{"id":"https://openalex.org/W4401413822","doi":"https://doi.org/10.1109/icra57147.2024.10610510","title":"Synthesis of Temporally-Robust Policies for Signal Temporal Logic Tasks using Reinforcement Learning","display_name":"Synthesis of Temporally-Robust Policies for Signal Temporal Logic Tasks using Reinforcement Learning","publication_year":2024,"publication_date":"2024-05-13","ids":{"openalex":"https://openalex.org/W4401413822","doi":"https://doi.org/10.1109/icra57147.2024.10610510"},"language":"en","primary_location":{"id":"doi:10.1109/icra57147.2024.10610510","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icra57147.2024.10610510","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-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/A5102730865","display_name":"Siqi Wang","orcid":"https://orcid.org/0000-0003-3186-7785"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Siqi Wang","raw_affiliation_strings":["Shanghai Jiao Tong University,Department of Automation and Key Laboratory of System Control and Information Processing,Shanghai,China,200240"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Department of Automation and Key Laboratory of System Control and Information Processing,Shanghai,China,200240","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041126305","display_name":"Shaoyuan Li","orcid":"https://orcid.org/0000-0003-3427-2912"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaoyuan Li","raw_affiliation_strings":["Shanghai Jiao Tong University,Department of Automation and Key Laboratory of System Control and Information Processing,Shanghai,China,200240"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Department of Automation and Key Laboratory of System Control and Information Processing,Shanghai,China,200240","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008928096","display_name":"Li Yin","orcid":"https://orcid.org/0000-0002-0456-1775"},"institutions":[{"id":"https://openalex.org/I111950717","display_name":"Macau University of Science and Technology","ror":"https://ror.org/03jqs2n27","country_code":"MO","type":"education","lineage":["https://openalex.org/I111950717","https://openalex.org/I4391767947"]}],"countries":["MO"],"is_corresponding":false,"raw_author_name":"Li Yin","raw_affiliation_strings":["Macau University of Science and Technology,Institute of Systems Engineering,Taipa,China"],"affiliations":[{"raw_affiliation_string":"Macau University of Science and Technology,Institute of Systems Engineering,Taipa,China","institution_ids":["https://openalex.org/I111950717"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034304769","display_name":"Xiang Yin","orcid":"https://orcid.org/0000-0003-1944-1570"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiang Yin","raw_affiliation_strings":["Shanghai Jiao Tong University,Department of Automation and Key Laboratory of System Control and Information Processing,Shanghai,China,200240"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,Department of Automation and Key Laboratory of System Control and Information Processing,Shanghai,China,200240","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5102730865"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":1.6207,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.84556037,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"10503","last_page":"10509"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10142","display_name":"Formal Methods in Verification","score":0.9987000226974487,"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":0.9987000226974487,"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":0.9858999848365784,"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/T11596","display_name":"Constraint Satisfaction and Optimization","score":0.9847999811172485,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.7601314783096313},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7137197256088257},{"id":"https://openalex.org/keywords/temporal-logic","display_name":"Temporal logic","score":0.48105835914611816},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.4494485557079315},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43428370356559753},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.23987135291099548},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.14923810958862305}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7601314783096313},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7137197256088257},{"id":"https://openalex.org/C25016198","wikidata":"https://www.wikidata.org/wiki/Q781833","display_name":"Temporal logic","level":2,"score":0.48105835914611816},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.4494485557079315},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43428370356559753},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.23987135291099548},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.14923810958862305}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra57147.2024.10610510","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icra57147.2024.10610510","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W1533557569","https://openalex.org/W1547304883","https://openalex.org/W2092884371","https://openalex.org/W2101804404","https://openalex.org/W2167799541","https://openalex.org/W2524638160","https://openalex.org/W2607424191","https://openalex.org/W2841721725","https://openalex.org/W2886331135","https://openalex.org/W2937276195","https://openalex.org/W2980133010","https://openalex.org/W3001024844","https://openalex.org/W3048348667","https://openalex.org/W3137252442","https://openalex.org/W3149132974","https://openalex.org/W3153191410","https://openalex.org/W3185320737","https://openalex.org/W3201878770","https://openalex.org/W4210600503","https://openalex.org/W4210750948","https://openalex.org/W4225386864","https://openalex.org/W4229029576","https://openalex.org/W4286001025","https://openalex.org/W4304547391","https://openalex.org/W4309793424","https://openalex.org/W4315488730","https://openalex.org/W4389235528","https://openalex.org/W4391020489","https://openalex.org/W4391021338","https://openalex.org/W6772627330"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4306904969","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2138720691","https://openalex.org/W2376932109","https://openalex.org/W4362501864","https://openalex.org/W2001405890"],"abstract_inverted_index":{"This":[0],"paper":[1],"investigates":[2],"the":[3,30,53,71,75,84,100,137,146,157],"problem":[4],"of":[5,33,55,74,86,145,159],"designing":[6],"control":[7,67,117,127],"policies":[8],"that":[9,132],"satisfy":[10],"high-level":[11],"specifications":[12],"described":[13],"by":[14,42],"signal":[15],"temporal":[16,45,72],"logic":[17],"(STL)":[18],"in":[19,58,129,143],"unknown,":[20],"stochastic":[21],"environments.":[22],"While":[23],"many":[24],"existing":[25],"works":[26],"concentrate":[27],"on":[28],"optimizing":[29],"spatial":[31,102],"robustness":[32,46,73,103],"a":[34,39,48,91,106,130],"system,":[35],"our":[36,160],"work":[37],"takes":[38],"step":[40],"further":[41],"also":[43,149],"considering":[44],"as":[47],"critical":[49],"metric":[50],"to":[51,69,82,98,114,135,155],"quantify":[52],"tolerance":[54],"time":[56,108],"uncertainty":[57],"STL.":[59],"To":[60],"this":[61],"end,":[62],"we":[63,124],"formulate":[64],"two":[65],"relevant":[66],"objectives":[68,128],"enhance":[70],"synthesized":[76],"policies.":[77],"The":[78,94],"first":[79],"objective":[80,96],"is":[81,97],"maximize":[83,99],"probability":[85],"being":[87],"temporally":[88],"robust":[89],"for":[90,120],"given":[92],"threshold.":[93],"second":[95],"worst-case":[101],"value":[104],"within":[105],"bounded":[107],"shift.":[109],"We":[110,151],"use":[111],"reinforcement":[112],"learning":[113],"solve":[115],"both":[116,126],"synthesis":[118],"problems":[119],"unknown":[121],"systems.":[122],"Specifically,":[123],"approximate":[125],"way":[131],"enables":[133],"us":[134],"apply":[136],"standard":[138],"Q-learning":[139],"algorithm.":[140],"Theoretical":[141],"bounds":[142],"terms":[144],"approximations":[147],"are":[148],"derived.":[150],"present":[152],"case":[153],"studies":[154],"demonstrate":[156],"feasibility":[158],"approach.":[161]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3}],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}