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3744706","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3744706","pdf_url":null,"source":{"id":"https://openalex.org/S103482838","display_name":"Communications of the ACM","issn_l":"0001-0782","issn":["0001-0782","1557-7317"],"is_oa":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Communications of the ACM","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6925521478","display_name":null,"funder_award_id":"N00014-20-1-2115","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G8011581273","display_name":null,"funder_award_id":"SLES 2331783","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W2023808162","https://openalex.org/W2129670787","https://openalex.org/W2524638160","https://openalex.org/W2567705466","https://openalex.org/W2895196950","https://openalex.org/W2963778636","https://openalex.org/W2964890016","https://openalex.org/W3011250830","https://openalex.org/W3090827750","https://openalex.org/W3201037672","https://openalex.org/W3208792968","https://openalex.org/W3213843225","https://openalex.org/W4289874473","https://openalex.org/W4384471509"],"related_works":[],"abstract_inverted_index":{"A":[0],"tutorial-style":[1],"introduction":[2],"to":[3,10],"recent":[4],"research":[5],"on":[6],"using":[7],"logical":[8],"specifications":[9],"encode":[11],"RL":[12],"tasks":[13],"illustrates":[14],"theoretical":[15],"limitations":[16],"and":[17],"practical":[18],"solutions.":[19]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2026-01-29T00:00:00"}