{"id":"https://openalex.org/W4206520121","doi":"https://doi.org/10.1109/lra.2021.3139380","title":"Learning Policies by Learning Rules","display_name":"Learning Policies by Learning Rules","publication_year":2021,"publication_date":"2021-12-31","ids":{"openalex":"https://openalex.org/W4206520121","doi":"https://doi.org/10.1109/lra.2021.3139380"},"language":"en","primary_location":{"id":"doi:10.1109/lra.2021.3139380","is_oa":true,"landing_page_url":"https://doi.org/10.1109/lra.2021.3139380","pdf_url":"https://ieeexplore.ieee.org/ielx7/7083369/9647862/09667222.pdf","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":true,"oa_status":"hybrid","oa_url":"https://ieeexplore.ieee.org/ielx7/7083369/9647862/09667222.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5006883016","display_name":"Brandon Araki","orcid":"https://orcid.org/0000-0002-3094-1587"},"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":"Brandon Araki","raw_affiliation_strings":["CSAIL, Massachusetts Institute of Technology, Cambridge, MA, USA"],"raw_orcid":"https://orcid.org/0000-0002-3094-1587","affiliations":[{"raw_affiliation_string":"CSAIL, Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053151494","display_name":"Jeana Choi","orcid":null},"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":"Jeana Choi","raw_affiliation_strings":["CSAIL, Massachusetts Institute of Technology, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CSAIL, Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067958726","display_name":"Lillian Chin","orcid":"https://orcid.org/0000-0003-4083-5275"},"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":"Lillian Chin","raw_affiliation_strings":["CSAIL, Massachusetts Institute of Technology, Cambridge, MA, USA"],"raw_orcid":"https://orcid.org/0000-0003-4083-5275","affiliations":[{"raw_affiliation_string":"CSAIL, Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100375332","display_name":"Xiao Li","orcid":"https://orcid.org/0000-0003-2565-9883"},"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":"Xiao Li","raw_affiliation_strings":["CSAIL, Massachusetts Institute of Technology, Cambridge, MA, USA"],"raw_orcid":"https://orcid.org/0000-0003-2565-9883","affiliations":[{"raw_affiliation_string":"CSAIL, Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066830185","display_name":"Daniela Rus","orcid":"https://orcid.org/0000-0001-5473-3566"},"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":"Daniela Rus","raw_affiliation_strings":["CSAIL, Massachusetts Institute of Technology, Cambridge, MA, USA"],"raw_orcid":"https://orcid.org/0000-0001-5473-3566","affiliations":[{"raw_affiliation_string":"CSAIL, Massachusetts Institute of Technology, Cambridge, MA, USA","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":0.1365,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.57590883,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"7","issue":"2","first_page":"1284","last_page":"1291"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.9987999796867371,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9987999796867371,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9976000189781189,"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":0.9915000200271606,"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/inference","display_name":"Inference","score":0.7203680872917175},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.695972204208374},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.634374737739563},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6243908405303955},{"id":"https://openalex.org/keywords/planner","display_name":"Planner","score":0.6075080633163452},{"id":"https://openalex.org/keywords/bayesian-inference","display_name":"Bayesian inference","score":0.5581480264663696},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5223206877708435},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.4801156520843506},{"id":"https://openalex.org/keywords/approximate-inference","display_name":"Approximate inference","score":0.4366748332977295},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07630252838134766}],"concepts":[{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7203680872917175},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.695972204208374},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.634374737739563},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6243908405303955},{"id":"https://openalex.org/C2776999362","wikidata":"https://www.wikidata.org/wiki/Q2349274","display_name":"Planner","level":2,"score":0.6075080633163452},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.5581480264663696},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5223206877708435},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.4801156520843506},{"id":"https://openalex.org/C2777472644","wikidata":"https://www.wikidata.org/wiki/Q16968992","display_name":"Approximate inference","level":3,"score":0.4366748332977295},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07630252838134766},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/lra.2021.3139380","is_oa":true,"landing_page_url":"https://doi.org/10.1109/lra.2021.3139380","pdf_url":"https://ieeexplore.ieee.org/ielx7/7083369/9647862/09667222.pdf","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"},{"id":"pmh:oai:dspace.mit.edu:1721.1/144055","is_oa":true,"landing_page_url":"https://hdl.handle.net/1721.1/144055","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,"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":"IEEE","raw_type":"Article"}],"best_oa_location":{"id":"doi:10.1109/lra.2021.3139380","is_oa":true,"landing_page_url":"https://doi.org/10.1109/lra.2021.3139380","pdf_url":"https://ieeexplore.ieee.org/ielx7/7083369/9647862/09667222.pdf","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4477799662","display_name":null,"funder_award_id":"1830901","funder_id":"https://openalex.org/F4320335353","funder_display_name":"National Science Foundation of Sri Lanka"}],"funders":[{"id":"https://openalex.org/F4320308782","display_name":"Hertz Foundation","ror":"https://ror.org/01ycgxf29"},{"id":"https://openalex.org/F4320315934","display_name":"Toyota Research Institute","ror":null},{"id":"https://openalex.org/F4320316620","display_name":"Amazon Catalyst","ror":"https://ror.org/04mv4n011"},{"id":"https://openalex.org/F4320335353","display_name":"National Science Foundation of Sri Lanka","ror":"https://ror.org/010xaa060"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1498432697","https://openalex.org/W1999874108","https://openalex.org/W2063471043","https://openalex.org/W2522043470","https://openalex.org/W2787066086","https://openalex.org/W2787908307","https://openalex.org/W2897613819","https://openalex.org/W2965569070","https://openalex.org/W2966183138","https://openalex.org/W2998509800","https://openalex.org/W3038945966","https://openalex.org/W3089728370","https://openalex.org/W3098843277","https://openalex.org/W3175871729","https://openalex.org/W4288617013","https://openalex.org/W6754526278","https://openalex.org/W6755447188","https://openalex.org/W6759517920","https://openalex.org/W6767015862","https://openalex.org/W6774932648","https://openalex.org/W6790681260","https://openalex.org/W7036529589"],"related_works":["https://openalex.org/W2020176575","https://openalex.org/W2372267530","https://openalex.org/W2969189870","https://openalex.org/W3015855446","https://openalex.org/W2965643117","https://openalex.org/W4226287370","https://openalex.org/W4303857162","https://openalex.org/W2114556850","https://openalex.org/W2159992248","https://openalex.org/W2215785064"],"abstract_inverted_index":{"Efficiently":[0],"learning":[1,23,32,142],"interpretable":[2,52],"policies":[3,134],"for":[4,115],"complex":[5,57,181],"tasks":[6,162],"from":[7,65,101,144],"demonstrations":[8,30],"is":[9,38,123],"a":[10,21,85,108,116,128,155,177,180],"challenging":[11],"problem.":[12],"We":[13,138,167],"present":[14],"Hierarchical":[15],"Inference":[16],"with":[17],"Logical":[18],"Options":[19],"(HILO),":[20],"novel":[22],"algorithm":[24],"that":[25,35,140],"learns":[26,69],"to":[27,103,110,126],"imitate":[28],"expert":[29,37,136],"by":[31,71,83,106,141,175],"the":[33,36,99,172],"rules":[34,41,64,70,143],"following.":[39],"The":[40,95],"are":[42,51],"represented":[43],"as":[44,78],"linear":[45],"temporal":[46],"logic":[47],"(LTL)":[48],"formulas,":[49,90],"which":[50,62],"and":[53,75,92,133,147,158],"capable":[54],"of":[55],"encoding":[56],"behaviors.":[58],"Unlike":[59],"previous":[60,152],"works,":[61],"learn":[63],"high-level":[66],"propositions,":[67,91],"HILO":[68,150,170],"taking":[72],"both":[73,145],"propositions":[74,146],"low-level":[76,93,104,148],"trajectories":[77],"input.":[79],"It":[80],"does":[81],"this":[82],"defining":[84],"Bayesian":[86,96],"model":[87,97],"over":[88,131],"LTL":[89,118],"trajectories.":[94],"bridges":[98],"gap":[100],"formula":[102],"trajectory":[105],"using":[107],"planner":[109],"find":[111,127],"an":[112],"optimal":[113],"policy":[114],"given":[117,135],"formula.":[119],"Stochastic":[120],"variational":[121],"inference":[122],"then":[124],"used":[125],"posterior":[129],"distribution":[130],"formulas":[132],"demonstrations.":[137],"show":[139],"states,":[149],"outperforms":[151],"work":[153],"on":[154,159],"rule-learning":[156],"task":[157],"four":[160],"planning":[161],"while":[163],"needing":[164],"less":[165],"data.":[166],"also":[168],"validate":[169],"in":[171],"real":[173],"world":[174],"teaching":[176],"robotic":[178],"arm":[179],"packing":[182],"task.":[183]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-05-19T21:40:30.786675","created_date":"2025-10-10T00:00:00"}