{"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/emergent-communication-through-negotiation","title":"Emergent Communication through Negotiation","arxiv_id":"1804.03980","date":"2018-04-11","proceeding":"ICLR 2018 1","authors":["Kris Cao","Angeliki Lazaridou","Marc Lanctot","Joel Z. Leibo","Karl Tuyls","Stephen Clark"],"abstract":"Multi-agent reinforcement learning offers a way to study how communication\ncould emerge in communities of agents needing to solve specific problems. In\nthis paper, we study the emergence of communication in the negotiation\nenvironment, a semi-cooperative model of agent interaction. We introduce two\ncommunication protocols -- one grounded in the semantics of the game, and one\nwhich is \\textit{a priori} ungrounded and is a form of cheap talk. We show that\nself-interested agents can use the pre-grounded communication channel to\nnegotiate fairly, but are unable to effectively use the ungrounded channel.\nHowever, prosocial agents do learn to use cheap talk to find an optimal\nnegotiating strategy, suggesting that cooperation is necessary for language to\nemerge. We also study communication behaviour in a setting where one agent\ninteracts with agents in a community with different levels of prosociality and\nshow how agent identifiability can aid negotiation.","url_abs":"http://arxiv.org/abs/1804.03980v1","url_pdf":"http://arxiv.org/pdf/1804.03980v1.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":"emergent-communication-through-negotiation","repo_url":"https://github.com/longtermrisk/marltoolbox","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"multi-agent-reinforcement-learning","task_name":"Multi-agent Reinforcement Learning"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1804.03980","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}