{"id":"https://openalex.org/W4225411334","doi":"https://doi.org/10.1145/3501710.3524914","title":"Poster Abstract: Learning from Demonstrations with Temporal Logics","display_name":"Poster Abstract: Learning from Demonstrations with Temporal Logics","publication_year":2022,"publication_date":"2022-04-28","ids":{"openalex":"https://openalex.org/W4225411334","doi":"https://doi.org/10.1145/3501710.3524914"},"language":"en","primary_location":{"id":"doi:10.1145/3501710.3524914","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3501710.3524914","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3501710.3524914","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"25th ACM International Conference on Hybrid Systems: Computation and Control","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3501710.3524914","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010006741","display_name":"Aniruddh G. Puranic","orcid":"https://orcid.org/0000-0003-0010-9789"},"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"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Aniruddh Puranic","raw_affiliation_strings":["Department of Computer Science, University of Southern California, United States"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Southern California, United States","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057473400","display_name":"Jyotirmoy V. Deshmukh","orcid":"https://orcid.org/0000-0003-4683-5540"},"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jyotirmoy Deshmukh","raw_affiliation_strings":["Department of Computer Science, University of Southern California, United States"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Southern California, United States","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042344629","display_name":"Stefanos Nikolaidis","orcid":"https://orcid.org/0000-0002-8617-3871"},"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stefanos Nikolaidis","raw_affiliation_strings":["Department of Computer Science, University of Southern California, United States"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Southern California, United States","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5010006741"],"corresponding_institution_ids":["https://openalex.org/I1174212"],"apc_list":null,"apc_paid":null,"fwci":0.4134,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.66718023,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"2"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9713000059127808,"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":0.9713000059127808,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9537000060081482,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.941100001335144,"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/interpretability","display_name":"Interpretability","score":0.9414737224578857},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8020045757293701},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7991654276847839},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6332979798316956},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5714468955993652},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.559816300868988},{"id":"https://openalex.org/keywords/temporal-logic","display_name":"Temporal logic","score":0.538112223148346},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4890347421169281},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.4665016531944275},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.44473928213119507},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.20786452293395996},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.14533308148384094},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07569801807403564}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.9414737224578857},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8020045757293701},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7991654276847839},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6332979798316956},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5714468955993652},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.559816300868988},{"id":"https://openalex.org/C25016198","wikidata":"https://www.wikidata.org/wiki/Q781833","display_name":"Temporal logic","level":2,"score":0.538112223148346},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4890347421169281},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.4665016531944275},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.44473928213119507},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.20786452293395996},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.14533308148384094},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07569801807403564},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3501710.3524914","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3501710.3524914","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3501710.3524914","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"25th ACM International Conference on Hybrid Systems: Computation and Control","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3501710.3524914","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3501710.3524914","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3501710.3524914","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"25th ACM International Conference on Hybrid Systems: Computation and Control","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1889334499","display_name":"FMitF: A Novel Framework for Learning Formal Abstractions and Causal Relations from Temporal Behaviors","funder_award_id":"1837131","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4185534415","display_name":"CAREER: A Framework for Logic-based Requirements to guide Safe Deep Learning for Autonomous Mobile Systems","funder_award_id":"2048094","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4835183429","display_name":null,"funder_award_id":"SHF-2048094, CCF-1837131, CNS-1932620","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4851802478","display_name":null,"funder_award_id":"SHF-2048094","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5876574054","display_name":null,"funder_award_id":"1932620","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6671297155","display_name":null,"funder_award_id":"CAREER","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8116892299","display_name":null,"funder_award_id":"CCF-1837131","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8535605147","display_name":null,"funder_award_id":"CNS-1932620","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/W4225411334.pdf","grobid_xml":"https://content.openalex.org/works/W4225411334.grobid-xml"},"referenced_works_count":2,"referenced_works":["https://openalex.org/W3176233416","https://openalex.org/W4225411334"],"related_works":["https://openalex.org/W2905433371","https://openalex.org/W4390569940","https://openalex.org/W2888392564","https://openalex.org/W4361193272","https://openalex.org/W4310278675","https://openalex.org/W4388422664","https://openalex.org/W2806259446","https://openalex.org/W2963326959","https://openalex.org/W4247136043","https://openalex.org/W4312407344"],"abstract_inverted_index":{"Learning-from-demonstrations":[0],"(LfD)":[1],"is":[2,28],"a":[3],"popular":[4],"paradigm":[5],"to":[6,21,30,53,59,69,82,120,136],"obtain":[7],"effective":[8],"robot":[9],"control":[10,45],"policies":[11],"for":[12,123,150],"complex":[13],"tasks":[14,63,96],"via":[15],"reinforcement":[16,124],"learning":[17,125],"without":[18],"the":[19,43,73,152],"need":[20],"explicitly":[22],"design":[23],"reward":[24],"functions.":[25],"However,":[26],"it":[27],"susceptible":[29],"imperfections":[31],"in":[32,42,158],"demonstrations":[33,116],"and":[34,40,64,71,86,117,156],"also":[35,88],"raises":[36],"concerns":[37],"of":[38,75,90,154],"safety":[39],"interpretability":[41,157],"learned":[44],"policies.":[46],"To":[47],"address":[48],"these":[49],"issues,":[50],"we":[51],"propose":[52],"use":[54,65],"Signal":[55],"Temporal":[56,77],"Logic":[57],"(STL)":[58],"express":[60],"high-level":[61],"robotic":[62],"its":[66],"quantitative":[67],"semantics":[68],"evaluate":[70],"rank":[72],"quality":[74],"demonstrations.":[76],"logic-based":[78],"specifications":[79,119],"allow":[80],"us":[81],"create":[83],"non-Markovian":[84],"rewards,":[85],"are":[87],"capable":[89],"defining":[91],"interesting":[92],"causal":[93],"dependencies":[94],"between":[95],"such":[97,159],"as":[98],"sequential":[99],"task":[100],"specifications.":[101],"We":[102,127,145],"present":[103],"our":[104,130,139],"completed":[105],"work":[106],"that":[107,111],"proposed":[108],"LfD-STL":[109],"framework":[110],"learns":[112],"from":[113],"even":[114],"suboptimal/imperfect":[115],"STL":[118],"infer":[121],"rewards":[122],"tasks.":[126],"have":[128],"validated":[129],"approach":[131],"through":[132],"various":[133],"experimental":[134],"setups":[135],"show":[137],"how":[138],"method":[140],"outperforms":[141],"prior":[142],"LfD":[143],"methods.":[144],"then":[146],"discuss":[147],"future":[148],"directions":[149],"tackling":[151],"problem":[153],"explainability":[155],"learning-based":[160],"systems.":[161]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-03-18T14:38:29.013473","created_date":"2025-10-10T00:00:00"}