{"id":"https://openalex.org/W3043557120","doi":"https://doi.org/10.1007/978-3-030-53291-8_30","title":"Program Synthesis Using Deduction-Guided Reinforcement Learning","display_name":"Program Synthesis Using Deduction-Guided Reinforcement Learning","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3043557120","doi":"https://doi.org/10.1007/978-3-030-53291-8_30","mag":"3043557120"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-030-53291-8_30","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-030-53291-8_30","pdf_url":"https://link.springer.com/content/pdf/10.1007%2F978-3-030-53291-8_30.pdf","source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007%2F978-3-030-53291-8_30.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101573237","display_name":"Yanju Chen","orcid":"https://orcid.org/0000-0002-6494-3126"},"institutions":[{"id":"https://openalex.org/I154570441","display_name":"University of California, Santa Barbara","ror":"https://ror.org/02t274463","country_code":"US","type":"education","lineage":["https://openalex.org/I154570441"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yanju Chen","raw_affiliation_strings":["University of California, Santa Barbara, Santa Barbara, CA, 93106, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Santa Barbara, Santa Barbara, CA, 93106, USA","institution_ids":["https://openalex.org/I154570441"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100367825","display_name":"Chenglong Wang","orcid":"https://orcid.org/0000-0003-2391-0923"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]},{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chenglong Wang","raw_affiliation_strings":["University of Southern California, Los Angeles, CA, USA","University of Washington, Seattle, WA, 98115, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"University of Washington, Seattle, WA, 98115, USA","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029243071","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, PA, 19104, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Pennsylvania, Philadelphia, PA, 19104, USA","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006424908","display_name":"I\u015f\u0131l Dillig","orcid":"https://orcid.org/0000-0001-8006-1230"},"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":"Isil Dillig","raw_affiliation_strings":["The University of Texas at Austin, Austin, TX, 78712, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin, Austin, TX, 78712, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101567136","display_name":"Yu Feng","orcid":"https://orcid.org/0000-0003-1000-1229"},"institutions":[{"id":"https://openalex.org/I154570441","display_name":"University of California, Santa Barbara","ror":"https://ror.org/02t274463","country_code":"US","type":"education","lineage":["https://openalex.org/I154570441"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yu Feng","raw_affiliation_strings":["University of California, Santa Barbara, Santa Barbara, CA, 93106, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California, Santa Barbara, Santa Barbara, CA, 93106, USA","institution_ids":["https://openalex.org/I154570441"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":{"value":5000,"currency":"EUR","value_usd":5392},"fwci":null,"has_fulltext":true,"cited_by_count":30,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"587","last_page":"610"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9988999962806702,"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":0.9988999962806702,"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":0.9972000122070312,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9904999732971191,"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/computer-science","display_name":"Computer science","score":0.8467003107070923},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8412793874740601},{"id":"https://openalex.org/keywords/program-synthesis","display_name":"Program synthesis","score":0.5357286930084229},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4180186092853546},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3364368677139282},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3011966347694397}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8467003107070923},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8412793874740601},{"id":"https://openalex.org/C2776937632","wikidata":"https://www.wikidata.org/wiki/Q4117718","display_name":"Program synthesis","level":2,"score":0.5357286930084229},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4180186092853546},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3364368677139282},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3011966347694397}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/978-3-030-53291-8_30","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-030-53291-8_30","pdf_url":"https://link.springer.com/content/pdf/10.1007%2F978-3-030-53291-8_30.pdf","source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},{"id":"pmh:oai:pubmedcentral.nih.gov:7363208","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/7363208","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"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":"Computer Aided Verification","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1007/978-3-030-53291-8_30","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-030-53291-8_30","pdf_url":"https://link.springer.com/content/pdf/10.1007%2F978-3-030-53291-8_30.pdf","source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/17","display_name":"Partnerships for the goals","score":0.4399999976158142}],"awards":[{"id":"https://openalex.org/G5503499271","display_name":"SHF: Small: Scalable Program Synthesis using Counterexample-Guided Abstraction Refinement","funder_award_id":"1811865","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5985606540","display_name":"SaTC: CORE: Medium: Collaborative: Effective Formal Reasoning for Mobile Malware","funder_award_id":"1908494","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6901837805","display_name":"SHF: Small: Inferring Specifications for Blackbox Code","funder_award_id":"1910769","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"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3043557120.pdf","grobid_xml":"https://content.openalex.org/works/W3043557120.grobid-xml"},"referenced_works_count":67,"referenced_works":["https://openalex.org/W1480909796","https://openalex.org/W1526922602","https://openalex.org/W1858945639","https://openalex.org/W2013596093","https://openalex.org/W2057156093","https://openalex.org/W2060610732","https://openalex.org/W2093535699","https://openalex.org/W2094878426","https://openalex.org/W2096307462","https://openalex.org/W2104733512","https://openalex.org/W2130942839","https://openalex.org/W2132525863","https://openalex.org/W2134734244","https://openalex.org/W2149236697","https://openalex.org/W2155027007","https://openalex.org/W2157331557","https://openalex.org/W2263738566","https://openalex.org/W2531982678","https://openalex.org/W2550100435","https://openalex.org/W2550120381","https://openalex.org/W2550471858","https://openalex.org/W2561055248","https://openalex.org/W2625764229","https://openalex.org/W2626990892","https://openalex.org/W2740130372","https://openalex.org/W2762513422","https://openalex.org/W2765742677","https://openalex.org/W2767301967","https://openalex.org/W2786248241","https://openalex.org/W2884243532","https://openalex.org/W2888925928","https://openalex.org/W2891160484","https://openalex.org/W2891691255","https://openalex.org/W2899212285","https://openalex.org/W2905664673","https://openalex.org/W2910040435","https://openalex.org/W2949084598","https://openalex.org/W2949800357","https://openalex.org/W2949895386","https://openalex.org/W2950006889","https://openalex.org/W2950863242","https://openalex.org/W2951766328","https://openalex.org/W2952356355","https://openalex.org/W2952466824","https://openalex.org/W2953054522","https://openalex.org/W2953388933","https://openalex.org/W2955270045","https://openalex.org/W2963102152","https://openalex.org/W2963393993","https://openalex.org/W2963426888","https://openalex.org/W2963929497","https://openalex.org/W2964240296","https://openalex.org/W2964362549","https://openalex.org/W2968700020","https://openalex.org/W2971291256","https://openalex.org/W2971324190","https://openalex.org/W2979746918","https://openalex.org/W2980180246","https://openalex.org/W2982614426","https://openalex.org/W2995746305","https://openalex.org/W3011737828","https://openalex.org/W3033889389","https://openalex.org/W3195542280","https://openalex.org/W4251125603","https://openalex.org/W4255584681","https://openalex.org/W6600741150","https://openalex.org/W6634978047"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W3046775127","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W3107602296","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347"],"abstract_inverted_index":{"In":[0,154],"this":[1,26,81],"paper,":[2],"we":[3,46],"present":[4],"a":[5,41,51,57,70,96,122,164],"new":[6,58],"program":[7,48],"synthesis":[8,49,131,145,166,170],"algorithm":[9,64],"based":[10],"on":[11,130,176],"reinforcement":[12,52],"learning.":[13],"Given":[14],"an":[15],"initial":[16],"policy":[17,27,62],"(i.e.":[18],"statistical":[19,76,93],"model)":[20],"trained":[21],"off-line,":[22],"our":[23,151],"method":[24],"uses":[25],"to":[28,105,112,162],"guide":[29,113],"its":[30],"search":[31,108],"and":[32,55,92,126,142],"gradually":[33],"improves":[34],"it":[35,86,100,129],"by":[36,172,182],"leveraging":[37],"feedback":[38,68],"obtained":[39],"from":[40,69],"deductive":[42,91],"reasoning":[43,94],"engine.":[44],"Specifically,":[45],"formulate":[47],"as":[50],"learning":[53],"problem":[54],"propose":[56],"variant":[59],"of":[60,80,90,150],"the":[61,74,88,107,118,148],"gradient":[63],"that":[65,178],"can":[66,179],"incorporate":[67],"deduction":[71,102],"engine":[72],"into":[73],"underlying":[75],"model.":[77],"The":[78],"benefit":[79],"approach":[82,120],"is":[83],"two-fold:":[84],"First,":[85],"combines":[87],"power":[89],"in":[95,121,134],"unified":[97],"framework.":[98],"Second,":[99],"leverages":[101],"not":[103],"only":[104],"prune":[106],"space":[109],"but":[110],"also":[111],"search.":[114],"We":[115],"have":[116],"implemented":[117],"proposed":[119,152],"tool":[123],"called":[124],"Concord":[125,156],"experimentally":[127],"evaluate":[128],"tasks":[132],"studied":[133],"prior":[135],"work.":[136],"Our":[137],"comparison":[138],"against":[139],"several":[140],"baselines":[141],"two":[143],"existing":[144],"tools":[146],"shows":[147],"advantages":[149],"approach.":[153],"particular,":[155],"solves":[157],"15%":[158],"more":[159],"benchmarks":[160,177],"compared":[161],"Neo,":[163],"state-of-the-art":[165],"tool,":[167],"while":[168],"improving":[169],"time":[171],"8.71":[173],"$$\\times":[174],"$$":[175],"be":[180],"solved":[181],"both":[183],"tools.":[184]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}