{"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-to-play-guess-who-and-inventing-a","title":"Learning to Play Guess Who? and Inventing a Grounded Language as a Consequence","arxiv_id":"1611.03218","date":"2016-11-10","proceeding":null,"authors":["Emilio Jorge","Mikael Kågebäck","Fredrik D. Johansson","Emil Gustavsson"],"abstract":"Acquiring your first language is an incredible feat and not easily\nduplicated. Learning to communicate using nothing but a few pictureless books,\na corpus, would likely be impossible even for humans. Nevertheless, this is the\ndominating approach in most natural language processing today. As an\nalternative, we propose the use of situated interactions between agents as a\ndriving force for communication, and the framework of Deep Recurrent Q-Networks\nfor evolving a shared language grounded in the provided environment. We task\nthe agents with interactive image search in the form of the game Guess Who?.\nThe images from the game provide a non trivial environment for the agents to\ndiscuss and a natural grounding for the concepts they decide to encode in their\ncommunication. Our experiments show that the agents learn not only to encode\nphysical concepts in their words, i.e. grounding, but also that the agents\nlearn to hold a multi-step dialogue remembering the state of the dialogue from\nstep to step.","url_abs":"http://arxiv.org/abs/1611.03218v4","url_pdf":"http://arxiv.org/pdf/1611.03218v4.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-to-play-guess-who-and-inventing-a","repo_url":"https://github.com/emiliojorge/Inventing-a-Grounded-Language","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"image-retrieval","task_name":"Image Retrieval"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1611.03218","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}