{"id":"https://openalex.org/W2900677334","doi":"https://doi.org/10.48550/arxiv.1811.09740","title":"Connecting the Dots Between MLE and RL for Sequence Prediction","display_name":"Connecting the Dots Between MLE and RL for Sequence Prediction","publication_year":2018,"publication_date":"2018-11-24","ids":{"openalex":"https://openalex.org/W2900677334","doi":"https://doi.org/10.48550/arxiv.1811.09740","mag":"2900677334"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:1811.09740","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1811.09740","pdf_url":"https://arxiv.org/pdf/1811.09740","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","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1811.09740","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Tan, Bowen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tan, Bowen","raw_affiliation_strings":["( equal contribution) Carnegie Mellon University 1 , Petuum Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"( equal contribution) Carnegie Mellon University 1 , Petuum Inc","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085608858","display_name":"Zhiting Hu","orcid":"https://orcid.org/0000-0002-6239-5031","observed_orcids":["https://orcid.org/0000-0002-6239-5031"]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hu, Zhiting","raw_affiliation_strings":["( equal contribution) Carnegie Mellon University 1 , Petuum Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"( equal contribution) Carnegie Mellon University 1 , Petuum Inc","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101461004","display_name":"Zichao Yang","orcid":"https://orcid.org/0009-0001-7734-5766","observed_orcids":["https://orcid.org/0009-0001-7734-5766"]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yang, Zichao","raw_affiliation_strings":["( equal contribution) Carnegie Mellon University 1 , Petuum Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"( equal contribution) Carnegie Mellon University 1 , Petuum Inc","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071983998","display_name":"Ruslan Salakhutdinov","orcid":"https://orcid.org/0000-0002-3752-2756","observed_orcids":["https://orcid.org/0000-0002-3752-2756"]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Salakhutdinov, Ruslan","raw_affiliation_strings":["( equal contribution) Carnegie Mellon University 1 , Petuum Inc","Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"( equal contribution) Carnegie Mellon University 1 , Petuum Inc","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009547049","display_name":"Eric P. Xing","orcid":"https://orcid.org/0009-0005-9158-4201","observed_orcids":["https://orcid.org/0009-0005-9158-4201","https://orcid.org/0000-0002-3683-4280"]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xing, Eric","raw_affiliation_strings":["( equal contribution) Carnegie Mellon University 1 , Petuum Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"( equal contribution) Carnegie Mellon University 1 , Petuum Inc","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":17,"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":0.9564999938011169,"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":0.9564999938011169,"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":0.013500000350177288,"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":0.013299999758601189,"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/sequence-prediction","display_name":"sequence prediction","score":0.9480000138282776},{"id":"https://openalex.org/keywords/maximum-likelihood-estimation","display_name":"maximum likelihood estimation","score":0.9039999842643738},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.890999972820282},{"id":"https://openalex.org/keywords/policy-gradient","display_name":"policy gradient","score":0.7739999890327454},{"id":"https://openalex.org/keywords/exploration-efficiency","display_name":"exploration efficiency","score":0.7139999866485596},{"id":"https://openalex.org/keywords/compounding-errors","display_name":"compounding errors","score":0.7749999761581421},{"id":"https://openalex.org/keywords/reward-function-design","display_name":"reward function design","score":0.7289999723434448},{"id":"https://openalex.org/keywords/machine-translation","display_name":"machine translation","score":0.7540000081062317},{"id":"https://openalex.org/keywords/text-summarization","display_name":"text summarization","score":0.9950000047683716}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7489815950393677},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.6722385883331299},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6488655805587769},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.6366419196128845},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5856825709342957},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.541069746017456},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4535081386566162},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3787781596183777},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","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}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:1811.09740","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1811.09740","pdf_url":"https://arxiv.org/pdf/1811.09740","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.1811.09740","doi":"https://doi.org/10.48550/arxiv.1811.09740","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1811.09740","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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1811.09740","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1811.09740","pdf_url":"https://arxiv.org/pdf/1811.09740","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":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2900677334.pdf","grobid_xml":"https://content.openalex.org/works/W2900677334.grobid-xml"},"referenced_works_count":54,"referenced_works":["https://openalex.org/W648786980","https://openalex.org/W1499669280","https://openalex.org/W1771410628","https://openalex.org/W1843891098","https://openalex.org/W1895577753","https://openalex.org/W1902237438","https://openalex.org/W1905882502","https://openalex.org/W1924770834","https://openalex.org/W1969415786","https://openalex.org/W2064675550","https://openalex.org/W2080039641","https://openalex.org/W2099471712","https://openalex.org/W2123086176","https://openalex.org/W2130942839","https://openalex.org/W2142641780","https://openalex.org/W2145339207","https://openalex.org/W2154368244","https://openalex.org/W2155027007","https://openalex.org/W2158782408","https://openalex.org/W2296073425","https://openalex.org/W2434014514","https://openalex.org/W2487501366","https://openalex.org/W2525778437","https://openalex.org/W2560313346","https://openalex.org/W2594103415","https://openalex.org/W2594978815","https://openalex.org/W2609482285","https://openalex.org/W2609650878","https://openalex.org/W2618606525","https://openalex.org/W2626177496","https://openalex.org/W2626778328","https://openalex.org/W2735642330","https://openalex.org/W2736601468","https://openalex.org/W2770553825","https://openalex.org/W2784823820","https://openalex.org/W2785601945","https://openalex.org/W2785738552","https://openalex.org/W2799151646","https://openalex.org/W2805041018","https://openalex.org/W2810565934","https://openalex.org/W2889862754","https://openalex.org/W2890964657","https://openalex.org/W2892043231","https://openalex.org/W2907222274","https://openalex.org/W2949608212","https://openalex.org/W2963199420","https://openalex.org/W2963248296","https://openalex.org/W2963620441","https://openalex.org/W2963673305","https://openalex.org/W2963687836","https://openalex.org/W2963962369","https://openalex.org/W2964308564","https://openalex.org/W3041866211","https://openalex.org/W6903351479"],"related_works":["https://openalex.org/W2963244606","https://openalex.org/W4376639574","https://openalex.org/W3165994454","https://openalex.org/W2965282611","https://openalex.org/W3213789840","https://openalex.org/W2554701276","https://openalex.org/W2891958946","https://openalex.org/W7018112921","https://openalex.org/W6929370958","https://openalex.org/W4361229589"],"abstract_inverted_index":{"Sequence":[0],"prediction":[1],"models":[2],"can":[3,23,41,92],"be":[4,94],"learned":[5],"from":[6,25,64,136],"example":[7],"sequences":[8],"with":[9,102],"a":[10,70,78,110,114,122,141],"variety":[11],"of":[12,50,99,109,116,125,129,150,170],"training":[13],"algorithms.":[14,75],"Maximum":[15],"likelihood":[16],"learning":[17,32,132,166],"is":[18],"simple":[19],"and":[20,57,85,113,131,163],"efficient,":[21],"yet":[22],"suffer":[24],"compounding":[26],"error":[27],"at":[28],"test":[29],"time.":[30],"Reinforcement":[31],"such":[33,53],"as":[34,54,96],"policy":[35,82],"gradient":[36],"addresses":[37],"the":[38,88,100,103,107,126,137,148,168,171],"issue":[39],"but":[40],"have":[42,60],"prohibitively":[43],"poor":[44],"exploration":[45,130],"efficiency.":[46,133],"A":[47],"rich":[48],"set":[49],"other":[51],"algorithms":[52,91,151],"RAML,":[55],"SPG,":[56],"data":[58],"noising,":[59],"also":[61],"been":[62],"developed":[63],"different":[65],"perspectives.":[66],"This":[67],"paper":[68],"establishes":[69],"formal":[71],"connection":[72],"between":[73],"these":[74],"We":[76],"present":[77,140],"generalized":[79],"entropy":[80],"regularized":[81],"optimization":[83],"formulation,":[84],"show":[86],"that":[87,144],"apparently":[89],"distinct":[90],"all":[93],"reformulated":[95],"special":[97],"instances":[98],"framework,":[101,138],"only":[104],"difference":[105],"being":[106],"configurations":[108],"reward":[111],"function":[112],"couple":[115],"hyperparameters.":[117],"The":[118],"unified":[119],"interpretation":[120],"offers":[121],"systematic":[123],"view":[124],"varying":[127],"properties":[128],"Besides,":[134],"inspired":[135],"we":[139],"new":[142],"algorithm":[143],"dynamically":[145],"interpolates":[146],"among":[147],"family":[149],"for":[152],"scheduled":[153],"sequence":[154],"model":[155],"learning.":[156],"Experiments":[157],"on":[158],"machine":[159],"translation,":[160],"text":[161],"summarization,":[162],"game":[164],"imitation":[165],"demonstrate":[167],"superiority":[169],"proposed":[172],"algorithm.":[173]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2018-11-29T00:00:00"}