{"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/robust-policy-gradient-against-strong-data","title":"Robust Policy Gradient against Strong Data Corruption","arxiv_id":"2102.05800","date":"2021-02-11","proceeding":null,"authors":["Xuezhou Zhang","Yiding Chen","Xiaojin Zhu","Wen Sun"],"abstract":"We study the problem of robust reinforcement learning under adversarial corruption on both rewards and transitions. Our attack model assumes an \\textit{adaptive} adversary who can arbitrarily corrupt the reward and transition at every step within an episode, for at most $\\epsilon$-fraction of the learning episodes. Our attack model is strictly stronger than those considered in prior works. Our first result shows that no algorithm can find a better than $O(\\epsilon)$-optimal policy under our attack model. Next, we show that surprisingly the natural policy gradient (NPG) method retains a natural robustness property if the reward corruption is bounded, and can find an $O(\\sqrt{\\epsilon})$-optimal policy. Consequently, we develop a Filtered Policy Gradient (FPG) algorithm that can tolerate even unbounded reward corruption and can find an $O(\\epsilon^{1/4})$-optimal policy. We emphasize that FPG is the first that can achieve a meaningful learning guarantee when a constant fraction of episodes are corrupted. Complimentary to the theoretical results, we show that a neural implementation of FPG achieves strong robust learning performance on the MuJoCo continuous control benchmarks.","url_abs":"https://arxiv.org/abs/2102.05800v3","url_pdf":"https://arxiv.org/pdf/2102.05800v3.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":"robust-policy-gradient-against-strong-data","repo_url":"https://github.com/zhangxz1123/FilteredPolicyGradient","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"continuous-control","task_name":"Continuous Control"},{"task_slug":"mujoco","task_name":"MuJoCo"},{"task_slug":"continuous-control","task_name":"continuous-control"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"fpg","method_name":"FPG"},{"method_slug":"relu","method_name":"ReLU"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2102.05800","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}