{"id":"https://openalex.org/W4225533190","doi":"https://doi.org/10.1007/978-3-031-04083-2_11","title":"Interpretable, Verifiable, and Robust Reinforcement Learning via Program Synthesis","display_name":"Interpretable, Verifiable, and Robust Reinforcement Learning via Program Synthesis","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4225533190","doi":"https://doi.org/10.1007/978-3-031-04083-2_11"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-031-04083-2_11","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-031-04083-2_11","pdf_url":"https://link.springer.com/content/pdf/10.1007/978-3-031-04083-2_11.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/10.1007/978-3-031-04083-2_11.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","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":true,"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/A5020203532","display_name":"Jeevana Priya Inala","orcid":"https://orcid.org/0000-0003-1843-589X"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jeevana Priya Inala","raw_affiliation_strings":["Microsoft Research, Redmond, WA, 98052, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA, 98052, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010786661","display_name":"Armando Solar-Lezama","orcid":"https://orcid.org/0000-0001-7604-8252"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Armando Solar-Lezama","raw_affiliation_strings":["Massachusetts Institute of Technology, Cambridge, MA, 02139, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, MA, 02139, USA","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5029243071"],"corresponding_institution_ids":["https://openalex.org/I79576946"],"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":9,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"207","last_page":"228"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.996399998664856,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.996399998664856,"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":0.9898999929428101,"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.9868999719619751,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8891645669937134},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8521032333374023},{"id":"https://openalex.org/keywords/verifiable-secret-sharing","display_name":"Verifiable secret sharing","score":0.7382354736328125},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.6493065357208252},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6433594822883606},{"id":"https://openalex.org/keywords/black-box","display_name":"Black box","score":0.5381892919540405},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5288777351379395},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5122898817062378},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5087290406227112},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4875142276287079},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4526304304599762},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.11404049396514893},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.11055201292037964},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.05940335988998413}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8891645669937134},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8521032333374023},{"id":"https://openalex.org/C85847156","wikidata":"https://www.wikidata.org/wiki/Q59015987","display_name":"Verifiable secret sharing","level":3,"score":0.7382354736328125},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.6493065357208252},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6433594822883606},{"id":"https://openalex.org/C94966114","wikidata":"https://www.wikidata.org/wiki/Q29256","display_name":"Black box","level":2,"score":0.5381892919540405},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5288777351379395},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5122898817062378},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5087290406227112},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4875142276287079},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4526304304599762},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.11404049396514893},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.11055201292037964},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.05940335988998413},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-031-04083-2_11","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-031-04083-2_11","pdf_url":"https://link.springer.com/content/pdf/10.1007/978-3-031-04083-2_11.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"}],"best_oa_location":{"id":"doi:10.1007/978-3-031-04083-2_11","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-031-04083-2_11","pdf_url":"https://link.springer.com/content/pdf/10.1007/978-3-031-04083-2_11.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":[{"score":0.4099999964237213,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4225533190.pdf","grobid_xml":"https://content.openalex.org/works/W4225533190.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W146900863","https://openalex.org/W856973001","https://openalex.org/W1480909796","https://openalex.org/W1577785134","https://openalex.org/W1995691455","https://openalex.org/W2029058516","https://openalex.org/W2132525863","https://openalex.org/W2145339207","https://openalex.org/W2168359464","https://openalex.org/W2174803659","https://openalex.org/W2257979135","https://openalex.org/W2962775887","https://openalex.org/W2963575966","https://openalex.org/W2966260136","https://openalex.org/W3043557120","https://openalex.org/W3091691175","https://openalex.org/W3098218044","https://openalex.org/W3134310339","https://openalex.org/W3171035942","https://openalex.org/W3173598197","https://openalex.org/W3186708588","https://openalex.org/W3189981105","https://openalex.org/W4214717370","https://openalex.org/W4253977062","https://openalex.org/W4297957988","https://openalex.org/W4299968636","https://openalex.org/W6635361849","https://openalex.org/W6739901393","https://openalex.org/W6757459056","https://openalex.org/W6759199104","https://openalex.org/W6811020836"],"related_works":["https://openalex.org/W3184396788","https://openalex.org/W4377865163","https://openalex.org/W4312822655","https://openalex.org/W3157170264","https://openalex.org/W3193857078","https://openalex.org/W4312601715","https://openalex.org/W4298185893","https://openalex.org/W2888956734","https://openalex.org/W3208304128","https://openalex.org/W2896078964"],"abstract_inverted_index":{"Abstract":[0],"Reinforcement":[1],"learning":[2,19,50],"is":[3],"a":[4],"promising":[5],"strategy":[6],"for":[7,11],"automatically":[8],"training":[9,23],"policies":[10,51,62],"challenging":[12],"control":[13],"tasks.":[14],"However,":[15],"state-of-the-art":[16],"deep":[17,24],"reinforcement":[18],"algorithms":[20,79],"focus":[21],"on":[22],"neural":[25],"network":[26],"(DNN)":[27],"policies,":[28,84],"which":[29],"are":[30,35,63],"black":[31],"box":[32],"models":[33],"that":[34],"hard":[36],"to":[37,58,68,81],"interpret":[38],"and":[39,71,85],"reason":[40],"about.":[41],"In":[42],"this":[43],"chapter,":[44],"we":[45],"describe":[46,86],"recent":[47],"progress":[48],"towards":[49],"in":[52],"the":[53],"form":[54],"of":[55,78],"programs.":[56],"Compared":[57],"DNNs,":[59],"such":[60],"programmatic":[61,83],"significantly":[64],"more":[65,72],"interpretable,":[66],"easier":[67],"formally":[69],"verify,":[70],"robust.":[73],"We":[74],"give":[75],"an":[76],"overview":[77],"designed":[80],"learn":[82],"several":[87],"case":[88],"studies":[89],"demonstrating":[90],"their":[91],"various":[92],"advantages.":[93]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":5}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}