{"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/generalization-and-exploration-via-randomized","title":"Generalization and Exploration via Randomized Value Functions","arxiv_id":"1402.0635","date":"2014-02-04","proceeding":null,"authors":["Ian Osband","Benjamin Van Roy","Zheng Wen"],"abstract":"We propose randomized least-squares value iteration (RLSVI) -- a new\nreinforcement learning algorithm designed to explore and generalize efficiently\nvia linearly parameterized value functions. We explain why versions of\nleast-squares value iteration that use Boltzmann or epsilon-greedy exploration\ncan be highly inefficient, and we present computational results that\ndemonstrate dramatic efficiency gains enjoyed by RLSVI. Further, we establish\nan upper bound on the expected regret of RLSVI that demonstrates\nnear-optimality in a tabula rasa learning context. More broadly, our results\nsuggest that randomized value functions offer a promising approach to tackling\na critical challenge in reinforcement learning: synthesizing efficient\nexploration and effective generalization.","url_abs":"http://arxiv.org/abs/1402.0635v3","url_pdf":"http://arxiv.org/pdf/1402.0635v3.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":"generalization-and-exploration-via-randomized","repo_url":"https://github.com/qdevpsi3/randomized-value-iteration","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok","spdx":"GPL-3.0"}}],"tasks":[{"task_slug":"efficient-exploration","task_name":"Efficient Exploration"},{"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=1402.0635","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}