{"id":"https://openalex.org/W3089014878","doi":"https://doi.org/10.1145/3437992.3439927","title":"CertRL: formalizing convergence proofs for value and policy iteration in Coq","display_name":"CertRL: formalizing convergence proofs for value and policy iteration in Coq","publication_year":2021,"publication_date":"2021-01-17","ids":{"openalex":"https://openalex.org/W3089014878","doi":"https://doi.org/10.1145/3437992.3439927","mag":"3089014878"},"language":"en","primary_location":{"id":"doi:10.1145/3437992.3439927","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3437992.3439927","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 10th ACM SIGPLAN International Conference on Certified Programs and Proofs","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2009.11403","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5090846850","display_name":"Koundinya Vajjha","orcid":"https://orcid.org/0000-0003-3799-6326"},"institutions":[{"id":"https://openalex.org/I170201317","display_name":"University of Pittsburgh","ror":"https://ror.org/01an3r305","country_code":"US","type":"education","lineage":["https://openalex.org/I170201317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Koundinya Vajjha","raw_affiliation_strings":["University of Pittsburgh, USA"],"raw_orcid":"https://orcid.org/0000-0003-3799-6326","affiliations":[{"raw_affiliation_string":"University of Pittsburgh, USA","institution_ids":["https://openalex.org/I170201317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079889502","display_name":"Avraham Shinnar","orcid":"https://orcid.org/0000-0001-6259-0016"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Avraham Shinnar","raw_affiliation_strings":["IBM Research, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008523066","display_name":"Barry Trager","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Barry Trager","raw_affiliation_strings":["IBM Research, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002656257","display_name":"Vasily Pestun","orcid":"https://orcid.org/0000-0001-8014-4685"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vasily Pestun","raw_affiliation_strings":["IBM Research, USA / IHES, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research, USA / IHES, France","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069329835","display_name":"Nathan Fulton","orcid":"https://orcid.org/0000-0002-4172-7631"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nathan Fulton","raw_affiliation_strings":["IBM Research, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1522,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.47262812,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"18","last_page":"31"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10142","display_name":"Formal Methods in Verification","score":0.9962000250816345,"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"}},"topics":[{"id":"https://openalex.org/T10142","display_name":"Formal Methods in Verification","score":0.9962000250816345,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9955000281333923,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9891999959945679,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8841794729232788},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.8093079328536987},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7312749028205872},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.5138931274414062},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.47187915444374084},{"id":"https://openalex.org/keywords/mathematical-proof","display_name":"Mathematical proof","score":0.4311037063598633},{"id":"https://openalex.org/keywords/correctness","display_name":"Correctness","score":0.4107840061187744},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3536812663078308},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.32659289240837097},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.30734318494796753},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.28403112292289734},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.2737675607204437},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20231372117996216}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8841794729232788},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.8093079328536987},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7312749028205872},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.5138931274414062},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.47187915444374084},{"id":"https://openalex.org/C108710211","wikidata":"https://www.wikidata.org/wiki/Q11538","display_name":"Mathematical proof","level":2,"score":0.4311037063598633},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.4107840061187744},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3536812663078308},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.32659289240837097},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30734318494796753},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.28403112292289734},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.2737675607204437},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20231372117996216},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/3437992.3439927","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3437992.3439927","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 10th ACM SIGPLAN International Conference on Certified Programs and Proofs","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2009.11403","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2009.11403","pdf_url":"https://arxiv.org/pdf/2009.11403","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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:3089014878","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2009.11403.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"doi:10.48550/arxiv.2009.11403","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2009.11403","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2009.11403","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2009.11403","pdf_url":"https://arxiv.org/pdf/2009.11403","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.8100000023841858}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306151","display_name":"Alfred P. Sloan Foundation","ror":"https://ror.org/052csg198"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3089014878.pdf","grobid_xml":"https://content.openalex.org/works/W3089014878.grobid-xml"},"referenced_works_count":36,"referenced_works":["https://openalex.org/W342302233","https://openalex.org/W1975906542","https://openalex.org/W1980516134","https://openalex.org/W2028145673","https://openalex.org/W2030213839","https://openalex.org/W2050509196","https://openalex.org/W2099474694","https://openalex.org/W2106677467","https://openalex.org/W2119567691","https://openalex.org/W2154231274","https://openalex.org/W2155748644","https://openalex.org/W2257979135","https://openalex.org/W2312609093","https://openalex.org/W2529573675","https://openalex.org/W2546463436","https://openalex.org/W2561269734","https://openalex.org/W2562825158","https://openalex.org/W2605690278","https://openalex.org/W2613500637","https://openalex.org/W2747942685","https://openalex.org/W2784931892","https://openalex.org/W2785464537","https://openalex.org/W2787908307","https://openalex.org/W2798378744","https://openalex.org/W2892234234","https://openalex.org/W2903710663","https://openalex.org/W2952652756","https://openalex.org/W2963575966","https://openalex.org/W2963808954","https://openalex.org/W2987877727","https://openalex.org/W2995392093","https://openalex.org/W2999044305","https://openalex.org/W3039045514","https://openalex.org/W3043578334","https://openalex.org/W3100000179","https://openalex.org/W3122767180"],"related_works":["https://openalex.org/W3125631598","https://openalex.org/W3038962357","https://openalex.org/W169931978","https://openalex.org/W1626977535","https://openalex.org/W3198564127","https://openalex.org/W2170141744","https://openalex.org/W1548889916","https://openalex.org/W2150339816","https://openalex.org/W59916768","https://openalex.org/W1511927616","https://openalex.org/W2944639720","https://openalex.org/W3090442079","https://openalex.org/W2576525097","https://openalex.org/W1251831436","https://openalex.org/W3144370392","https://openalex.org/W1851714595","https://openalex.org/W2122942244","https://openalex.org/W2970694551","https://openalex.org/W3004970331","https://openalex.org/W1976275358"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,20,43,62],"algorithms":[2],"solve":[3],"sequential":[4],"decision-making":[5],"problems":[6],"in":[7,21,45],"probabilistic":[8],"environments":[9],"by":[10],"optimizing":[11],"for":[12],"long-term":[13],"reward.":[14],"The":[15,50],"desire":[16],"to":[17,65],"use":[18],"reinforcement":[19,33],"safety-critical":[22],"settings":[23],"inspires":[24],"a":[25,58],"recent":[26],"line":[27],"of":[28,41,54],"work":[29],"on":[30],"formally":[31],"constrained":[32],"learning;":[34],"however,":[35],"these":[36,55],"methods":[37],"place":[38],"the":[39,42,61],"implementation":[40],"algorithm":[44,63],"their":[46],"Trusted":[47],"Computing":[48],"Base.":[49],"crucial":[51],"correctness":[52],"property":[53],"implementations":[56],"is":[57],"guarantee":[59],"that":[60],"converges":[64],"an":[66],"optimal":[67],"policy.":[68]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}