{"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/imap-intrinsically-motivated-adversarial","title":"Toward Evaluating Robustness of Reinforcement Learning with Adversarial Policy","arxiv_id":"2305.02605","date":"2023-05-04","proceeding":null,"authors":["Xiang Zheng","Xingjun Ma","Shengjie Wang","Xinyu Wang","Chao Shen","Cong Wang"],"abstract":"Reinforcement learning agents are susceptible to evasion attacks during deployment. In single-agent environments, these attacks can occur through imperceptible perturbations injected into the inputs of the victim policy network. In multi-agent environments, an attacker can manipulate an adversarial opponent to influence the victim policy's observations indirectly. While adversarial policies offer a promising technique to craft such attacks, current methods are either sample-inefficient due to poor exploration strategies or require extra surrogate model training under the black-box assumption. To address these challenges, in this paper, we propose Intrinsically Motivated Adversarial Policy (IMAP) for efficient black-box adversarial policy learning in both single- and multi-agent environments. We formulate four types of adversarial intrinsic regularizers -- maximizing the adversarial state coverage, policy coverage, risk, or divergence -- to discover potential vulnerabilities of the victim policy in a principled way. We also present a novel bias-reduction method to balance the extrinsic objective and the adversarial intrinsic regularizers adaptively. Our experiments validate the effectiveness of the four types of adversarial intrinsic regularizers and the bias-reduction method in enhancing black-box adversarial policy learning across a variety of environments. Our IMAP successfully evades two types of defense methods, adversarial training and robust regularizer, decreasing the performance of the state-of-the-art robust WocaR-PPO agents by 34\\%-54\\% across four single-agent tasks. IMAP also achieves a state-of-the-art attacking success rate of 83.91\\% in the multi-agent game YouShallNotPass. Our code is available at \\url{https://github.com/x-zheng16/IMAP}.","url_abs":"https://arxiv.org/abs/2305.02605v3","url_pdf":"https://arxiv.org/pdf/2305.02605v3.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":"imap-intrinsically-motivated-adversarial","repo_url":"https://github.com/x-zheng16/imap","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"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=2305.02605","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}