{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/learning-through-dialogue-interactions-by","title":"Learning through Dialogue Interactions by Asking Questions","arxiv_id":"1612.04936","date":"2016-12-15","proceeding":null,"authors":["Jiwei Li","Alexander H. Miller","Sumit Chopra","Marc'Aurelio Ranzato","Jason Weston"],"abstract":"A good dialogue agent should have the ability to interact with users by both\nresponding to questions and by asking questions, and importantly to learn from\nboth types of interaction. In this work, we explore this direction by designing\na simulator and a set of synthetic tasks in the movie domain that allow such\ninteractions between a learner and a teacher. We investigate how a learner can\nbenefit from asking questions in both offline and online reinforcement learning\nsettings, and demonstrate that the learner improves when asking questions.\nFinally, real experiments with Mechanical Turk validate the approach. Our work\nrepresents a first step in developing such end-to-end learned interactive\ndialogue agents.","url_abs":"http://arxiv.org/abs/1612.04936v4","url_pdf":"http://arxiv.org/pdf/1612.04936v4.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"learning-through-dialogue-interactions-by","repo_url":"https://github.com/facebook/MemNN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"torch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"learning-through-dialogue-interactions-by","repo_url":"https://github.com/aus10powell/Automated-Health-Responses","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1612.04936","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}