{"id":"https://openalex.org/W2611884151","doi":"https://doi.org/10.18653/v1/d17-1106","title":"Mapping Instructions and Visual Observations to Actions with Reinforcement Learning","display_name":"Mapping Instructions and Visual Observations to Actions with Reinforcement Learning","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2611884151","doi":"https://doi.org/10.18653/v1/d17-1106","mag":"2611884151"},"language":"en","primary_location":{"id":"doi:10.18653/v1/d17-1106","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d17-1106","pdf_url":"https://www.aclweb.org/anthology/D17-1106.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 2017 Conference on Empirical Methods in Natural\n          Language Processing","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/D17-1106.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5088218114","display_name":"Dipendra Misra","orcid":null},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Dipendra Misra","raw_affiliation_strings":["Dept. of Computer Science and Cornell Tech, Cornell University, New York, NY 10044","Cornell University, Ithaca, United States"],"affiliations":[{"raw_affiliation_string":"Dept. of Computer Science and Cornell Tech, Cornell University, New York, NY 10044","institution_ids":["https://openalex.org/I205783295"]},{"raw_affiliation_string":"Cornell University, Ithaca, United States","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005003250","display_name":"John Langford","orcid":"https://orcid.org/0000-0002-9811-3550"},"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/I4401726785","display_name":"Microsoft Research New York City (United States)","ror":"https://ror.org/056zprp28","country_code":null,"type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4401726785"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John Langford","raw_affiliation_strings":["Microsoft Research, New York, NY 10011","Microsoft (United States), Redmond, United States"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, New York, NY 10011","institution_ids":["https://openalex.org/I1290206253","https://openalex.org/I4401726785"]},{"raw_affiliation_string":"Microsoft (United States), Redmond, United States","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047026141","display_name":"Yoav Artzi","orcid":"https://orcid.org/0000-0002-4605-6144"},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yoav Artzi","raw_affiliation_strings":["Dept. of Computer Science and Cornell Tech, Cornell University, New York, NY 10044","Cornell University, Ithaca, United States"],"affiliations":[{"raw_affiliation_string":"Dept. of Computer Science and Cornell Tech, Cornell University, New York, NY 10044","institution_ids":["https://openalex.org/I205783295"]},{"raw_affiliation_string":"Cornell University, Ithaca, United States","institution_ids":["https://openalex.org/I205783295"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5088218114"],"corresponding_institution_ids":["https://openalex.org/I205783295"],"apc_list":null,"apc_paid":null,"fwci":2.7732,"has_fulltext":true,"cited_by_count":42,"citation_normalized_percentile":{"value":0.94523045,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1004","last_page":"1015"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998000264167786,"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"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.995199978351593,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9822999835014343,"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":0.8615760207176208},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.761509895324707},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.7368568181991577},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.580305814743042},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.48226290941238403},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4591479003429413},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.10756418108940125},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.06182706356048584}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8615760207176208},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.761509895324707},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7368568181991577},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.580305814743042},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.48226290941238403},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4591479003429413},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.10756418108940125},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.06182706356048584},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.18653/v1/d17-1106","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d17-1106","pdf_url":"https://www.aclweb.org/anthology/D17-1106.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 2017 Conference on Empirical Methods in Natural\n          Language Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1704.08795","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1704.08795","pdf_url":"https://arxiv.org/pdf/1704.08795","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"mag:2611884151","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/1704.08795","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1704.08795","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1704.08795","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"article"}],"best_oa_location":{"id":"doi:10.18653/v1/d17-1106","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/d17-1106","pdf_url":"https://www.aclweb.org/anthology/D17-1106.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 2017 Conference on Empirical Methods in Natural\n          Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.4699999988079071,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G2514421424","display_name":null,"funder_award_id":"Award","funder_id":"https://openalex.org/F4320308943","funder_display_name":"Microsoft Research"}],"funders":[{"id":"https://openalex.org/F4320308943","display_name":"Microsoft Research","ror":"https://ror.org/00d0nc645"},{"id":"https://openalex.org/F4320310598","display_name":"Amazon Web Services","ror":"https://ror.org/04mv4n011"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2611884151.pdf","grobid_xml":"https://content.openalex.org/works/W2611884151.grobid-xml"},"referenced_works_count":53,"referenced_works":["https://openalex.org/W46490633","https://openalex.org/W1522301498","https://openalex.org/W1575592356","https://openalex.org/W1602500555","https://openalex.org/W1757796397","https://openalex.org/W1777239053","https://openalex.org/W1889081078","https://openalex.org/W1925737941","https://openalex.org/W1934909785","https://openalex.org/W1962416794","https://openalex.org/W1977655452","https://openalex.org/W1993411524","https://openalex.org/W2005814556","https://openalex.org/W2014421850","https://openalex.org/W2070789508","https://openalex.org/W2077902449","https://openalex.org/W2098258765","https://openalex.org/W2110485445","https://openalex.org/W2118781169","https://openalex.org/W2121863487","https://openalex.org/W2129629813","https://openalex.org/W2137607685","https://openalex.org/W2138455848","https://openalex.org/W2145339207","https://openalex.org/W2155027007","https://openalex.org/W2164419340","https://openalex.org/W2170329722","https://openalex.org/W2189089430","https://openalex.org/W2229480318","https://openalex.org/W2236233024","https://openalex.org/W2251648989","https://openalex.org/W2257979135","https://openalex.org/W2310425190","https://openalex.org/W2397581010","https://openalex.org/W2418628973","https://openalex.org/W2467589492","https://openalex.org/W2474390746","https://openalex.org/W2542999299","https://openalex.org/W2613863866","https://openalex.org/W2949608212","https://openalex.org/W2950178297","https://openalex.org/W2950761309","https://openalex.org/W2952629144","https://openalex.org/W2953212746","https://openalex.org/W2962887844","https://openalex.org/W2962905474","https://openalex.org/W2963143606","https://openalex.org/W2963167649","https://openalex.org/W2964043796","https://openalex.org/W2964118342","https://openalex.org/W2964161785","https://openalex.org/W2964179661","https://openalex.org/W3023151133"],"related_works":["https://openalex.org/W2118781169","https://openalex.org/W2189089430","https://openalex.org/W2627585944","https://openalex.org/W2236233024","https://openalex.org/W2194775991","https://openalex.org/W2963800628","https://openalex.org/W1602500555","https://openalex.org/W1522301498","https://openalex.org/W2964935470","https://openalex.org/W2964161785","https://openalex.org/W2963341956","https://openalex.org/W2950761309","https://openalex.org/W2785955089","https://openalex.org/W2064675550","https://openalex.org/W2951420334","https://openalex.org/W2897513296","https://openalex.org/W2774005037","https://openalex.org/W2467589492","https://openalex.org/W3037114407","https://openalex.org/W2887503931"],"abstract_inverted_index":{"We":[0,46,88],"propose":[1],"to":[2,11,21,38,55],"directly":[3],"map":[4],"raw":[5],"visual":[6,44],"observations":[7],"and":[8,43,94,101],"text":[9],"input":[10],"actions":[12],"for":[13],"instruction":[14],"execution.":[15],"While":[16],"existing":[17],"approaches":[18],"assume":[19],"access":[20],"structured":[22],"environment":[23],"representations":[24],"or":[25,84],"use":[26,47,67],"a":[27,35,51,57,91],"pipeline":[28],"of":[29,73],"separately":[30],"trained":[31],"models,":[32],"we":[33,66],"learn":[34],"single":[36],"model":[37],"jointly":[39],"reason":[40],"about":[41],"linguistic":[42],"input.":[45],"reinforcement":[48,103],"learning":[49,100,104],"in":[50,90],"contextual":[52],"bandit":[53],"setting":[54],"train":[56],"neural":[58],"network":[59],"agent.":[60],"To":[61],"guide":[62],"the":[63],"agent's":[64],"exploration,":[65],"reward":[68],"shaping":[69],"with":[70],"different":[71,86],"forms":[72],"supervision.":[74],"Our":[75],"approach":[76],"does":[77],"not":[78],"require":[79],"intermediate":[80],"representations,":[81],"planning":[82],"procedures,":[83],"training":[85],"models.":[87],"evaluate":[89],"simulated":[92],"environment,":[93],"show":[95],"significant":[96],"improvements":[97],"over":[98],"supervised":[99],"common":[102],"variants.":[105]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":9},{"year":2018,"cited_by_count":12},{"year":2017,"cited_by_count":2}],"updated_date":"2026-04-12T07:58:50.170612","created_date":"2025-10-10T00:00:00"}