{"id":"https://openalex.org/W2567705466","doi":"https://doi.org/10.1109/iros.2017.8206234","title":"Reinforcement learning with temporal logic rewards","display_name":"Reinforcement learning with temporal logic rewards","publication_year":2017,"publication_date":"2017-09-01","ids":{"openalex":"https://openalex.org/W2567705466","doi":"https://doi.org/10.1109/iros.2017.8206234","mag":"2567705466"},"language":"en","primary_location":{"id":"doi:10.1109/iros.2017.8206234","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2017.8206234","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100375332","display_name":"Xiao Li","orcid":"https://orcid.org/0000-0003-2565-9883"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiao Li","raw_affiliation_strings":["Boston University, Boston, MA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Boston University, Boston, MA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086654963","display_name":"Cristian-Ioan Vasile","orcid":"https://orcid.org/0000-0002-1132-1462"},"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":"Cristian-Ioan Vasile","raw_affiliation_strings":["Massachusetts Institute of Technology, Cambridge, MA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology, Cambridge, MA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086742095","display_name":"C\u0103lin Belta","orcid":"https://orcid.org/0000-0002-7141-2657"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Calin Belta","raw_affiliation_strings":["Boston University, Boston, MA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Boston University, Boston, MA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":14.2556,"has_fulltext":false,"cited_by_count":161,"citation_normalized_percentile":{"value":0.99799818,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"3834","last_page":"3839"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10142","display_name":"Formal Methods in Verification","score":0.9990000128746033,"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":0.9990000128746033,"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/T11010","display_name":"Logic, Reasoning, and Knowledge","score":0.9797999858856201,"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/T10126","display_name":"Logic, programming, and type systems","score":0.9754999876022339,"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/computer-science","display_name":"Computer science","score":0.7656474113464355},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7608209252357483},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.7164877653121948},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6804165840148926},{"id":"https://openalex.org/keywords/linear-temporal-logic","display_name":"Linear temporal logic","score":0.6341364979743958},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5850015878677368},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5819774270057678},{"id":"https://openalex.org/keywords/temporal-logic","display_name":"Temporal logic","score":0.5537989139556885},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.4809664785861969},{"id":"https://openalex.org/keywords/temporal-logic-of-actions","display_name":"Temporal logic of actions","score":0.4627312421798706},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.444105863571167},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4323161542415619},{"id":"https://openalex.org/keywords/expressive-power","display_name":"Expressive power","score":0.4312150478363037},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.41115105152130127},{"id":"https://openalex.org/keywords/interval-temporal-logic","display_name":"Interval temporal logic","score":0.39709973335266113},{"id":"https://openalex.org/keywords/description-logic","display_name":"Description logic","score":0.2705421447753906},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.21661177277565002}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7656474113464355},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7608209252357483},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.7164877653121948},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6804165840148926},{"id":"https://openalex.org/C4777664","wikidata":"https://www.wikidata.org/wiki/Q1536492","display_name":"Linear temporal logic","level":2,"score":0.6341364979743958},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5850015878677368},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5819774270057678},{"id":"https://openalex.org/C25016198","wikidata":"https://www.wikidata.org/wiki/Q781833","display_name":"Temporal logic","level":2,"score":0.5537989139556885},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.4809664785861969},{"id":"https://openalex.org/C11648818","wikidata":"https://www.wikidata.org/wiki/Q2403081","display_name":"Temporal logic of actions","level":4,"score":0.4627312421798706},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.444105863571167},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4323161542415619},{"id":"https://openalex.org/C195818886","wikidata":"https://www.wikidata.org/wiki/Q5421724","display_name":"Expressive power","level":2,"score":0.4312150478363037},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.41115105152130127},{"id":"https://openalex.org/C162670838","wikidata":"https://www.wikidata.org/wiki/Q6057295","display_name":"Interval temporal logic","level":3,"score":0.39709973335266113},{"id":"https://openalex.org/C102993220","wikidata":"https://www.wikidata.org/wiki/Q387196","display_name":"Description logic","level":2,"score":0.2705421447753906},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.21661177277565002},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/iros.2017.8206234","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2017.8206234","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},{"id":"pmh:oai:open.bu.edu:2144/29608","is_oa":false,"landing_page_url":"http://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcApp=PARTNER_APP&SrcAuth=LinksAMR&KeyUT=WOS:000426978203115&DestLinkType=FullRecord&DestApp=ALL_WOS&UsrCustomerID=6e74115fe3da270499c3d65c9b17d654","pdf_url":null,"source":{"id":"https://openalex.org/S4306402384","display_name":"OpenBU (Boston University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I111088046","host_organization_name":"Boston University","host_organization_lineage":["https://openalex.org/I111088046"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W91905023","https://openalex.org/W1512185023","https://openalex.org/W1533557569","https://openalex.org/W1700264732","https://openalex.org/W1792768639","https://openalex.org/W2012587148","https://openalex.org/W2078151802","https://openalex.org/W2342662072","https://openalex.org/W2462906003","https://openalex.org/W2524638160","https://openalex.org/W2529601334","https://openalex.org/W2951442171","https://openalex.org/W2963641140","https://openalex.org/W2963778636","https://openalex.org/W4205513846","https://openalex.org/W6704571135"],"related_works":["https://openalex.org/W946220898","https://openalex.org/W2143050727","https://openalex.org/W4232446061","https://openalex.org/W2124110813","https://openalex.org/W4387188591","https://openalex.org/W2092656858","https://openalex.org/W4285022830","https://openalex.org/W2561906579","https://openalex.org/W59129029","https://openalex.org/W2585210618"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,116],"(RL)":[2],"depends":[3],"critically":[4],"on":[5],"the":[6,14,58,69,107,123,127,136,142,149],"choice":[7],"of":[8,19,57,61,135],"reward":[9],"functions":[10],"used":[11],"to":[12,65],"capture":[13],"desired":[15],"behavior":[16],"and":[17,30,48,73,119],"constraints":[18],"a":[20,27,87,98,154,159],"robot.":[21,161],"Usually,":[22],"these":[23],"are":[24,144],"handcrafted":[25],"by":[26,158],"expert":[28],"designer":[29],"represent":[31],"heuristics":[32],"for":[33,106],"relatively":[34],"simple":[35],"tasks.":[36],"Real":[37],"world":[38],"applications":[39],"typically":[40],"involve":[41],"more":[42],"complex":[43,67],"tasks":[44,143],"with":[45],"rich":[46],"temporal":[47,62],"logical":[49],"structure.":[50],"In":[51],"this":[52],"paper":[53],"we":[54,147],"take":[55],"advantage":[56],"expressive":[59],"power":[60],"logic":[63],"(TL)":[64],"specify":[66],"rules":[68],"robot":[70],"should":[71],"follow,":[72],"incorporate":[74],"domain":[75],"knowledge":[76],"into":[77],"learning.":[78],"We":[79,90,110],"propose":[80,91],"Truncated":[81,92],"Linear":[82,93],"Temporal":[83,94],"Logic":[84,95],"(TLTL)":[85,96],"as":[86,97],"specification":[88,99],"language,":[89,100],"that":[101,115],"is":[102,117],"arguably":[103],"well":[104,141],"suited":[105],"robotics":[108],"applications,":[109],"show":[111],"in":[112,133,153],"simulated":[113],"trials":[114],"faster":[118],"policies":[120],"obtained":[121],"using":[122,130],"proposed":[124,150],"approach":[125,152],"outperform":[126],"ones":[128],"learned":[129,157],"heuristic":[131],"rewards":[132],"terms":[134],"robustness":[137],"degree,":[138],"i.e.,":[139],"how":[140],"satisfied.":[145],"Furthermore,":[146],"demonstrate":[148],"RL":[151],"toast-placing":[155],"task":[156],"Baxter":[160]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":16},{"year":2024,"cited_by_count":19},{"year":2023,"cited_by_count":28},{"year":2022,"cited_by_count":21},{"year":2021,"cited_by_count":29},{"year":2020,"cited_by_count":23},{"year":2019,"cited_by_count":13},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}