{"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/being-curious-about-the-answers-to-questions","title":"Being curious about the answers to questions: novelty search with learned attention","arxiv_id":"1806.00201","date":"2018-06-01","proceeding":null,"authors":["Nicholas Guttenberg","Martin Biehl","Nathaniel Virgo","Ryota Kanai"],"abstract":"We investigate the use of attentional neural network layers in order to learn\na `behavior characterization' which can be used to drive novelty search and\ncuriosity-based policies. The space is structured towards answering a\nparticular distribution of questions, which are used in a supervised way to\ntrain the attentional neural network. We find that in a 2d exploration task,\nthe structure of the space successfully encodes local sensory-motor\ncontingencies such that even a greedy local `do the most novel action' policy\nwith no reinforcement learning or evolution can explore the space quickly. We\nalso apply this to a high/low number guessing game task, and find that guessing\naccording to the learned attention profile performs active inference and can\ndiscover the correct number more quickly than an exact but passive approach.","url_abs":"http://arxiv.org/abs/1806.00201v1","url_pdf":"http://arxiv.org/pdf/1806.00201v1.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":"being-curious-about-the-answers-to-questions","repo_url":"https://github.com/arayabrain/QuestionDrivenNovelty","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}