{"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/deal-or-no-deal-end-to-end-learning-for","title":"Deal or No Deal? End-to-End Learning for Negotiation Dialogues","arxiv_id":"1706.05125","date":"2017-06-16","proceeding":null,"authors":["Mike Lewis","Denis Yarats","Yann N. Dauphin","Devi Parikh","Dhruv Batra"],"abstract":"Much of human dialogue occurs in semi-cooperative settings, where agents with\ndifferent goals attempt to agree on common decisions. Negotiations require\ncomplex communication and reasoning skills, but success is easy to measure,\nmaking this an interesting task for AI. We gather a large dataset of\nhuman-human negotiations on a multi-issue bargaining task, where agents who\ncannot observe each other's reward functions must reach an agreement (or a\ndeal) via natural language dialogue. For the first time, we show it is possible\nto train end-to-end models for negotiation, which must learn both linguistic\nand reasoning skills with no annotated dialogue states. We also introduce\ndialogue rollouts, in which the model plans ahead by simulating possible\ncomplete continuations of the conversation, and find that this technique\ndramatically improves performance. Our code and dataset are publicly available\n(https://github.com/facebookresearch/end-to-end-negotiator).","url_abs":"http://arxiv.org/abs/1706.05125v1","url_pdf":"http://arxiv.org/pdf/1706.05125v1.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":"deal-or-no-deal-end-to-end-learning-for","repo_url":"https://github.com/facebookresearch/end-to-end-negotiator","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"deal-or-no-deal-end-to-end-learning-for","repo_url":"https://github.com/jinhaoduan/gtbench","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"deal-or-no-deal-end-to-end-learning-for","repo_url":"https://github.com/nickatomlin/lm-selfplay","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1706.05125","atlas_url":"https://app.syntology.ai/?focus=1706.05125","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}