中文
相关论文

相关论文: Mitigation of Adversarial Policy Imitation via Con…

200 篇论文

Recent studies have shown that deep reinforcement learning (DRL) policies are vulnerable to adversarial attacks, which raise concerns about applications of DRL to safety-critical systems. In this work, we adopt a principled way and study…

机器学习 · 计算机科学 2022-05-17 Chao Wang

This paper investigates a class of attacks targeting the confidentiality aspect of security in Deep Reinforcement Learning (DRL) policies. Recent research have established the vulnerability of supervised machine learning models (e.g.,…

机器学习 · 计算机科学 2019-06-05 Vahid Behzadan , William Hsu

Reinforcement Learning (RL) has achieved remarkable success in sequential decision tasks. However, recent studies have revealed the vulnerability of RL policies to different perturbations, raising concerns about their effectiveness and…

机器学习 · 计算机科学 2025-07-08 Buqing Nie , Yangqing Fu , Jingtian Ji , Yue Gao

Deep reinforcement learning (DRL) policies have been shown to be deceived by perturbations (e.g., random noise or intensional adversarial attacks) on state observations that appear at test time but are unknown during training. To increase…

机器学习 · 计算机科学 2020-12-25 Xinghua Qu , Yew-Soon Ong , Abhishek Gupta , Zhu Sun

Deep reinforcement learning (DRL) is vulnerable to adversarial perturbations. Adversaries can mislead the policies of DRL agents by perturbing the state of the environment observed by the agents. Existing attacks are feasible in principle,…

机器学习 · 计算机科学 2022-09-26 Buse G. A. Tekgul , Shelly Wang , Samuel Marchal , N. Asokan

Although well-established in general reinforcement learning (RL), value-based methods are rarely explored in constrained RL (CRL) for their incapability of finding policies that can randomize among multiple actions. To apply value-based…

机器学习 · 计算机科学 2022-06-28 Tianchi Cai , Wenpeng Zhang , Lihong Gu , Xiaodong Zeng , Jinjie Gu

Offline reinforcement learning (RL) aims to optimize a policy using collected data without online interactions. Model-based approaches are particularly appealing for addressing offline RL challenges because of their capability to mitigate…

Deep Reinforcement Learning (DRL) suffers from uncertainties and inaccuracies in the observation signal in realworld applications. Adversarial attack is an effective method for evaluating the robustness of DRL agents. However, existing…

机器学习 · 计算机科学 2025-01-09 Tianyang Duan , Zongyuan Zhang , Zheng Lin , Yue Gao , Ling Xiong , Yong Cui , Hongbin Liang , Xianhao Chen , Heming Cui , Dong Huang

Deep reinforcement learning (DRL) algorithms can suffer from modeling errors between the simulation and the real world. Many studies use adversarial learning to generate perturbation during training process to model the discrepancy and…

机器学习 · 计算机科学 2024-05-21 Qianmei Liu , Yufei Kuang , Jie Wang

The policy represented by the deep neural network can overfit the spurious features in observations, which hamper a reinforcement learning agent from learning effective policy. This issue becomes severe in high-dimensional state, where the…

机器学习 · 计算机科学 2023-05-01 Md Masudur Rahman , Yexiang Xue

Conservative Policy Iteration (CPI) is a founding algorithm of Approximate Dynamic Programming (ADP). Its core principle is to stabilize greediness through stochastic mixtures of consecutive policies. It comes with strong theoretical…

机器学习 · 计算机科学 2020-01-07 Nino Vieillard , Olivier Pietquin , Matthieu Geist

Deep reinforcement learning (DRL) has emerged as a promising paradigm for autonomous driving. However, despite their advanced capabilities, DRL-based policies remain highly vulnerable to adversarial attacks, posing serious safety risks in…

机器学习 · 计算机科学 2025-06-24 Junchao Fan , Xuyang Lei , Xiaolin Chang

Imitation learning can reproduce policies by observing experts, which poses a problem regarding policy privacy. Policies, such as human, or policies on deployed robots, can all be cloned without consent from the owners. How can we protect…

机器学习 · 计算机科学 2020-08-04 Albert Zhan , Stas Tiomkin , Pieter Abbeel

This study investigates behavior-targeted attacks on reinforcement learning and their countermeasures. Behavior-targeted attacks aim to manipulate the victim's behavior as desired by the adversary through adversarial interventions in state…

机器学习 · 计算机科学 2026-02-18 Shojiro Yamabe , Kazuto Fukuchi , Jun Sakuma

Deep Reinforcement Learning (DRL) has become an appealing solution to algorithmic trading such as high frequency trading of stocks and cyptocurrencies. However, DRL have been shown to be susceptible to adversarial attacks. It follows that…

机器学习 · 计算机科学 2020-10-24 Yaser Faghan , Nancirose Piazza , Vahid Behzadan , Ali Fathi

Constrained reinforcement learning has achieved promising progress in safety-critical fields where both rewards and constraints are considered. However, constrained reinforcement learning methods face challenges in striking the right…

机器学习 · 计算机科学 2024-10-29 Jianmina Ma , Jingtian Ji , Yue Gao

Neural networks are known to be vulnerable to adversarial examples. Carefully chosen perturbations to real images, while imperceptible to humans, induce misclassification and threaten the reliability of deep learning systems in the wild. To…

Deep Reinforcement Learning (DRL) has been successfully applied in several research domains such as robot navigation and automated video game playing. However, these methods require excessive computation and interaction with the…

机器学习 · 计算机科学 2020-04-07 Ayberk Aydın , Elif Surer

Reinforcement learning (RL) has achieved remarkable success in fields like robotics and autonomous driving, but adversarial attacks designed to mislead RL systems remain challenging. Existing approaches often rely on modifying the…

机器学习 · 计算机科学 2025-07-25 Junyong Jiang , Buwei Tian , Chenxing Xu , Songze Li , Lu Dong

We consider a problem of learning the reward and policy from expert examples under unknown dynamics. Our proposed method builds on the framework of generative adversarial networks and introduces the empowerment-regularized maximum-entropy…

机器学习 · 计算机科学 2019-02-26 Ahmed H. Qureshi , Byron Boots , Michael C. Yip
‹ 上一页 1 2 3 10 下一页 ›