{"id":"https://openalex.org/W4312555784","doi":"https://doi.org/10.1109/ijcnn55064.2022.9892304","title":"Integrating Symbolic Planning and Reinforcement Learning for Following Temporal Logic Specifications","display_name":"Integrating Symbolic Planning and Reinforcement Learning for Following Temporal Logic Specifications","publication_year":2022,"publication_date":"2022-07-18","ids":{"openalex":"https://openalex.org/W4312555784","doi":"https://doi.org/10.1109/ijcnn55064.2022.9892304"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn55064.2022.9892304","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn55064.2022.9892304","pdf_url":null,"source":{"id":"https://openalex.org/S4363607707","display_name":"2022 International Joint Conference on Neural Networks (IJCNN)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"2022 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-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/A5101428767","display_name":"Duo Xu","orcid":"https://orcid.org/0000-0001-6195-3444"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Duo Xu","raw_affiliation_strings":["Georgia Institute of Technology,Department of Electrical and Computer Engineering,GA,USA,30332"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology,Department of Electrical and Computer Engineering,GA,USA,30332","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083854532","display_name":"Faramarz Fekri","orcid":"https://orcid.org/0000-0001-5008-8803"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Faramarz Fekri","raw_affiliation_strings":["Georgia Institute of Technology,Department of Electrical and Computer Engineering,GA,USA,30332"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology,Department of Electrical and Computer Engineering,GA,USA,30332","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101428767"],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":null,"apc_paid":null,"fwci":0.1041,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.3221462,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"01","last_page":"08"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9955999851226807,"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":0.9955999851226807,"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":0.9955999851226807,"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":0.9955000281333923,"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":0.7803874015808105},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.749987006187439},{"id":"https://openalex.org/keywords/inductive-logic-programming","display_name":"Inductive logic programming","score":0.7071535587310791},{"id":"https://openalex.org/keywords/linear-temporal-logic","display_name":"Linear temporal logic","score":0.6918215751647949},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6622288227081299},{"id":"https://openalex.org/keywords/automaton","display_name":"Automaton","score":0.581307053565979},{"id":"https://openalex.org/keywords/transition-system","display_name":"Transition system","score":0.5650903582572937},{"id":"https://openalex.org/keywords/temporal-logic","display_name":"Temporal logic","score":0.5191720724105835},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5160017013549805},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4999814033508301},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.48431578278541565},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.47569382190704346},{"id":"https://openalex.org/keywords/logic-programming","display_name":"Logic programming","score":0.47529709339141846},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.46275708079338074},{"id":"https://openalex.org/keywords/model-checking","display_name":"Model checking","score":0.4191170930862427},{"id":"https://openalex.org/keywords/finite-state-machine","display_name":"Finite-state machine","score":0.414512038230896},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.3447434902191162}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7803874015808105},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.749987006187439},{"id":"https://openalex.org/C2779382394","wikidata":"https://www.wikidata.org/wiki/Q1464197","display_name":"Inductive logic programming","level":2,"score":0.7071535587310791},{"id":"https://openalex.org/C4777664","wikidata":"https://www.wikidata.org/wiki/Q1536492","display_name":"Linear temporal logic","level":2,"score":0.6918215751647949},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6622288227081299},{"id":"https://openalex.org/C112505250","wikidata":"https://www.wikidata.org/wiki/Q787116","display_name":"Automaton","level":2,"score":0.581307053565979},{"id":"https://openalex.org/C2779167558","wikidata":"https://www.wikidata.org/wiki/Q176468","display_name":"Transition system","level":2,"score":0.5650903582572937},{"id":"https://openalex.org/C25016198","wikidata":"https://www.wikidata.org/wiki/Q781833","display_name":"Temporal logic","level":2,"score":0.5191720724105835},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5160017013549805},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4999814033508301},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.48431578278541565},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.47569382190704346},{"id":"https://openalex.org/C128838566","wikidata":"https://www.wikidata.org/wiki/Q275603","display_name":"Logic programming","level":2,"score":0.47529709339141846},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.46275708079338074},{"id":"https://openalex.org/C110251889","wikidata":"https://www.wikidata.org/wiki/Q1569697","display_name":"Model checking","level":2,"score":0.4191170930862427},{"id":"https://openalex.org/C167822520","wikidata":"https://www.wikidata.org/wiki/Q176452","display_name":"Finite-state machine","level":2,"score":0.414512038230896},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3447434902191162},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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":1,"locations":[{"id":"doi:10.1109/ijcnn55064.2022.9892304","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn55064.2022.9892304","pdf_url":null,"source":{"id":"https://openalex.org/S4363607707","display_name":"2022 International Joint Conference on Neural Networks (IJCNN)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"2022 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities","score":0.5899999737739563}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W1563854815","https://openalex.org/W1585529040","https://openalex.org/W2073548775","https://openalex.org/W2082965709","https://openalex.org/W2119709400","https://openalex.org/W2145339207","https://openalex.org/W2148446974","https://openalex.org/W2149390907","https://openalex.org/W2605514557","https://openalex.org/W2616430965","https://openalex.org/W2784743256","https://openalex.org/W2804948070","https://openalex.org/W2823112946","https://openalex.org/W2900860440","https://openalex.org/W2962924847","https://openalex.org/W2963190533","https://openalex.org/W2964890016","https://openalex.org/W2964915587","https://openalex.org/W2966183138","https://openalex.org/W2966537673","https://openalex.org/W2976866784","https://openalex.org/W2990118443","https://openalex.org/W3032689177","https://openalex.org/W3034655091","https://openalex.org/W3036143433","https://openalex.org/W3037476194","https://openalex.org/W3080398910","https://openalex.org/W3080598349","https://openalex.org/W3080730120","https://openalex.org/W3092156990","https://openalex.org/W3131897549","https://openalex.org/W3133109218","https://openalex.org/W3149428720","https://openalex.org/W3171517119","https://openalex.org/W3175128928","https://openalex.org/W3203321737","https://openalex.org/W3207251292","https://openalex.org/W4205130889","https://openalex.org/W4287758155","https://openalex.org/W4297669644","https://openalex.org/W4299861076","https://openalex.org/W6669133860","https://openalex.org/W6730038592","https://openalex.org/W6737937804","https://openalex.org/W6738654461","https://openalex.org/W6752298494","https://openalex.org/W6758262585","https://openalex.org/W6766842884","https://openalex.org/W6768323397","https://openalex.org/W6802417772"],"related_works":["https://openalex.org/W2124110813","https://openalex.org/W3021103820","https://openalex.org/W2521108391","https://openalex.org/W1532447905","https://openalex.org/W2763487042","https://openalex.org/W2468920154","https://openalex.org/W2546438959","https://openalex.org/W1581671536","https://openalex.org/W2158345050","https://openalex.org/W4312555784"],"abstract_inverted_index":{"Teaching":[0],"a":[1,14,25,70,78,143,149],"deep":[2],"reinforcement":[3,72],"learning":[4,73],"(RL)":[5],"agent":[6,93,136],"to":[7,41,84,110],"follow":[8],"instructions":[9],"in":[10,35,44,76,163],"multi-task":[11],"environments":[12,37,162],"is":[13,50,82,103],"challenging":[15],"problem.":[16],"We":[17,155],"consider":[18],"that":[19,89],"user":[20,43,49],"defines":[21],"every":[22],"task":[23],"by":[24,59,105],"linear":[26],"temporal":[27],"logic":[28,107,112],"(LTL)":[29],"formula.":[30],"However,":[31],"some":[32],"causal":[33,139],"dependencies":[34,140],"complex":[36,145],"may":[38],"be":[39],"unknown":[40],"the":[42,53,57,62,92,99,120,123,128,132,135,157],"advance.":[45],"Hence,":[46],"when":[47],"human":[48],"specifying":[51],"instructions,":[52],"robot":[54],"cannot":[55],"solve":[56,95],"tasks":[58],"simply":[60],"following":[61],"given":[63],"instructions.":[64],"In":[65],"this":[66],"work,":[67],"we":[68],"propose":[69],"hierarchical":[71],"(HRL)":[74],"framework":[75,159],"which":[77],"symbolic":[79,100,124],"transition":[80,101,125],"model":[81,102,126],"learned":[83,104],"efficiently":[85,94],"produce":[86],"high-level":[87],"plans":[88],"can":[90,137],"guide":[91],"different":[96],"tasks.":[97],"Specifically,":[98],"inductive":[106],"programming":[108],"(ILP)":[109],"capture":[111],"rules":[113],"of":[114,122,151],"state":[115],"transitions.":[116],"By":[117],"planning":[118],"over":[119,171],"product":[121],"and":[127,141,166],"automaton":[129],"derived":[130],"from":[131],"LTL":[133],"formula,":[134],"resolve":[138],"break":[142],"causally":[144],"problem":[146],"down":[147],"into":[148],"sequence":[150],"simpler":[152],"low-level":[153],"sub-tasks.":[154],"evaluate":[156],"proposed":[158],"on":[160],"three":[161],"both":[164],"discrete":[165],"continuous":[167],"domains,":[168],"showing":[169],"advantages":[170],"previous":[172],"representative":[173],"methods.":[174]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}