{"id":"https://openalex.org/W4285599953","doi":"https://doi.org/10.24963/ijcai.2022/742","title":"Detect, Understand, Act: A Neuro-Symbolic Hierarchical Reinforcement Learning Framework (Extended Abstract)","display_name":"Detect, Understand, Act: A Neuro-Symbolic Hierarchical Reinforcement Learning Framework (Extended Abstract)","publication_year":2022,"publication_date":"2022-07-01","ids":{"openalex":"https://openalex.org/W4285599953","doi":"https://doi.org/10.24963/ijcai.2022/742"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2022/742","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2022/742","pdf_url":"https://www.ijcai.org/proceedings/2022/0742.pdf","source":{"id":"https://openalex.org/S4363608755","display_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","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":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://www.ijcai.org/proceedings/2022/0742.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5029949736","display_name":"Ludovico Mitchener","orcid":"https://orcid.org/0000-0002-5968-9776"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ludovico Mitchener","raw_affiliation_strings":["Imperial College London"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Imperial College London","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030185505","display_name":"David Tuckey","orcid":null},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"David Tuckey","raw_affiliation_strings":["Imperial College London"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Imperial College London","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012483737","display_name":"Matthew Crosby","orcid":"https://orcid.org/0000-0001-7606-7533"},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]},{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Matthew Crosby","raw_affiliation_strings":["DeepMind","Imperial College London"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepMind","institution_ids":["https://openalex.org/I4210090411"]},{"raw_affiliation_string":"Imperial College London","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046462940","display_name":"Alessandra Russo","orcid":"https://orcid.org/0000-0002-3318-8711"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Alessandra Russo","raw_affiliation_strings":["Imperial College London"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Imperial College London","institution_ids":["https://openalex.org/I47508984"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1038,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.2651471,"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":"5314","last_page":"5318"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994000196456909,"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":0.9994000196456909,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.9902999997138977,"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":0.9842000007629395,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.86785888671875},{"id":"https://openalex.org/keywords/testbed","display_name":"Testbed","score":0.8495925664901733},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7283146381378174},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.7151955962181091},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6441298127174377},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5377758741378784},{"id":"https://openalex.org/keywords/inductive-logic-programming","display_name":"Inductive logic programming","score":0.4219767451286316},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.34308314323425293},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3205080032348633},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.22101670503616333}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.86785888671875},{"id":"https://openalex.org/C31395832","wikidata":"https://www.wikidata.org/wiki/Q1318674","display_name":"Testbed","level":2,"score":0.8495925664901733},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7283146381378174},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.7151955962181091},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6441298127174377},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5377758741378784},{"id":"https://openalex.org/C2779382394","wikidata":"https://www.wikidata.org/wiki/Q1464197","display_name":"Inductive logic programming","level":2,"score":0.4219767451286316},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.34308314323425293},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3205080032348633},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.22101670503616333},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.24963/ijcai.2022/742","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2022/742","pdf_url":"https://www.ijcai.org/proceedings/2022/0742.pdf","source":{"id":"https://openalex.org/S4363608755","display_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","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":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},{"id":"pmh:oai:spiral.imperial.ac.uk:10044/1/101611","is_oa":false,"landing_page_url":"http://hdl.handle.net/10044/1/101611","pdf_url":null,"source":{"id":"https://openalex.org/S4306401396","display_name":"Spiral (Imperial College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I47508984","host_organization_name":"Imperial College London","host_organization_lineage":["https://openalex.org/I47508984"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"THE 31ST INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE","raw_type":"Conference Paper"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2022/742","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2022/742","pdf_url":"https://www.ijcai.org/proceedings/2022/0742.pdf","source":{"id":"https://openalex.org/S4363608755","display_name":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","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":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.7200000286102295,"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4285599953.pdf","grobid_xml":"https://content.openalex.org/works/W4285599953.grobid-xml"},"referenced_works_count":17,"referenced_works":["https://openalex.org/W2109910161","https://openalex.org/W2121863487","https://openalex.org/W2521274174","https://openalex.org/W2735526831","https://openalex.org/W2736601468","https://openalex.org/W2774183894","https://openalex.org/W2883899184","https://openalex.org/W2930003055","https://openalex.org/W2996037775","https://openalex.org/W3005742798","https://openalex.org/W3092731680","https://openalex.org/W3116950227","https://openalex.org/W3118210634","https://openalex.org/W3139531864","https://openalex.org/W4287660741","https://openalex.org/W4288351558","https://openalex.org/W4298084898"],"related_works":["https://openalex.org/W2883256816","https://openalex.org/W2171408034","https://openalex.org/W3003320923","https://openalex.org/W2106140982","https://openalex.org/W2152313554","https://openalex.org/W2064303750","https://openalex.org/W4285042611","https://openalex.org/W1509300825","https://openalex.org/W3092582874","https://openalex.org/W2338718585"],"abstract_inverted_index":{"We":[0,66],"introduce":[1],"Detect,":[2],"Understand,":[3],"Act":[4,26],"(DUA),":[5],"a":[6,17,29,47,76,84,93,98],"neuro-symbolic":[7],"reinforcement":[8,39],"learning":[9,40,56],"framework.":[10],"The":[11,25,43],"Detect":[12],"component":[13,27,45],"is":[14],"composed":[15],"of":[16,31,78,86,109,124,142],"traditional":[18],"computer":[19,125],"vision":[20],"object":[21],"detector":[22],"and":[23,128,135],"tracker.":[24],"houses":[28],"set":[30,50,77,85],"options,":[32],"high-level":[33],"actions":[34],"enacted":[35],"by":[36],"pre-trained":[37,87],"deep":[38],"(DRL)":[41],"policies.":[42],"Understand":[44],"provides":[46],"novel":[48],"answer":[49],"programming":[51,64],"(ASP)":[52],"paradigm":[53],"for":[54,139],"effectively":[55],"symbolic":[57],"meta-policies":[58],"over":[59],"options":[60],"using":[61],"inductive":[62],"logic":[63],"(ILP).":[65],"evaluate":[67],"our":[68],"framework":[69],"on":[70,107],"the":[71,105,110,115,119,137],"Animal-AI":[72],"(AAI)":[73],"competition":[74],"testbed,":[75],"physical":[79],"cognitive":[80],"reasoning":[81],"problems.":[82],"Given":[83],"DRL":[88,129,146],"policies,":[89],"DUA":[90,117],"requires":[91],"only":[92],"few":[94],"examples":[95],"to":[96,103,131],"learn":[97],"meta-policy":[99],"that":[100],"allows":[101],"it":[102],"improve":[104],"state-of-the-art":[106],"multiple":[108],"most":[111],"challenging":[112],"categories":[113],"from":[114],"testbed.":[116],"constitutes":[118],"first":[120],"holistic":[121],"hybrid":[122],"integration":[123],"vision,":[126],"ILP":[127,143],"applied":[130],"an":[132],"AAI-like":[133],"environment":[134],"sets":[136],"foundations":[138],"further":[140],"use":[141],"in":[144],"complex":[145],"challenges.":[147]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}