{"id":"https://openalex.org/W2948380112","doi":"https://doi.org/10.24963/ijcai.2019/880","title":"A Survey of Reinforcement Learning Informed by Natural Language","display_name":"A Survey of Reinforcement Learning Informed by Natural Language","publication_year":2019,"publication_date":"2019-07-28","ids":{"openalex":"https://openalex.org/W2948380112","doi":"https://doi.org/10.24963/ijcai.2019/880","mag":"2948380112"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2019/880","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/880","pdf_url":"https://www.ijcai.org/proceedings/2019/0880.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2019/0880.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5020311328","display_name":"Jelena Luketina","orcid":null},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Jelena Luketina","raw_affiliation_strings":["University of Oxford"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oxford","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013399434","display_name":"Nantas Nardelli","orcid":"https://orcid.org/0000-0001-8491-8166"},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]},{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB","IL"],"is_corresponding":false,"raw_author_name":"Nantas Nardelli","raw_affiliation_strings":["Facebook AI Research","University of Oxford"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook AI Research","institution_ids":["https://openalex.org/I2252078561"]},{"raw_affiliation_string":"University of Oxford","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016496356","display_name":"Gregory Farquhar","orcid":null},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]},{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB","IL"],"is_corresponding":false,"raw_author_name":"Gregory Farquhar","raw_affiliation_strings":["Facebook AI Research","University of Oxford"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook AI Research","institution_ids":["https://openalex.org/I2252078561"]},{"raw_affiliation_string":"University of Oxford","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059094093","display_name":"Jakob Foerster","orcid":"https://orcid.org/0000-0001-9688-2498"},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Jakob Foerster","raw_affiliation_strings":["Facebook AI Research","Facebook AI Research#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook AI Research","institution_ids":["https://openalex.org/I2252078561"]},{"raw_affiliation_string":"Facebook AI Research#TAB#","institution_ids":["https://openalex.org/I2252078561"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070829652","display_name":"Jacob Andreas","orcid":"https://orcid.org/0000-0002-3141-5845"},"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":"Jacob Andreas","raw_affiliation_strings":["Massachusetts Institute of Technology","Massachusetts Institute Of Technology#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology","institution_ids":["https://openalex.org/I63966007"]},{"raw_affiliation_string":"Massachusetts Institute Of Technology#TAB#","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023508792","display_name":"Edward Grefenstette","orcid":"https://orcid.org/0000-0003-1164-8809"},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]},{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]}],"countries":["GB","IL"],"is_corresponding":false,"raw_author_name":"Edward Grefenstette","raw_affiliation_strings":["Facebook AI Research","University College London"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook AI Research","institution_ids":["https://openalex.org/I2252078561"]},{"raw_affiliation_string":"University College London","institution_ids":["https://openalex.org/I45129253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056879203","display_name":"Shimon Whiteson","orcid":null},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Shimon Whiteson","raw_affiliation_strings":["University of Oxford"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oxford","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079315903","display_name":"Tim Rockt\u00e4schel","orcid":null},"institutions":[{"id":"https://openalex.org/I2252078561","display_name":"Meta (Israel)","ror":"https://ror.org/02388em19","country_code":"IL","type":"company","lineage":["https://openalex.org/I2252078561","https://openalex.org/I4210114444"]},{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB","IL"],"is_corresponding":false,"raw_author_name":"Tim Rockt\u00e4schel","raw_affiliation_strings":["Facebook AI Research","University College London"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Facebook AI Research","institution_ids":["https://openalex.org/I2252078561"]},{"raw_affiliation_string":"University College London","institution_ids":["https://openalex.org/I45129253"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5020311328"],"corresponding_institution_ids":["https://openalex.org/I40120149"],"apc_list":null,"apc_paid":null,"fwci":9.4367,"has_fulltext":false,"cited_by_count":73,"citation_normalized_percentile":{"value":0.98297357,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"6309","last_page":"6317"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998000264167786,"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/T10028","display_name":"Topic Modeling","score":0.9998000264167786,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9993000030517578,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9972000122070312,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.8055733442306519},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7852528095245361},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.7120732069015503},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5964136123657227},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5630431771278381},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5312948822975159},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.49729517102241516},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.4947776198387146},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.47928446531295776},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4616258442401886},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.45740559697151184},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.4105575680732727},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07194086909294128}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8055733442306519},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7852528095245361},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.7120732069015503},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5964136123657227},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5630431771278381},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5312948822975159},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.49729517102241516},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4947776198387146},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.47928446531295776},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4616258442401886},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.45740559697151184},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.4105575680732727},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07194086909294128},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","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}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.24963/ijcai.2019/880","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/880","pdf_url":"https://www.ijcai.org/proceedings/2019/0880.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1906.03926","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1906.03926","pdf_url":"https://arxiv.org/pdf/1906.03926","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"mag:2948380112","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1906.03926.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"arXiv (Cornell University)","raw_type":null},{"id":"pmh:oai:eprints.ucl.ac.uk.OAI2:10074415","is_oa":false,"landing_page_url":"https://discovery.ucl.ac.uk/id/eprint/10074415/","pdf_url":null,"source":{"id":"https://openalex.org/S4306400024","display_name":"UCL Discovery (University College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I45129253","host_organization_name":"University College London","host_organization_lineage":["https://openalex.org/I45129253"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"     In: Eiter, Thomas and Kraus, Sarit, (eds.) Proceedings of the 28th International Joint Conference on Artificial Intelligence (IJCAI-19).  (pp. pp. 6309-6317).  AAAI Press (Association for the Advancement of Artificial Intelligence): Palo Alto, CA, USA. (2019)     ","raw_type":"Proceedings paper"},{"id":"pmh:oai:ora.ox.ac.uk:uuid:f484e032-a09f-49bb-8e72-f54dcc9bb863","is_oa":false,"landing_page_url":"https://ora.ox.ac.uk/objects/uuid:f484e032-a09f-49bb-8e72-f54dcc9bb863","pdf_url":null,"source":{"id":"https://openalex.org/S4306402636","display_name":"Oxford University Research Archive (ORA) (University of Oxford)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I40120149","host_organization_name":"University of Oxford","host_organization_lineage":["https://openalex.org/I40120149"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference item"},{"id":"doi:10.48550/arxiv.1906.03926","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1906.03926","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2019/880","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2019/880","pdf_url":"https://www.ijcai.org/proceedings/2019/0880.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.49000000953674316,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G2819684465","display_name":null,"funder_award_id":"1896649","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G7842005466","display_name":null,"funder_award_id":"Horizon 2020","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2948380112.pdf","grobid_xml":"https://content.openalex.org/works/W2948380112.grobid-xml"},"referenced_works_count":77,"referenced_works":["https://openalex.org/W1493490255","https://openalex.org/W1505482271","https://openalex.org/W1602500555","https://openalex.org/W1681299129","https://openalex.org/W1933349210","https://openalex.org/W1934909785","https://openalex.org/W1962416794","https://openalex.org/W1996678589","https://openalex.org/W2005814556","https://openalex.org/W2006710607","https://openalex.org/W2019480195","https://openalex.org/W2069809153","https://openalex.org/W2079656678","https://openalex.org/W2098774185","https://openalex.org/W2118781169","https://openalex.org/W2121863487","https://openalex.org/W2123024445","https://openalex.org/W2124033848","https://openalex.org/W2131600418","https://openalex.org/W2140584963","https://openalex.org/W2147152072","https://openalex.org/W2153579005","https://openalex.org/W2159727049","https://openalex.org/W2170329722","https://openalex.org/W2181849516","https://openalex.org/W2189089430","https://openalex.org/W2236233024","https://openalex.org/W2277684984","https://openalex.org/W2278131208","https://openalex.org/W2467589492","https://openalex.org/W2553882142","https://openalex.org/W2561715562","https://openalex.org/W2620290674","https://openalex.org/W2627585944","https://openalex.org/W2734458248","https://openalex.org/W2774005037","https://openalex.org/W2784820185","https://openalex.org/W2787266721","https://openalex.org/W2794908222","https://openalex.org/W2806690340","https://openalex.org/W2810305479","https://openalex.org/W2888329843","https://openalex.org/W2895560838","https://openalex.org/W2902117899","https://openalex.org/W2902729397","https://openalex.org/W2903172725","https://openalex.org/W2907923173","https://openalex.org/W2910243263","https://openalex.org/W2914112028","https://openalex.org/W2917052767","https://openalex.org/W2947182319","https://openalex.org/W2950276680","https://openalex.org/W2952222085","https://openalex.org/W2953369973","https://openalex.org/W2954579883","https://openalex.org/W2962684798","https://openalex.org/W2962739339","https://openalex.org/W2962891854","https://openalex.org/W2963026768","https://openalex.org/W2963159690","https://openalex.org/W2963197656","https://openalex.org/W2963277051","https://openalex.org/W2963281204","https://openalex.org/W2963341956","https://openalex.org/W2963367210","https://openalex.org/W2963475460","https://openalex.org/W2963571817","https://openalex.org/W2963791035","https://openalex.org/W2964118342","https://openalex.org/W2964164804","https://openalex.org/W2964193163","https://openalex.org/W2964217371","https://openalex.org/W2964654516","https://openalex.org/W2964935470","https://openalex.org/W3101555782","https://openalex.org/W3121541553","https://openalex.org/W3121854931"],"related_works":["https://openalex.org/W2964915587","https://openalex.org/W2627585944","https://openalex.org/W2963341956","https://openalex.org/W567721252","https://openalex.org/W2895560838","https://openalex.org/W2145339207","https://openalex.org/W2121863487","https://openalex.org/W2970786335","https://openalex.org/W2964001908","https://openalex.org/W2064675550","https://openalex.org/W2963403868","https://openalex.org/W2736601468","https://openalex.org/W2964179661","https://openalex.org/W2914112028","https://openalex.org/W2158782408","https://openalex.org/W3121854931","https://openalex.org/W2964043796","https://openalex.org/W2963921132","https://openalex.org/W2553882142","https://openalex.org/W1757796397"],"abstract_inverted_index":{"To":[0],"be":[1],"successful":[2],"in":[3,33,79],"real-world":[4],"tasks,":[5],"Reinforcement":[6],"Learning":[7],"(RL)":[8],"needs":[9],"to":[10,23,26,41,68],"exploit":[11],"the":[12,19,27,64,83,86,105,116],"compositional,":[13],"relational,":[14],"and":[15,21,51,95],"hierarchical":[16],"structure":[17],"of":[18,73,85,107,119],"world,":[20],"learn":[22],"transfer":[24],"it":[25,39],"task":[28],"at":[29],"hand.":[30],"Recent":[31],"advances":[32],"representation":[34],"learning":[35,96],"for":[36,104,126],"language":[37,75],"make":[38],"possible":[40],"build":[42],"models":[43],"that":[44,63],"acquire":[45],"world":[46],"knowledge":[47,54],"from":[48,97],"text":[49,93],"corpora":[50],"integrate":[52],"this":[53],"into":[55,77,115],"downstream":[56],"decision":[57],"making":[58],"problems.":[59],"We":[60,81],"thus":[61],"argue":[62],"time":[65],"is":[66],"right":[67],"investigate":[69],"a":[70],"tight":[71],"integration":[72],"natural":[74],"understanding":[76],"RL":[78],"particular.":[80],"survey":[82],"state":[84],"field,":[87],"including":[88],"work":[89],"on":[90],"instruction":[91],"following,":[92],"games,":[94],"textual":[98],"domain":[99],"knowledge.":[100],"Finally,":[101],"we":[102],"call":[103],"development":[106],"new":[108],"environments":[109],"as":[110,112],"well":[111],"further":[113],"investigation":[114],"potential":[117],"uses":[118],"recent":[120],"Natural":[121],"Language":[122],"Processing":[123],"(NLP)":[124],"techniques":[125],"such":[127],"tasks.":[128]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":25},{"year":2020,"cited_by_count":25},{"year":2019,"cited_by_count":8}],"updated_date":"2026-05-05T08:41:31.759640","created_date":"2025-10-10T00:00:00"}