{"id":"https://openalex.org/W4389610038","doi":"https://doi.org/10.1109/lra.2023.3341775","title":"Funnel-Based Reward Shaping for Signal Temporal Logic Tasks in Reinforcement Learning","display_name":"Funnel-Based Reward Shaping for Signal Temporal Logic Tasks in Reinforcement Learning","publication_year":2023,"publication_date":"2023-12-12","ids":{"openalex":"https://openalex.org/W4389610038","doi":"https://doi.org/10.1109/lra.2023.3341775"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2023.3341775","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2023.3341775","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-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/A5082531724","display_name":"Naman Saxena","orcid":"https://orcid.org/0000-0001-8400-5092"},"institutions":[{"id":"https://openalex.org/I59270414","display_name":"Indian Institute of Science Bangalore","ror":"https://ror.org/04dese585","country_code":"IN","type":"education","lineage":["https://openalex.org/I59270414"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Naman Saxena","raw_affiliation_strings":["Department of Computer Science and Automation, Indian Institute of Science, Bangalore, India"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Automation, Indian Institute of Science, Bangalore, India","institution_ids":["https://openalex.org/I59270414"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5097926779","display_name":"Sandeep Gorantla","orcid":"https://orcid.org/0009-0005-5892-5270"},"institutions":[{"id":"https://openalex.org/I59270414","display_name":"Indian Institute of Science Bangalore","ror":"https://ror.org/04dese585","country_code":"IN","type":"education","lineage":["https://openalex.org/I59270414"]},{"id":"https://openalex.org/I4210151956","display_name":"Robert Bosch (India)","ror":"https://ror.org/04my8ty22","country_code":"IN","type":"company","lineage":["https://openalex.org/I4210151956","https://openalex.org/I889804353"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sandeep Gorantla","raw_affiliation_strings":["Robert Bosch Center for Cyber-Physical Systems, Indian Institute of Science, Bangalore, India"],"affiliations":[{"raw_affiliation_string":"Robert Bosch Center for Cyber-Physical Systems, Indian Institute of Science, Bangalore, India","institution_ids":["https://openalex.org/I4210151956","https://openalex.org/I59270414"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073867567","display_name":"Pushpak Jagtap","orcid":"https://orcid.org/0000-0002-5452-8850"},"institutions":[{"id":"https://openalex.org/I59270414","display_name":"Indian Institute of Science Bangalore","ror":"https://ror.org/04dese585","country_code":"IN","type":"education","lineage":["https://openalex.org/I59270414"]},{"id":"https://openalex.org/I4210151956","display_name":"Robert Bosch (India)","ror":"https://ror.org/04my8ty22","country_code":"IN","type":"company","lineage":["https://openalex.org/I4210151956","https://openalex.org/I889804353"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Pushpak Jagtap","raw_affiliation_strings":["Robert Bosch Center for Cyber-Physical Systems, Indian Institute of Science, Bangalore, India"],"affiliations":[{"raw_affiliation_string":"Robert Bosch Center for Cyber-Physical Systems, Indian Institute of Science, Bangalore, India","institution_ids":["https://openalex.org/I4210151956","https://openalex.org/I59270414"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5082531724"],"corresponding_institution_ids":["https://openalex.org/I59270414"],"apc_list":null,"apc_paid":null,"fwci":1.6136,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.86453277,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"9","issue":"2","first_page":"1373","last_page":"1379"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10142","display_name":"Formal Methods in Verification","score":0.8626999855041504,"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":0.8626999855041504,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/funnel","display_name":"Funnel","score":0.7989197969436646},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7703085541725159},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.7064236402511597},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5612800717353821},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.5585045218467712},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.4329296946525574},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4238736927509308},{"id":"https://openalex.org/keywords/cognitive-science","display_name":"Cognitive science","score":0.38426727056503296},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.36996373534202576},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.1755695641040802},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0896492600440979}],"concepts":[{"id":"https://openalex.org/C17435862","wikidata":"https://www.wikidata.org/wiki/Q29957","display_name":"Funnel","level":2,"score":0.7989197969436646},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7703085541725159},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.7064236402511597},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5612800717353821},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.5585045218467712},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.4329296946525574},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4238736927509308},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.38426727056503296},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.36996373534202576},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.1755695641040802},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0896492600440979},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lra.2023.3341775","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2023.3341775","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1498432697","https://openalex.org/W1533557569","https://openalex.org/W1547304883","https://openalex.org/W1975219867","https://openalex.org/W2145339207","https://openalex.org/W2209913494","https://openalex.org/W2524638160","https://openalex.org/W2567705466","https://openalex.org/W2615395111","https://openalex.org/W2912250739","https://openalex.org/W2946780124","https://openalex.org/W2963190533","https://openalex.org/W2972788319","https://openalex.org/W4293872189","https://openalex.org/W4304731161","https://openalex.org/W4309793424","https://openalex.org/W4380558516","https://openalex.org/W4389610038","https://openalex.org/W6748599296","https://openalex.org/W6748839928","https://openalex.org/W6771753067","https://openalex.org/W6772627330","https://openalex.org/W6845987091","https://openalex.org/W6854089544"],"related_works":["https://openalex.org/W2073875810","https://openalex.org/W2356551568","https://openalex.org/W2081113335","https://openalex.org/W2358635018","https://openalex.org/W4242602405","https://openalex.org/W2364686644","https://openalex.org/W2889922688","https://openalex.org/W2368101485","https://openalex.org/W3201452447","https://openalex.org/W2098552852"],"abstract_inverted_index":{"Signal":[0],"Temporal":[1],"Logic":[2],"(STL)":[3],"is":[4],"a":[5,30,68,75],"powerful":[6],"framework":[7],"for":[8,78],"describing":[9],"the":[10,17,44,61,90],"complex":[11],"temporal":[12],"and":[13,54],"logical":[14],"behaviour":[15],"of":[16,46,63,81,92],"dynamical":[18],"system.":[19],"Numerous":[20],"studies":[21],"have":[22,38],"attempted":[23],"to":[24,28,41,73],"employ":[25],"reinforcement":[26,70],"learning":[27,71],"learn":[29,74],"controller":[31],"that":[32],"enforces":[33],"STL":[34,82,97],"specifications;":[35],"however,":[36],"they":[37],"been":[39],"unable":[40],"effectively":[42],"tackle":[43],"challenges":[45],"ensuring":[47],"robust":[48,79],"satisfaction":[49,80],"in":[50,84],"continuous":[51,85],"state":[52,86],"space":[53],"maintaining":[55],"tractability.":[56],"In":[57],"this":[58],"letter,":[59],"leveraging":[60],"concept":[62],"funnel":[64],"functions,":[65],"we":[66],"propose":[67],"tractable":[69],"algorithm":[72],"time-dependent":[76],"policy":[77],"specification":[83],"space.":[87],"We":[88],"demonstrate":[89],"utility":[91],"our":[93],"approach":[94],"on":[95],"several":[96],"tasks":[98],"using":[99],"different":[100],"environments.":[101]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}