{"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/deep-dyna-q-integrating-planning-for-task","title":"Deep Dyna-Q: Integrating Planning for Task-Completion Dialogue Policy Learning","arxiv_id":"1801.06176","date":"2018-01-18","proceeding":"ACL 2018 7","authors":["Baolin Peng","Xiujun Li","Jianfeng Gao","Jingjing Liu","Kam-Fai Wong","Shang-Yu Su"],"abstract":"Training a task-completion dialogue agent via reinforcement learning (RL) is\ncostly because it requires many interactions with real users. One common\nalternative is to use a user simulator. However, a user simulator usually lacks\nthe language complexity of human interlocutors and the biases in its design may\ntend to degrade the agent. To address these issues, we present Deep Dyna-Q,\nwhich to our knowledge is the first deep RL framework that integrates planning\nfor task-completion dialogue policy learning. We incorporate into the dialogue\nagent a model of the environment, referred to as the world model, to mimic real\nuser response and generate simulated experience. During dialogue policy\nlearning, the world model is constantly updated with real user experience to\napproach real user behavior, and in turn, the dialogue agent is optimized using\nboth real experience and simulated experience. The effectiveness of our\napproach is demonstrated on a movie-ticket booking task in both simulated and\nhuman-in-the-loop settings.","url_abs":"http://arxiv.org/abs/1801.06176v3","url_pdf":"http://arxiv.org/pdf/1801.06176v3.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":"deep-dyna-q-integrating-planning-for-task","repo_url":"https://github.com/MiuLab/DDQ","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"deep-dyna-q-integrating-planning-for-task","repo_url":"https://github.com/para-zhou/RL_DDQ","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"deep-dyna-q-integrating-planning-for-task","repo_url":"https://github.com/sujoung/debuggedDDQ","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"task-completion-dialogue-policy-learning","task_name":"Task-Completion Dialogue Policy Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1801.06176","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}