{"id":"https://openalex.org/W2805465728","doi":null,"title":"Learning to Follow Language Instructions with Adversarial Reward Induction","display_name":"Learning to Follow Language Instructions with Adversarial Reward Induction","publication_year":2018,"publication_date":"2018-06-05","ids":{"openalex":"https://openalex.org/W2805465728","mag":"2805465728"},"language":"en","primary_location":{"id":"mag:2805465728","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1806.01946.pdf","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/1806.01946.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010465328","display_name":"Dzmitry Bahdanau","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dzmitry Bahdanau","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010396788","display_name":"Felix Hill","orcid":"https://orcid.org/0000-0002-6712-1718","observed_orcids":["https://orcid.org/0000-0002-6712-1718"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Felix Hill","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-6712-1718","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090592321","display_name":"Jan Leike","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jan Leike","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006947993","display_name":"Edward Hughes","orcid":"https://orcid.org/0000-0002-2434-2334","observed_orcids":["https://orcid.org/0000-0002-2434-2334"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Edward Hughes","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-2434-2334","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013834379","display_name":"Pushmeet Kohli","orcid":"https://orcid.org/0000-0002-7466-7997","observed_orcids":["https://orcid.org/0000-0002-7466-7997"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pushmeet Kohli","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-7466-7997","affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5023508792","display_name":"Edward Grefenstette","orcid":"https://orcid.org/0000-0003-1164-8809","observed_orcids":["https://orcid.org/0000-0003-1164-8809"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Edward Grefenstette","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-1164-8809","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":18,"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":0.8345000147819519,"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":0.8345000147819519,"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/T12031","display_name":"Speech and dialogue systems","score":0.01940000057220459,"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":0.015300000086426735,"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/language-teaching","display_name":"language teaching","score":0.5839999914169312},{"id":"https://openalex.org/keywords/instruction-following","display_name":"instruction following","score":0.6809999942779541},{"id":"https://openalex.org/keywords/reward-modeling","display_name":"reward modeling","score":0.49000000953674316},{"id":"https://openalex.org/keywords/language-models","display_name":"language models","score":0.4020000100135803}],"concepts":[{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.825186014175415},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5138497948646545},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.43099379539489746},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4209243059158325},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4064926505088806},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.3963722884654999}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:2805465728","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1806.01946.pdf","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}],"best_oa_location":{"id":"mag:2805465728","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1806.01946.pdf","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":22,"referenced_works":["https://openalex.org/W1525482321","https://openalex.org/W1933065844","https://openalex.org/W1962416794","https://openalex.org/W1999874108","https://openalex.org/W2005814556","https://openalex.org/W2061562262","https://openalex.org/W2098774185","https://openalex.org/W2111526438","https://openalex.org/W2116671302","https://openalex.org/W2118781169","https://openalex.org/W2156869222","https://openalex.org/W2189089430","https://openalex.org/W2236233024","https://openalex.org/W2260756217","https://openalex.org/W2416885651","https://openalex.org/W2434014514","https://openalex.org/W2551887912","https://openalex.org/W2611884151","https://openalex.org/W2620290674","https://openalex.org/W2626804490","https://openalex.org/W2734458248","https://openalex.org/W2760103357"],"related_works":["https://openalex.org/W7166806628","https://openalex.org/W7133211372","https://openalex.org/W2802590481","https://openalex.org/W2935695449","https://openalex.org/W3128141398","https://openalex.org/W7166824301","https://openalex.org/W7128138590","https://openalex.org/W4401042519","https://openalex.org/W7131843780","https://openalex.org/W3028694114"],"abstract_inverted_index":null,"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":8},{"year":2018,"cited_by_count":2}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2018-06-13T00:00:00"}
