{"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/world-discovery-models","title":"World Discovery Models","arxiv_id":"1902.07685","date":"2019-02-20","proceeding":null,"authors":["Mohammad Gheshlaghi Azar","Bilal Piot","Bernardo Avila Pires","Jean-bastien Grill","Florent Altché","Rémi Munos"],"abstract":"As humans we are driven by a strong desire for seeking novelty in our world.\nAlso upon observing a novel pattern we are capable of refining our\nunderstanding of the world based on the new information---humans can discover\ntheir world. The outstanding ability of the human mind for discovery has led to\nmany breakthroughs in science, art and technology. Here we investigate the\npossibility of building an agent capable of discovering its world using the\nmodern AI technology. In particular we introduce NDIGO, Neural Differential\nInformation Gain Optimisation, a self-supervised discovery model that aims at\nseeking new information to construct a global view of its world from partial\nand noisy observations. Our experiments on some controlled 2-D navigation tasks\nshow that NDIGO outperforms state-of-the-art information-seeking methods in\nterms of the quality of the learned representation. The improvement in\nperformance is particularly significant in the presence of white or structured\nnoise where other information-seeking methods follow the noise instead of\ndiscovering their world.","url_abs":"http://arxiv.org/abs/1902.07685v3","url_pdf":"http://arxiv.org/pdf/1902.07685v3.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":"world-discovery-models","repo_url":"https://github.com/subinlab/model_based_rl_paper","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1902.07685","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}