{"id":"https://openalex.org/W3132564992","doi":"https://doi.org/10.1109/iros45743.2020.9341325","title":"Encoding formulas as deep networks: Reinforcement learning for zero-shot execution of LTL formulas","display_name":"Encoding formulas as deep networks: Reinforcement learning for zero-shot execution of LTL formulas","publication_year":2020,"publication_date":"2020-10-24","ids":{"openalex":"https://openalex.org/W3132564992","doi":"https://doi.org/10.1109/iros45743.2020.9341325","mag":"3132564992"},"language":"en","primary_location":{"id":"doi:10.1109/iros45743.2020.9341325","doi":"https://doi.org/10.1109/iros45743.2020.9341325","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros45743.2020.9341325","pdf_url":null,"source":{"id":"https://openalex.org/S4393918188","display_name":"IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","issn_l":"2153-0858","issn":["2153-0858"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2006.01110","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5087296750","display_name":"Yen\u2010Ling Kuo","orcid":"https://orcid.org/0000-0002-6433-6713","observed_orcids":["https://orcid.org/0000-0002-6433-6713"]},"institutions":[{"id":"https://openalex.org/I4405258931","display_name":"MIT Computer Science and Artificial Intelligence Laboratory","ror":"https://ror.org/01e85r662","country_code":"US","type":"facility","lineage":["https://openalex.org/I4405258931","https://openalex.org/I63966007"]},{"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":"Yen-Ling Kuo","raw_affiliation_strings":["CSAIL and CBMM, MIT"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CSAIL and CBMM, MIT","institution_ids":["https://openalex.org/I4405258931","https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002527110","display_name":"Boris Katz","orcid":"https://orcid.org/0000-0002-3871-5824","observed_orcids":["https://orcid.org/0000-0002-3871-5824"]},"institutions":[{"id":"https://openalex.org/I4405258931","display_name":"MIT Computer Science and Artificial Intelligence Laboratory","ror":"https://ror.org/01e85r662","country_code":"US","type":"facility","lineage":["https://openalex.org/I4405258931","https://openalex.org/I63966007"]},{"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":"Boris Katz","raw_affiliation_strings":["CSAIL and CBMM, MIT"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CSAIL and CBMM, MIT","institution_ids":["https://openalex.org/I4405258931","https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018507577","display_name":"Andrei Barbu","orcid":"https://orcid.org/0000-0001-7626-9266","observed_orcids":["https://orcid.org/0000-0001-7626-9266"]},"institutions":[{"id":"https://openalex.org/I4405258931","display_name":"MIT Computer Science and Artificial Intelligence Laboratory","ror":"https://ror.org/01e85r662","country_code":"US","type":"facility","lineage":["https://openalex.org/I4405258931","https://openalex.org/I63966007"]},{"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":"Andrei Barbu","raw_affiliation_strings":["CSAIL and CBMM, MIT"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CSAIL and CBMM, MIT","institution_ids":["https://openalex.org/I4405258931","https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.0492,"has_fulltext":true,"cited_by_count":21,"citation_normalized_percentile":{"value":0.81829243,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"5604","last_page":"5610"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.8432999849319458,"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":0.8432999849319458,"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/T11010","display_name":"Logic, Reasoning, and Knowledge","score":0.05249999836087227,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.026499999687075615,"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/linear-temporal-logic","display_name":"linear temporal logic","score":0.9269999861717224},{"id":"https://openalex.org/keywords/zero-shot-generalization","display_name":"zero-shot generalization","score":0.9459999799728394},{"id":"https://openalex.org/keywords/reinforcement-learning-agents","display_name":"reinforcement learning agents","score":0.8190000057220459},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"multi-task learning","score":0.9359999895095825},{"id":"https://openalex.org/keywords/symbolic-reasoning","display_name":"symbolic reasoning","score":0.3100000023841858}],"concepts":[{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.8330250382423401},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.679999589920044},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6773808598518372},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.6587237119674683},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6265433430671692},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6046888828277588},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.5645318031311035},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5601692199707031},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.5351494550704956},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.5144996643066406},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.504372239112854},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4095609188079834},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3453846573829651},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2143048346042633},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08841422200202942},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"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/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},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/iros45743.2020.9341325","doi":"https://doi.org/10.1109/iros45743.2020.9341325","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros45743.2020.9341325","pdf_url":null,"source":{"id":"https://openalex.org/S4393918188","display_name":"IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","issn_l":"2153-0858","issn":["2153-0858"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2006.01110","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2006.01110","pdf_url":"https://arxiv.org/pdf/2006.01110","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:dspace.mit.edu:1721.1/141355","doi":null,"is_oa":true,"landing_page_url":"https://hdl.handle.net/1721.1/141355","pdf_url":null,"source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Technical Report"},{"id":"doi:10.48550/arxiv.2006.01110","doi":"https://doi.org/10.48550/arxiv.2006.01110","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2006.01110","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2006.01110","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2006.01110","pdf_url":"https://arxiv.org/pdf/2006.01110","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320315934","display_name":"Toyota Research Institute","ror":"https://ror.org/04fpkc108"},{"id":"https://openalex.org/F4320322923","display_name":"Siemens","ror":"https://ror.org/059mq0909"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3132564992.pdf","grobid_xml":"https://content.openalex.org/works/W3132564992.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W1700264732","https://openalex.org/W2023808162","https://openalex.org/W2075335084","https://openalex.org/W2078151802","https://openalex.org/W2155027007","https://openalex.org/W2260756217","https://openalex.org/W2522043470","https://openalex.org/W2553882142","https://openalex.org/W2567705466","https://openalex.org/W2775536965","https://openalex.org/W2808386811","https://openalex.org/W2963190533","https://openalex.org/W2963575966","https://openalex.org/W2963604565","https://openalex.org/W2963778636","https://openalex.org/W2964199361","https://openalex.org/W2966183138","https://openalex.org/W2966537673","https://openalex.org/W3006059152","https://openalex.org/W6773526284"],"related_works":["https://openalex.org/W3186650888","https://openalex.org/W7129350594","https://openalex.org/W3131897549","https://openalex.org/W7128621211","https://openalex.org/W4416552878","https://openalex.org/W3034655091","https://openalex.org/W2808386811","https://openalex.org/W7128376725","https://openalex.org/W4403322836","https://openalex.org/W7166897594"],"abstract_inverted_index":{"We":[0,81],"demonstrate":[1,82,134],"a":[2,8,44,65,89,95,103,109],"reinforcement":[3],"learning":[4,49],"agent":[5,93,107],"which":[6,165,182],"uses":[7],"compositional":[9],"recurrent":[10],"neural":[11,194],"network":[12,35,75],"that":[13,99,113,131,150],"takes":[14],"as":[15,160,162],"input":[16,25],"an":[17,185],"LTL":[18,26,180],"formula":[19,126],"and":[20,62,153],"determines":[21],"satisfying":[22],"actions.":[23],"The":[24,71,171],"formulas":[27,139],"have":[28],"never":[29],"been":[30],"seen":[31],"before,":[32],"yet":[33],"the":[34,74,92,106,116,144,163],"performs":[36],"zero-shot":[37,197],"generalization":[38,176,198],"to":[39,64,79,115,123,136,179,199],"satisfy":[40],"them.":[41],"This":[42,141],"is":[43,100],"novel":[45],"form":[46,143],"of":[47,60,68,73,97,111,130,146],"multi-task":[48],"for":[50,174,196],"RL":[51],"agents":[52,54,149,164],"where":[53],"learn":[55,122],"from":[56],"one":[57,125],"diverse":[58,69],"set":[59,67],"tasks":[61],"generalize":[63],"new":[66,147],"tasks.":[70],"formulation":[72],"enables":[76],"this":[77,83,175],"capacity":[78],"generalize.":[80],"ability":[84],"in":[85,193],"two":[86],"domains.":[87],"In":[88,102],"symbolic":[90],"domain,":[91],"finds":[94,108],"sequence":[96,110],"letters":[98],"accepted.":[101],"Minecraft-like":[104],"environment,":[105],"actions":[112],"conform":[114],"formula.":[117],"While":[118],"prior":[119],"work":[120],"could":[121,142],"execute":[124,154],"reliably":[127],"given":[128],"examples":[129],"formula,":[132],"we":[133],"how":[135],"encode":[137],"all":[138],"reliably.":[140],"basis":[145],"multitask":[148],"discover":[151],"sub-tasks":[152],"them":[155],"without":[156],"any":[157],"additional":[158],"training,":[159],"well":[161],"follow":[166],"more":[167],"complex":[168],"linguistic":[169],"commands.":[170],"structures":[172,190],"required":[173,192],"are":[177,191],"specific":[178],"formulas,":[181],"opens":[183],"up":[184],"interesting":[186],"theoretical":[187],"question:":[188],"what":[189],"networks":[195],"different":[200],"logics?":[201]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":2}],"updated_date":"2026-10-26T11:51:55.731654","created_date":"2021-03-01T00:00:00"}