{"id":"https://openalex.org/W4412544449","doi":"https://doi.org/10.1007/978-3-031-98685-7_4","title":"Deductive Synthesis of\u00a0Reinforcement Learning Agents for\u00a0Infinite Horizon Tasks","display_name":"Deductive Synthesis of\u00a0Reinforcement Learning Agents for\u00a0Infinite Horizon Tasks","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412544449","doi":"https://doi.org/10.1007/978-3-031-98685-7_4"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-031-98685-7_4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-031-98685-7_4","pdf_url":"https://link.springer.com/content/pdf/10.1007/978-3-031-98685-7_4.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":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/978-3-031-98685-7_4.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5066740799","display_name":"Yuning Wang","orcid":"https://orcid.org/0009-0000-4317-9758"},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yuning Wang","raw_affiliation_strings":["Rutgers University, New Brunswick, NJ, USA"],"raw_orcid":"https://orcid.org/0009-0000-4317-9758","affiliations":[{"raw_affiliation_string":"Rutgers University, New Brunswick, NJ, USA","institution_ids":["https://openalex.org/I102322142"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004145814","display_name":"He Zhu","orcid":"https://orcid.org/0000-0001-9606-150X"},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"He Zhu","raw_affiliation_strings":["Rutgers University, New Brunswick, NJ, USA"],"raw_orcid":"https://orcid.org/0000-0001-9606-150X","affiliations":[{"raw_affiliation_string":"Rutgers University, New Brunswick, NJ, USA","institution_ids":["https://openalex.org/I102322142"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5066740799"],"corresponding_institution_ids":["https://openalex.org/I102322142"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":{"value":5000,"currency":"EUR","value_usd":5392},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.29340425,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"79","last_page":"103"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9962000250816345,"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":0.9962000250816345,"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/T10320","display_name":"Neural Networks and Applications","score":0.9894999861717224,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9884999990463257,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.837736964225769},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8205465078353882},{"id":"https://openalex.org/keywords/horizon","display_name":"Horizon","score":0.5228786468505859},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44514015316963196},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.42485958337783813},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08160960674285889},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.04828372597694397},{"id":"https://openalex.org/keywords/geometry","display_name":"Geometry","score":0.041032999753952026}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.837736964225769},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8205465078353882},{"id":"https://openalex.org/C159176650","wikidata":"https://www.wikidata.org/wiki/Q43261","display_name":"Horizon","level":2,"score":0.5228786468505859},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44514015316963196},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.42485958337783813},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08160960674285889},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.04828372597694397},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.041032999753952026},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-031-98685-7_4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-031-98685-7_4","pdf_url":"https://link.springer.com/content/pdf/10.1007/978-3-031-98685-7_4.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:10.1007/978-3-031-98685-7_4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-031-98685-7_4","pdf_url":"https://link.springer.com/content/pdf/10.1007/978-3-031-98685-7_4.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":[],"awards":[{"id":"https://openalex.org/G6459571137","display_name":"FMitF: Track I: Synthesis and Verification for Programmatic Reinforcement Learning","funder_award_id":"2124155","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7725450306","display_name":"SHF: Small: Formal Symbolic Reasoning of Deep Reinforcement Learning Systems","funder_award_id":"2007799","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":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412544449.pdf","grobid_xml":"https://content.openalex.org/works/W4412544449.grobid-xml"},"referenced_works_count":50,"referenced_works":["https://openalex.org/W172589331","https://openalex.org/W1565544898","https://openalex.org/W1600437712","https://openalex.org/W1607353007","https://openalex.org/W1838714828","https://openalex.org/W2011979623","https://openalex.org/W2033455284","https://openalex.org/W2071797744","https://openalex.org/W2079042739","https://openalex.org/W2091932875","https://openalex.org/W2100538121","https://openalex.org/W2116680678","https://openalex.org/W2145970716","https://openalex.org/W2151958719","https://openalex.org/W2156051490","https://openalex.org/W2164451522","https://openalex.org/W2337661843","https://openalex.org/W2347006063","https://openalex.org/W2567705466","https://openalex.org/W2616890610","https://openalex.org/W2899116309","https://openalex.org/W2905277694","https://openalex.org/W2911293880","https://openalex.org/W2938701611","https://openalex.org/W2952454357","https://openalex.org/W2964130946","https://openalex.org/W2964326012","https://openalex.org/W2966537673","https://openalex.org/W3004091789","https://openalex.org/W3011006546","https://openalex.org/W3023554972","https://openalex.org/W3046272654","https://openalex.org/W3080398910","https://openalex.org/W3080598349","https://openalex.org/W3090827750","https://openalex.org/W3091798065","https://openalex.org/W3092156990","https://openalex.org/W3104168345","https://openalex.org/W3124237877","https://openalex.org/W3130777366","https://openalex.org/W4290087551","https://openalex.org/W4366451070","https://openalex.org/W4385063004","https://openalex.org/W4385768249","https://openalex.org/W4395680447","https://openalex.org/W4400995688","https://openalex.org/W6600741150","https://openalex.org/W6602430163","https://openalex.org/W6603590957","https://openalex.org/W6814003322"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856"],"abstract_inverted_index":{"Abstract":[0],"We":[1],"propose":[2],"a":[3,29,51,69],"deductive":[4],"synthesis":[5],"framework":[6],"for":[7,34],"constructing":[8],"reinforcement":[9],"learning":[10],"(RL)":[11],"agents":[12,77],"that":[13,47,74],"provably":[14],"satisfy":[15],"temporal":[16,26,91],"reach-avoid":[17],"specifications":[18,27],"over":[19,63],"infinite":[20,64],"horizons.":[21,65],"Our":[22],"approach":[23],"decomposes":[24],"these":[25],"into":[28],"sequence":[30],"of":[31,50,54,59,71],"finite-horizon":[32],"subtasks,":[33],"which":[35],"we":[36,45],"synthesize":[37],"individual":[38],"RL":[39,80],"policies.":[40],"Using":[41],"formal":[42],"verification":[43],"techniques,":[44],"ensure":[46],"the":[48,60],"composition":[49],"finite":[52],"number":[53],"subtask":[55],"policies":[56],"guarantees":[57],"satisfaction":[58],"overall":[61],"specification":[62],"Experimental":[66],"results":[67],"on":[68],"suite":[70],"benchmarks":[72],"show":[73],"our":[75],"synthesized":[76],"outperform":[78],"standard":[79],"methods":[81],"in":[82],"both":[83],"task":[84],"performance":[85],"and":[86,90],"compliance":[87],"with":[88],"safety":[89],"requirements.":[92]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}