Robust Deep Reinforcement Learning against Adversarial Perturbations on State Observations

19 March 2020

Papers citing "Robust Deep Reinforcement Learning against Adversarial Perturbations on State Observations"

47 / 147 papers shown

Title
Feasible Adversarial Robust Reinforcement Learning for Underspecified Environments JB Lanier Stephen Marcus McAleer Pierre Baldi Roy Fox 24 9 0 19 Jul 2022
Robust Reinforcement Learning in Continuous Control Tasks with Uncertainty Set Regularization Yuan Zhang Jianhong Wang Joschka Boedecker 38 3 0 05 Jul 2022
Certifiably Robust Policy Learning against Adversarial Communication in Multi-agent Systems Yanchao Sun Ruijie Zheng Parisa Hassanzadeh Yongyuan Liang S. Feizi Sumitra Ganesh Furong Huang AAML 33 10 0 21 Jun 2022
Robust Deep Reinforcement Learning through Bootstrapped Opportunistic Curriculum Junlin Wu Yevgeniy Vorobeychik 24 21 0 21 Jun 2022
A Search-Based Testing Approach for Deep Reinforcement Learning Agents Amirhossein Zolfagharian Manel Abdellatif Lionel C. Briand M. Bagherzadeh Ramesh S 47 27 0 15 Jun 2022
Defending Observation Attacks in Deep Reinforcement Learning via Detection and Denoising Zikang Xiong Joe Eappen He Zhu Suresh Jagannathan AAML 31 10 0 14 Jun 2022
Consistent Attack: Universal Adversarial Perturbation on Embodied Vision Navigation Chengyang Ying You Qiaoben Xinning Zhou Hang Su Wenbo Ding Jianyong Ai AAML 32 11 0 12 Jun 2022
Towards Safe Reinforcement Learning via Constraining Conditional Value-at-Risk Chengyang Ying Xinning Zhou Hang Su Dong Yan Ning Chen Jun Zhu 24 41 0 09 Jun 2022
RORL: Robust Offline Reinforcement Learning via Conservative Smoothing Rui Yang Chenjia Bai Xiaoteng Ma Zhaoran Wang Chongjie Zhang Lei Han OffRL 32 74 0 06 Jun 2022
On the Robustness of Safe Reinforcement Learning under Observational Perturbations Zuxin Liu Zijian Guo Zhepeng Cen Huan Zhang Jie Tan Bo-wen Li Ding Zhao OOD OffRL 48 35 0 29 May 2022
Trust-based Consensus in Multi-Agent Reinforcement Learning Systems Ho Long Fung Victor-Alexandru Darvariu Stephen Hailes Mirco Musolesi 37 5 0 25 May 2022
Adversarial joint attacks on legged robots Takuto Otomo Hiroshi Kera K. Kawamoto AAML 29 1 0 20 May 2022
Policy Distillation with Selective Input Gradient Regularization for Efficient Interpretability Jinwei Xing Takashi Nagata Xinyun Zou Emre Neftci J. Krichmar AAML 25 4 0 18 May 2022
RoMFAC: A robust mean-field actor-critic reinforcement learning against adversarial perturbations on states Ziyuan Zhou Guanjun Liu AAML 35 24 0 15 May 2022
Review of Metrics to Measure the Stability, Robustness and Resilience of Reinforcement Learning L. Pullum 24 2 0 22 Mar 2022
COPA: Certifying Robust Policies for Offline Reinforcement Learning against Poisoning Attacks Fan Wu Linyi Li Chejian Xu Huan Zhang B. Kailkhura K. Kenthapadi Ding Zhao Bo-wen Li AAML OffRL 32 34 0 16 Mar 2022
Reinforcement Learning for Linear Quadratic Control is Vulnerable Under Cost Manipulation Yunhan Huang Quanyan Zhu OffRL AAML 42 4 0 11 Mar 2022
Sound Adversarial Audio-Visual Navigation Yinfeng Yu Wenbing Huang Gang Hua Changan Chen Yikai Wang Xiaohong Liu AAML 24 29 0 22 Feb 2022
User-Oriented Robust Reinforcement Learning Haoyi You Beichen Yu Haiming Jin Zhaoxing Yang Jiahui Sun OffRL 32 0 0 15 Feb 2022
L2C2: Locally Lipschitz Continuous Constraint towards Stable and Smooth Reinforcement Learning Taisuke Kobayashi 26 15 0 15 Feb 2022
Robust Policy Learning over Multiple Uncertainty Sets Annie Xie Shagun Sodhani Chelsea Finn Joelle Pineau Amy Zhang OOD OffRL 30 18 0 14 Feb 2022
Learning Robust Policy against Disturbance in Transition Dynamics via State-Conservative Policy Optimization Yufei Kuang Miao Lu Jie Wang Qi Zhou Bin Li Houqiang Li 22 20 0 20 Dec 2021
Deep Reinforcement Learning Policies Learn Shared Adversarial Features Across MDPs Ezgi Korkmaz 27 25 0 16 Dec 2021
Sample Complexity of Robust Reinforcement Learning with a Generative Model Kishan Panaganti D. Kalathil 93 71 0 02 Dec 2021
Improving Robustness of Reinforcement Learning for Power System Control with Adversarial Training Alexander Pan Yongkyun Lee Huan Zhang Yize Chen Yuanyuan Shi AAML 25 17 0 18 Oct 2021
Recurrent Model-Free RL Can Be a Strong Baseline for Many POMDPs Tianwei Ni Benjamin Eysenbach Ruslan Salakhutdinov 26 103 0 11 Oct 2021
Boosting Fast Adversarial Training with Learnable Adversarial Initialization Xiaojun Jia Yong Zhang Baoyuan Wu Jue Wang Xiaochun Cao AAML 50 54 0 11 Oct 2021
Targeted Attack on Deep RL-based Autonomous Driving with Learned Visual Patterns Prasanth Buddareddygari Travis Zhang Yezhou Yang Yi Ren AAML 37 13 0 16 Sep 2021
Dependability Analysis of Deep Reinforcement Learning based Robotics and Autonomous Systems through Probabilistic Model Checking Yizhen Dong Xingyu Zhao Xiaowei Huang 35 6 0 14 Sep 2021
Investigating Vulnerabilities of Deep Neural Policies Ezgi Korkmaz AAML 24 33 0 30 Aug 2021
Mis-spoke or mis-lead: Achieving Robustness in Multi-Agent Communicative Reinforcement Learning Wanqi Xue Wei Qiu Bo An Zinovi Rabinovich S. Obraztsova C. Yeo AAML 45 35 0 09 Aug 2021
Advances in adversarial attacks and defenses in computer vision: A survey Naveed Akhtar Ajmal Mian Navid Kardan M. Shah AAML 38 236 0 01 Aug 2021
Learning Altruistic Behaviours in Reinforcement Learning without External Rewards Tim Franzmeyer Mateusz Malinowski João F. Henriques 11 8 0 20 Jul 2021
Adversarial for Good? How the Adversarial ML Community's Values Impede Socially Beneficial Uses of Attacks Kendra Albert Maggie K. Delano B. Kulynych Ramnath Kumar AAML 22 5 0 11 Jul 2021
Understanding Adversarial Attacks on Observations in Deep Reinforcement Learning You Qiaoben Chengyang Ying Xinning Zhou Hang Su Jun Zhu Bo Zhang AAML 33 15 0 30 Jun 2021
Scalable Safety-Critical Policy Evaluation with Accelerated Rare Event Sampling Mengdi Xu Peide Huang Fengpei Li Jiacheng Zhu Xuewei Qi K. Oguchi Zhiyuan Huang Henry Lam Ding Zhao 13 4 0 19 Jun 2021
CROP: Certifying Robust Policies for Reinforcement Learning through Functional Smoothing Fan Wu Linyi Li Zijian Huang Yevgeniy Vorobeychik Ding Zhao Bo-wen Li AAML OffRL 21 59 0 17 Jun 2021
Real-time Adversarial Perturbations against Deep Reinforcement Learning Policies: Attacks and Defenses Buse G. A. Tekgul Shelly Wang Samuel Marchal Nadarajah Asokan AAML OffRL 20 5 0 16 Jun 2021
Learning on Abstract Domains: A New Approach for Verifiable Guarantee in Reinforcement Learning Peng-yun Jin Min Zhang Jianwen Li Li Han Xuejun Wen OffRL 16 3 0 13 Jun 2021
Who Is the Strongest Enemy? Towards Optimal and Efficient Evasion Attacks in Deep RL Yanchao Sun Ruijie Zheng Yongyuan Liang Furong Huang AAML 11 63 0 09 Jun 2021
Beta-CROWN: Efficient Bound Propagation with Per-neuron Split Constraints for Complete and Incomplete Neural Network Robustness Verification Shiqi Wang Huan Zhang Kaidi Xu Xue Lin Suman Jana Cho-Jui Hsieh Zico Kolter 11 185 0 11 Mar 2021
Policy Teaching in Reinforcement Learning via Environment Poisoning Attacks Amin Rakhsha Goran Radanović R. Devidze Xiaojin Zhu Adish Singla AAML OffRL 30 29 0 21 Nov 2020
Vulnerability-Aware Poisoning Mechanism for Online RL with Unknown Dynamics Yanchao Sun Da Huo Furong Huang AAML OffRL OnRL 23 49 0 02 Sep 2020
Adversary Agnostic Robust Deep Reinforcement Learning Xinghua Qu Yew-Soon Ong Abhishek Gupta Zhu Sun AAML 8 5 0 14 Aug 2020
Robust Deep Reinforcement Learning through Adversarial Loss Tuomas P. Oikarinen Wang Zhang Alexandre Megretski Luca Daniel Tsui-Wei Weng AAML 46 94 0 05 Aug 2020
Challenges and Countermeasures for Adversarial Attacks on Deep Reinforcement Learning Inaam Ilahi Muhammad Usama Junaid Qadir M. Janjua Ala I. Al-Fuqaha D. Hoang Dusit Niyato AAML 61 132 0 27 Jan 2020
Adversarial Machine Learning at Scale Alexey Kurakin Ian Goodfellow Samy Bengio AAML 298 3,113 0 04 Nov 2016