{"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/efficient-model-free-reinforcement-learning-1","title":"Efficient Model-free Reinforcement Learning in Metric Spaces","arxiv_id":"1905.00475","date":"2019-05-01","proceeding":null,"authors":["Zhao Song","Wen Sun"],"abstract":"Model-free Reinforcement Learning (RL) algorithms such as Q-learning\n[Watkins, Dayan 92] have been widely used in practice and can achieve human\nlevel performance in applications such as video games [Mnih et al. 15].\nRecently, equipped with the idea of optimism in the face of uncertainty,\nQ-learning algorithms [Jin, Allen-Zhu, Bubeck, Jordan 18] can be proven to be\nsample efficient for discrete tabular Markov Decision Processes (MDPs) which\nhave finite number of states and actions. In this work, we present an efficient\nmodel-free Q-learning based algorithm in MDPs with a natural metric on the\nstate-action space--hence extending efficient model-free Q-learning algorithms\nto continuous state-action space. Compared to previous model-based RL\nalgorithms for metric spaces [Kakade, Kearns, Langford 03], our algorithm does\nnot require access to a black-box planning oracle.","url_abs":"http://arxiv.org/abs/1905.00475v1","url_pdf":"http://arxiv.org/pdf/1905.00475v1.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":"efficient-model-free-reinforcement-learning-1","repo_url":"https://github.com/seanrsinclair/AdaptiveQLearning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"q-learning","task_name":"Q-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":[{"method_slug":"q-learning","method_name":"Q-Learning"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1905.00475","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}