{"id":"https://openalex.org/W2964179661","doi":"https://doi.org/10.18653/v1/p16-1153","title":"Deep Reinforcement Learning with a Natural Language Action Space","display_name":"Deep Reinforcement Learning with a Natural Language Action Space","publication_year":2016,"publication_date":"2016-01-01","ids":{"openalex":"https://openalex.org/W2964179661","doi":"https://doi.org/10.18653/v1/p16-1153","mag":"2964179661"},"language":"en","primary_location":{"id":"doi:10.18653/v1/p16-1153","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p16-1153","pdf_url":"https://www.aclweb.org/anthology/P16-1153.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/P16-1153.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5017295309","display_name":"Ji He","orcid":"https://orcid.org/0000-0001-9811-6500"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ji He","raw_affiliation_strings":["Department of Electrical Engineering, University of Washington, Seattle, WA 98195, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, University of Washington, Seattle, WA 98195, USA","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088339142","display_name":"Jianshu Chen","orcid":"https://orcid.org/0000-0001-8216-2756"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jianshu Chen","raw_affiliation_strings":["Microsoft Research, Redmond, WA 98052, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA 98052, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101727205","display_name":"Xiaodong He","orcid":"https://orcid.org/0000-0002-9463-9168"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaodong He","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114910293","display_name":"Jianfeng Gao","orcid":"https://orcid.org/0000-0002-5702-6143"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jianfeng Gao","raw_affiliation_strings":["Microsoft Research, Redmond, WA 98052, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA 98052, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100711454","display_name":"Lihong Li","orcid":"https://orcid.org/0000-0002-5440-8242"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lihong Li","raw_affiliation_strings":["Microsoft Research, Redmond, WA 98052, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA 98052, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100671324","display_name":"Li Deng","orcid":"https://orcid.org/0000-0002-1014-0790"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Li Deng","raw_affiliation_strings":["Microsoft Research, Redmond, WA 98052, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA 98052, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087215613","display_name":"Mari Ostendorf","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]},{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mari Ostendorf","raw_affiliation_strings":["Department of Electrical Engineering, University of Washington, Seattle, WA 98195, USA","Microsoft Research, Redmond, WA 98052, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, University of Washington, Seattle, WA 98195, USA","institution_ids":["https://openalex.org/I201448701"]},{"raw_affiliation_string":"Microsoft Research, Redmond, WA 98052, USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":176,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1621","last_page":"1630"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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/T10028","display_name":"Topic Modeling","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/T10181","display_name":"Natural Language Processing Techniques","score":0.9988999962806702,"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/T12031","display_name":"Speech and dialogue systems","score":0.996999979019165,"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/action","display_name":"Action (physics)","score":0.6178684830665588},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.612155020236969},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6023944616317749},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5319735407829285},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5157256722450256},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.494099885225296},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4567478895187378},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.4315774142742157},{"id":"https://openalex.org/keywords/cognitive-science","display_name":"Cognitive science","score":0.35381120443344116},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.2012510895729065},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.18738538026809692},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.10757765173912048}],"concepts":[{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.6178684830665588},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.612155020236969},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6023944616317749},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5319735407829285},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5157256722450256},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.494099885225296},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4567478895187378},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.4315774142742157},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.35381120443344116},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.2012510895729065},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.18738538026809692},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.10757765173912048},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/p16-1153","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p16-1153","pdf_url":"https://www.aclweb.org/anthology/P16-1153.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/p16-1153","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p16-1153","pdf_url":"https://www.aclweb.org/anthology/P16-1153.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.7799999713897705,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2964179661.pdf","grobid_xml":"https://content.openalex.org/works/W2964179661.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W1211946649","https://openalex.org/W1555295778","https://openalex.org/W1595483645","https://openalex.org/W1757796397","https://openalex.org/W1902237438","https://openalex.org/W1934909785","https://openalex.org/W1975244201","https://openalex.org/W2083205357","https://openalex.org/W2117130368","https://openalex.org/W2122223050","https://openalex.org/W2130942839","https://openalex.org/W2131744502","https://openalex.org/W2136189984","https://openalex.org/W2145339207","https://openalex.org/W2147768505","https://openalex.org/W2160815625","https://openalex.org/W2163605009","https://openalex.org/W2262178610","https://openalex.org/W2787259794","https://openalex.org/W2791590751","https://openalex.org/W2919115771","https://openalex.org/W2963864421","https://openalex.org/W3121854931","https://openalex.org/W4214717370","https://openalex.org/W4298857966","https://openalex.org/W4362203700"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W3084456289","https://openalex.org/W2024136090","https://openalex.org/W4391331176","https://openalex.org/W4226226396","https://openalex.org/W3153750606","https://openalex.org/W4308854837"],"abstract_inverted_index":{"Ji":[0],"He,":[1,5],"Jianshu":[2],"Chen,":[3],"Xiaodong":[4],"Jianfeng":[6],"Gao,":[7],"Lihong":[8],"Li,":[9],"Li":[10],"Deng,":[11],"Mari":[12],"Ostendorf.":[13],"Proceedings":[14],"of":[15,20],"the":[16,21],"54th":[17],"Annual":[18],"Meeting":[19],"Association":[22],"for":[23],"Computational":[24],"Linguistics":[25],"(Volume":[26],"1:":[27],"Long":[28],"Papers).":[29],"2016.":[30]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":16},{"year":2022,"cited_by_count":18},{"year":2021,"cited_by_count":33},{"year":2020,"cited_by_count":34},{"year":2019,"cited_by_count":28},{"year":2018,"cited_by_count":14},{"year":2017,"cited_by_count":10},{"year":2016,"cited_by_count":5}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
