{"id":"https://openalex.org/W3038023950","doi":"https://doi.org/10.48550/arxiv.2001.06944","title":"Nested-Wasserstein Self-Imitation Learning for Sequence Generation","display_name":"Nested-Wasserstein Self-Imitation Learning for Sequence Generation","publication_year":2020,"publication_date":"2020-01-20","ids":{"openalex":"https://openalex.org/W3038023950","doi":"https://doi.org/10.48550/arxiv.2001.06944","mag":"3038023950"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2001.06944","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2001.06944","pdf_url":"https://arxiv.org/pdf/2001.06944","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,"listed_in":[],"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"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2001.06944","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101424484","display_name":"Ruiyi Zhang","orcid":"https://orcid.org/0000-0002-4776-6762","observed_orcids":["https://orcid.org/0000-0002-4776-6762"]},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhang, Ruiyi","raw_affiliation_strings":["Duke University","Duke University#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Duke University","institution_ids":["https://openalex.org/I170897317"]},{"raw_affiliation_string":"Duke University#TAB#","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102745649","display_name":"Changyou Chen","orcid":"https://orcid.org/0000-0002-3230-2770","observed_orcids":["https://orcid.org/0000-0002-3230-2770"]},"institutions":[{"id":"https://openalex.org/I63190737","display_name":"University at Buffalo, State University of New York","ror":"https://ror.org/01y64my43","country_code":"US","type":"education","lineage":["https://openalex.org/I63190737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chen, Changyou","raw_affiliation_strings":["University at Buffalo","SUNY Buffalo, State University of New York (SUNY) System, State University of New York (SUNY) Buffalo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University at Buffalo","institution_ids":["https://openalex.org/I63190737"]},{"raw_affiliation_string":"SUNY Buffalo, State University of New York (SUNY) System, State University of New York (SUNY) Buffalo","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066666034","display_name":"Zhe Gan","orcid":null,"observed_orcids":[]},"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":"Gan, Zhe","raw_affiliation_strings":["Microsoft Dynamics 365 AI Research","Microsoft Dynam 365 AI Res"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Dynamics 365 AI Research","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft Dynam 365 AI Res","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067555437","display_name":"Zheng Wen","orcid":"https://orcid.org/0000-0001-6987-6463","observed_orcids":["https://orcid.org/0000-0001-6987-6463","https://orcid.org/0000-0002-6570-6245"]},"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"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Wen, Zheng","raw_affiliation_strings":["DeepMind"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepMind","institution_ids":["https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101558665","display_name":"Wenlin Wang","orcid":"https://orcid.org/0000-0003-0838-1920","observed_orcids":["https://orcid.org/0000-0003-0838-1920"]},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wang, Wenlin","raw_affiliation_strings":["Duke University","Duke University#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Duke University","institution_ids":["https://openalex.org/I170897317"]},{"raw_affiliation_string":"Duke University#TAB#","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016448581","display_name":"Lawrence Carin","orcid":"https://orcid.org/0000-0001-6277-7948","observed_orcids":["https://orcid.org/0000-0001-6277-7948"]},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Carin, Lawrence","raw_affiliation_strings":["Duke University","Duke University#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Duke University","institution_ids":["https://openalex.org/I170897317"]},{"raw_affiliation_string":"Duke University#TAB#","institution_ids":["https://openalex.org/I170897317"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"422","last_page":"433"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.8281000256538391,"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":0.8281000256538391,"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/T10028","display_name":"Topic Modeling","score":0.10530000180006027,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.018699999898672104,"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/self-imitation-learning","display_name":"self-imitation learning","score":0.9890000224113464},{"id":"https://openalex.org/keywords/sequence-generation","display_name":"sequence generation","score":0.9760000109672546},{"id":"https://openalex.org/keywords/proximal-policy-optimization","display_name":"proximal policy optimization","score":0.9890000224113464},{"id":"https://openalex.org/keywords/exploration-efficiency","display_name":"exploration efficiency","score":0.6930000185966492}],"concepts":[{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.7961667776107788},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7863149642944336},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7201134562492371},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.6839315891265869},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.6566816568374634},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.6453506350517273},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.536918580532074},{"id":"https://openalex.org/C2778493491","wikidata":"https://www.wikidata.org/wiki/Q7449072","display_name":"Semantic matching","level":3,"score":0.4737214148044586},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.45785295963287354},{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.45065826177597046},{"id":"https://openalex.org/C40506919","wikidata":"https://www.wikidata.org/wiki/Q7452469","display_name":"Sequence learning","level":2,"score":0.4144248068332672},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.384330689907074},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3378157615661621},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09934747219085693},{"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/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","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/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:arXiv.org:2001.06944","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2001.06944","pdf_url":"https://arxiv.org/pdf/2001.06944","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,"listed_in":[],"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.2001.06944","doi":"https://doi.org/10.48550/arxiv.2001.06944","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2001.06944","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,"listed_in":[],"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":false,"raw_source_name":null,"raw_type":"Preprint"},{"id":"mag:3038023950","doi":null,"is_oa":false,"landing_page_url":"http://proceedings.mlr.press/v108/zhang20b/zhang20b.pdf","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2001.06944","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2001.06944","pdf_url":"https://arxiv.org/pdf/2001.06944","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,"listed_in":[],"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"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3038023950.pdf","grobid_xml":"https://content.openalex.org/works/W3038023950.grobid-xml"},"referenced_works_count":10,"referenced_works":["https://openalex.org/W658020064","https://openalex.org/W1843891098","https://openalex.org/W1905882502","https://openalex.org/W2560313346","https://openalex.org/W2786002645","https://openalex.org/W2803839069","https://openalex.org/W2900260828","https://openalex.org/W2900677334","https://openalex.org/W2949376505","https://openalex.org/W2949608212"],"related_works":["https://openalex.org/W2898834548","https://openalex.org/W4393160802","https://openalex.org/W2902982219","https://openalex.org/W4380137125","https://openalex.org/W2997952181","https://openalex.org/W2787188308","https://openalex.org/W2802035631","https://openalex.org/W3016626426","https://openalex.org/W2949916679","https://openalex.org/W3165994454"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,63],"(RL)":[2],"has":[3],"been":[4],"widely":[5],"studied":[6],"for":[7,16,51,75],"improving":[8],"sequence-generation":[9,104],"models.":[10],"However,":[11],"the":[12,31,46,68,107],"conventional":[13],"rewards":[14,35],"used":[15],"RL":[17,37],"training":[18],"typically":[19],"cannot":[20],"capture":[21],"sufficient":[22],"semantic":[23,53,80],"information":[24],"and":[25,33,78,102],"therefore":[26],"render":[27],"model":[28,69],"bias.":[29],"Further,":[30],"sparse":[32],"delayed":[34],"make":[36],"exploration":[38,77],"inefficient.":[39],"To":[40,55],"alleviate":[41],"these":[42],"issues,":[43],"we":[44],"propose":[45],"concept":[47],"of":[48,100],"nested-Wasserstein":[49,61],"distance":[50],"distributional":[52],"matching.":[54,81],"further":[56],"exploit":[57,71],"it,":[58],"a":[59,98],"novel":[60],"self-imitation":[62],"framework":[64],"is":[65],"developed,":[66],"encouraging":[67],"to":[70,112],"historical":[72],"high-rewarded":[73],"sequences":[74],"enhanced":[76],"better":[79],"Our":[82],"solution":[83],"can":[84],"be":[85],"understood":[86],"as":[87],"approximately":[88],"executing":[89],"proximal":[90],"policy":[91],"optimization":[92],"with":[93],"Wasserstein":[94],"trust-regions.":[95],"Experiments":[96],"on":[97],"variety":[99],"unconditional":[101],"conditional":[103],"tasks":[105],"demonstrate":[106],"proposed":[108],"approach":[109],"consistently":[110],"leads":[111],"improved":[113],"performance.":[114]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2}],"updated_date":"2026-11-05T12:25:35.769452","created_date":"2020-07-02T00:00:00"}