{"id":"https://openalex.org/W2564034046","doi":null,"title":"Tuning Recurrent Neural Networks with Reinforcement Learning","display_name":"Tuning Recurrent Neural Networks with Reinforcement Learning","publication_year":2016,"publication_date":"2016-11-09","ids":{"openalex":"https://openalex.org/W2564034046","mag":"2564034046"},"language":"en","primary_location":{"id":"mag:2963274209","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1611.02796","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1611.02796","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5046953322","display_name":"Natasha Jaques","orcid":"https://orcid.org/0000-0002-8413-9469","observed_orcids":["https://orcid.org/0000-0002-8413-9469"]},"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":"Natasha Jaques","raw_affiliation_strings":["Massachusetts Institute Of Technology#TAB#"],"raw_orcid":"https://orcid.org/0000-0002-8413-9469","affiliations":[{"raw_affiliation_string":"Massachusetts Institute Of Technology#TAB#","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061613634","display_name":"Shixiang Gu","orcid":"https://orcid.org/0000-0001-9246-0896","observed_orcids":["https://orcid.org/0000-0001-9246-0896"]},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Shixiang Gu","raw_affiliation_strings":["Univ. of Cambridge"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Univ. of Cambridge","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108284020","display_name":"Richard E. Turner","orcid":"https://orcid.org/0000-0003-0066-0984","observed_orcids":["https://orcid.org/0000-0003-0066-0984","https://orcid.org/0000-0003-1751-0448"]},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Richard E. Turner","raw_affiliation_strings":["Univ. of Cambridge"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Univ. of Cambridge","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055592482","display_name":"Douglas Eck","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Douglas Eck","raw_affiliation_strings":["Google,,,,,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google,,,,,","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":56,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9110999703407288,"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":0.9110999703407288,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.047600001096725464,"subfield":{"id":"https://openalex.org/subfields/1210","display_name":"Music"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11574","display_name":"Artificial Intelligence in Games","score":0.0044999998062849045,"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/recurrent-neural-networks","display_name":"recurrent neural networks","score":0.8740000128746033},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.8600000143051147},{"id":"https://openalex.org/keywords/sequence-learning","display_name":"sequence learning","score":0.703000009059906},{"id":"https://openalex.org/keywords/deep-q-learning","display_name":"deep Q-learning","score":0.878000020980835},{"id":"https://openalex.org/keywords/music-generation","display_name":"music generation","score":0.8069999814033508},{"id":"https://openalex.org/keywords/lstm","display_name":"LSTM","score":0.8970000147819519},{"id":"https://openalex.org/keywords/music-theory","display_name":"music theory","score":0.7839999794960022},{"id":"https://openalex.org/keywords/failure-modes","display_name":"failure modes","score":0.44200000166893005}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8444966077804565},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.7943934202194214},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7534712553024292},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6575798392295837},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5562168955802917},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5525545477867126},{"id":"https://openalex.org/C40506919","wikidata":"https://www.wikidata.org/wiki/Q7452469","display_name":"Sequence learning","level":2,"score":0.5219820737838745},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.49767425656318665},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4829092025756836},{"id":"https://openalex.org/C43803900","wikidata":"https://www.wikidata.org/wiki/Q170412","display_name":"Melody","level":3,"score":0.46864575147628784},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.1019749641418457},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","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/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"mag:2963274209","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1611.02796","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"mag:2564034046","doi":null,"is_oa":false,"landing_page_url":"https://openreview.net/pdf?id=Syyv2e-Kx","pdf_url":null,"source":{"id":"https://openalex.org/S4306419637","display_name":"International Conference on Learning Representations","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"International Conference on Learning Representations","raw_type":null}],"best_oa_location":{"id":"mag:2963274209","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1611.02796","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2591984255","https://openalex.org/W3157522653","https://openalex.org/W2591904660","https://openalex.org/W4226266288","https://openalex.org/W1976953209","https://openalex.org/W4285152669","https://openalex.org/W4226133618","https://openalex.org/W648786980","https://openalex.org/W7097043324","https://openalex.org/W2884817714"],"abstract_inverted_index":{"The":[0],"approach":[1,38,115],"of":[2,52,113,119,130,152,185],"training":[3],"sequence":[4,67],"models":[5],"using":[6,147],"supervised":[7],"learning":[8],"and":[9,99,150,163,182],"next-step":[10],"prediction":[11],"suffers":[13],"from":[14,82,106,192],"known":[15],"failure":[16,183],"modes.":[17],"For":[18],"example,":[19],"it":[20],"is":[21,124,144],"notoriously":[22],"difficult":[23],"to":[24,49,88,132],"ensure":[25],"multi-step":[26],"generated":[27],"sequences":[28],"have":[29],"coherent":[30],"global":[31],"structure.":[32],"We":[33,84,109,155],"propose":[34,85],"a":[35,43,57,66,96,127,138],"novel":[36,101],"sequence-learning":[37],"in":[39,56,116,137,165],"which":[40],"we":[41,63,168],"use":[42],"pre-trained":[44],"Recurrent":[45],"Neural":[46],"Network":[47],"(RNN)":[48],"supply":[50],"part":[51],"the":[53,111,117,134,186],"reward":[54,74,98],"value":[55],"Reinforcement":[58],"Learning":[59],"(RL)":[60],"model.":[61],"Thus,":[62],"can":[64,169],"refine":[65],"predictor":[68],"by":[69,91,158],"optimizing":[70],"for":[71,104],"some":[72],"imposed":[73],"functions,":[75],"while":[76,188],"maintaining":[77,189],"good":[78],"predictive":[79],"properties":[80],"learned":[81,191],"data.":[83,193],"efficient":[86],"ways":[87],"solve":[89],"this":[90,166],"augmenting":[92],"deep":[93],"Q-learning":[94],"with":[95],"cross-entropy":[97],"deriving":[100],"off-policy":[102],"methods":[103],"RNNs":[105],"KL":[107],"control.":[108],"explore":[110],"usefulness":[112],"our":[114,148],"context":[118],"music":[120,153],"generation.":[121],"An":[122],"LSTM":[123],"trained":[125],"on":[126],"large":[128],"corpus":[129],"songs":[131],"predict":[133],"next":[135],"note":[136],"musical":[139],"sequence.":[140],"This":[141],"Note":[142],"RNN":[143],"then":[145],"refined":[146],"method":[149],"rules":[151],"theory.":[154],"show":[156],"that":[157],"combining":[159],"maximum":[160],"likelihood":[161],"(ML)":[162],"RL":[164],"way,":[167],"not":[170],"only":[171],"produce":[172],"more":[173],"pleasing":[174],"melodies,":[175],"but":[176],"significantly":[178],"reduce":[179],"unwanted":[180],"behaviors":[181],"modes":[184],"RNN,":[187],"information":[190]},"counts_by_year":[{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":13},{"year":2019,"cited_by_count":9},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":4}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2017-01-06T00:00:00"}