{"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/lipschitz-continuity-in-model-based","title":"Lipschitz Continuity in Model-based Reinforcement Learning","arxiv_id":"1804.07193","date":"2018-04-19","proceeding":"ICML 2018 7","authors":["Kavosh Asadi","Dipendra Misra","Michael L. Littman"],"abstract":"We examine the impact of learning Lipschitz continuous models in the context\nof model-based reinforcement learning. We provide a novel bound on multi-step\nprediction error of Lipschitz models where we quantify the error using the\nWasserstein metric. We go on to prove an error bound for the value-function\nestimate arising from Lipschitz models and show that the estimated value\nfunction is itself Lipschitz. We conclude with empirical results that show the\nbenefits of controlling the Lipschitz constant of neural-network models.","url_abs":"http://arxiv.org/abs/1804.07193v3","url_pdf":"http://arxiv.org/pdf/1804.07193v3.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":"lipschitz-continuity-in-model-based","repo_url":"https://github.com/kavosh8/Lip","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"model-based-reinforcement-learning","task_name":"Model-based Reinforcement Learning"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"model","task_name":"model"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1804.07193","atlas_url":"https://app.syntology.ai/?focus=1804.07193","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}