{"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/discovering-general-purpose-active-learning","title":"Discovering General-Purpose Active Learning Strategies","arxiv_id":"1810.04114","date":"2018-10-09","proceeding":"ICLR 2019 5","authors":["Ksenia Konyushkova","Raphael Sznitman","Pascal Fua"],"abstract":"We propose a general-purpose approach to discovering active learning (AL)\nstrategies from data. These strategies are transferable from one domain to\nanother and can be used in conjunction with many machine learning models. To\nthis end, we formalize the annotation process as a Markov decision process,\ndesign universal state and action spaces and introduce a new reward function\nthat precisely model the AL objective of minimizing the annotation cost. We\nseek to find an optimal (non-myopic) AL strategy using reinforcement learning.\nWe evaluate the learned strategies on multiple unrelated domains and show that\nthey consistently outperform state-of-the-art baselines.","url_abs":"http://arxiv.org/abs/1810.04114v2","url_pdf":"http://arxiv.org/pdf/1810.04114v2.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":"discovering-general-purpose-active-learning","repo_url":"https://github.com/ksenia-konyushkova/LAL-RL","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"active-learning","task_name":"Active Learning"},{"task_slug":"machine-learning","task_name":"BIG-bench Machine Learning"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1810.04114","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}