{"id":"https://openalex.org/W4414787247","doi":"https://doi.org/10.18653/v1/2026.acl-long.506","title":"Reinforcement Learning on Pre-Training Data","display_name":"Reinforcement Learning on Pre-Training Data","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W4414787247","doi":"https://doi.org/10.18653/v1/2026.acl-long.506"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.acl-long.506","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.506","pdf_url":"https://aclanthology.org/2026.acl-long.506.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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.acl-long.506.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5060478851","display_name":"Siheng Li","orcid":"https://orcid.org/0000-0001-9582-3568"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Siheng Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077452182","display_name":"Kejiao Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kejiao Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101699041","display_name":"Zhiying Xu","orcid":"https://orcid.org/0000-0003-0233-9713"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zenan Xu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023274590","display_name":"Guanhua Huang","orcid":"https://orcid.org/0000-0002-2836-248X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guanhua Huang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5143327157","display_name":"Kun Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kun Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071673364","display_name":"Haoyuan Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haoyuan Wu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071673364","display_name":"Haoyuan Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wujiajia","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107987282","display_name":"Zihao Zheng","orcid":"https://orcid.org/0000-0001-8166-0649"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zihao Zheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107987282","display_name":"Zihao Zheng","orcid":"https://orcid.org/0000-0001-8166-0649"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chenchen Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5143325779","display_name":"Kun Shi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kun Shi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123573658","display_name":"X Z Gong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xue Gong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5143362749","display_name":"Qi Yi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qi Yi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102311082","display_name":"Ruibin Xiong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ruibin Xiong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107517057","display_name":"Tingqiang Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tingqiang Xu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5143355905","display_name":"Yuhao Jiang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuhao Jiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5143392424","display_name":"Jianfeng Yan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jianfeng Yan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076901150","display_name":"Yuyuan Zeng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuyuan Zeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101552980","display_name":"Guanghui Xu","orcid":"https://orcid.org/0000-0003-2910-9870"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guanghui Xu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025328651","display_name":"Jinbao Xue","orcid":"https://orcid.org/0009-0003-4087-9873"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jinbao Xue","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025328651","display_name":"Jinbao Xue","orcid":"https://orcid.org/0009-0003-4087-9873"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhijiang xu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102052476","display_name":"Fang Zheng","orcid":"https://orcid.org/0000-0002-7122-6707"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zheng Fang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5143370034","display_name":"Shuai LI","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shuai LI","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083428910","display_name":"Shuai Cheng Li","orcid":"https://orcid.org/0000-0001-6246-6349"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qibin Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115592212","display_name":"Xiaoxue Li","orcid":"https://orcid.org/0000-0003-3581-3442"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaoxue Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115592212","display_name":"Xiaoxue Li","orcid":"https://orcid.org/0000-0003-3581-3442"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhuoyu Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077922409","display_name":"Yangyu Tao","orcid":"https://orcid.org/0009-0003-0536-4321"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yangyu Tao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101604884","display_name":"Fei Gao","orcid":"https://orcid.org/0000-0003-1010-3567"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fei Gao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021821354","display_name":"C Y Jiang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cheng Jiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003676104","display_name":"Bochao Wang","orcid":"https://orcid.org/0000-0002-3091-1257"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bochao Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100399934","display_name":"Kai Liu","orcid":"https://orcid.org/0000-0002-7584-9231"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kai Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048188910","display_name":"J ZHU","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jianchen Zhu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024253012","display_name":"W.K. Lam","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wai Lam","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5143165467","display_name":"Bo Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bo Zhou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5143353084","display_name":"Di Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Di Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00821962,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"11046","last_page":"11057"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12761","display_name":"Data Stream Mining Techniques","score":0.7793999910354614,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.7793999910354614,"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/T10320","display_name":"Neural Networks and Applications","score":0.7544000148773193,"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":0.7254999876022339,"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":0.8718000054359436},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.41269999742507935},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.38679999113082886},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.3564000129699707},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.35179999470710754},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"Temporal difference learning","score":0.33379998803138733}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8718000054359436},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6908000111579895},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6590999960899353},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4668999910354614},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.41269999742507935},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.38679999113082886},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.3564000129699707},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.35179999470710754},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.33379998803138733},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.31859999895095825},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.29030001163482666},{"id":"https://openalex.org/C85847156","wikidata":"https://www.wikidata.org/wiki/Q59015987","display_name":"Verifiable secret sharing","level":3,"score":0.28529998660087585},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.26899999380111694},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.26589998602867126}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.506","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.506","pdf_url":"https://aclanthology.org/2026.acl-long.506.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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2509.19249","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.19249","pdf_url":"https://arxiv.org/pdf/2509.19249","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"doi:10.48550/arxiv.2509.19249","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2509.19249","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-long.506","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.506","pdf_url":"https://aclanthology.org/2026.acl-long.506.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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321920","display_name":"Innovation and Technology Commission","ror":"https://ror.org/04vf9tr09"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4414787247.pdf","grobid_xml":"https://content.openalex.org/works/W4414787247.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Siheng":[0],"Li,":[1,3,9,46,48],"Kejiao":[2],"Zenan":[4],"Xu,":[5,26,34],"Guanhua":[6],"Huang,":[7],"Kun":[8,17],"Haoyuan":[10],"Wu,":[11],"Wujiajia,":[12],"Zihao":[13],"Zheng,":[14],"Chenchen":[15],"Zhang,":[16],"Shi,":[18],"Xue":[19],"Gong,":[20],"Qi":[21],"Yi,":[22],"Ruibin":[23],"Xiong,":[24],"Tingqiang":[25],"Yuhao":[27],"Jiang,":[28,54],"Jianfeng":[29],"Yan,":[30],"Yuyuan":[31],"Zeng,":[32],"Guanghui":[33],"Jinbao":[35],"Xue,":[36],"Zhijiang":[37],"xu,":[38],"Zheng":[39],"Fang,":[40],"Shuai":[41],"LI,":[42],"Qibin":[43],"Liu,":[44,58],"Xiaoxue":[45],"Zhuoyu":[47],"Yangyu":[49],"Tao,":[50],"Fei":[51],"Gao,":[52],"Cheng":[53],"Bochao":[55],"Wang,":[56],"Kai":[57],"Jianchen":[59],"Zhu,":[60],"Wai":[61],"Lam,":[62],"Bo":[63],"Zhou,":[64],"Di":[65],"Wang.":[66],"Proceedings":[67],"of":[68,73],"the":[69,74],"64th":[70],"Annual":[71],"Meeting":[72],"Association":[75],"for":[76],"Computational":[77],"Linguistics":[78],"(Volume":[79],"1:":[80],"Long":[81],"Papers).":[82],"2026.":[83]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
