English
Related papers

Related papers: Your Policy Regularizer is Secretly an Adversary

200 papers

Neural networks are vulnerable to adversarial examples, i.e. inputs that are imperceptibly perturbed from natural data and yet incorrectly classified by the network. Adversarial training, a heuristic form of robust optimization that…

Machine Learning · Computer Science 2019-11-12 Ruiqi Gao , Tianle Cai , Haochuan Li , Liwei Wang , Cho-Jui Hsieh , Jason D. Lee

Adversarial training has emerged as a key technique to enhance model robustness against adversarial input perturbations. Many of the existing methods rely on computationally expensive min-max problems that limit their application in…

Machine Learning · Statistics 2025-10-27 Antônio H. Ribeiro , David Vävinggren , Dave Zachariah , Thomas B. Schön , Francis Bach

Owing to security implications of adversarial vulnerability, adversarial robustness of deep metric learning models has to be improved. In order to avoid model collapse due to excessively hard examples, the existing defenses dismiss the…

Machine Learning · Computer Science 2022-03-04 Mo Zhou , Vishal M. Patel

Neural networks are vulnerable to adversarial examples and researchers have proposed many heuristic attack and defense mechanisms. We address this problem through the principled lens of distributionally robust optimization, which guarantees…

Machine Learning · Statistics 2020-05-04 Aman Sinha , Hongseok Namkoong , Riccardo Volpi , John Duchi

Recent developments have established the vulnerability of deep Reinforcement Learning (RL) to policy manipulation attacks via adversarial perturbations. In this paper, we investigate the robustness and resilience of deep RL to training-time…

Artificial Intelligence · Computer Science 2017-12-29 Vahid Behzadan , Arslan Munir

We investigate an entropy-regularized reinforcement learning (RL) approach to optimal stopping problems motivated by real option models. Classical stopping rules are strict and non-randomized, limiting natural exploration in RL settings. To…

Optimization and Control · Mathematics 2026-02-18 Jodi Dianetti , Giorgio Ferrari , Renyuan Xu

Entropy Regularisation is a widely adopted technique that enhances policy optimisation performance and stability. A notable form of entropy regularisation is augmenting the objective with an entropy term, thereby simultaneously optimising…

Machine Learning · Computer Science 2024-07-26 Jean Seong Bjorn Choe , Jong-Kook Kim

Adversarial training is a widely-applied approach to training deep neural networks to be robust against adversarial perturbation. However, although adversarial training has achieved empirical success in practice, it still remains unclear…

Machine Learning · Computer Science 2025-02-10 Binghui Li , Yuanzhi Li

In light of the burgeoning success of reinforcement learning (RL) in diverse real-world applications, considerable focus has been directed towards ensuring RL policies are robust to adversarial attacks during test time. Current approaches…

Machine Learning · Computer Science 2024-02-21 Xiangyu Liu , Chenghao Deng , Yanchao Sun , Yongyuan Liang , Furong Huang

Reinforcement learning (RL) has achieved remarkable success in a wide range of control and decision-making tasks. However, RL agents often exhibit unstable or degraded performance when deployed in environments subject to unexpected external…

Machine Learning · Computer Science 2026-03-13 Taeho Lee , Donghwan Lee

In recent years, neural networks have demonstrated outstanding effectiveness in a large amount of applications.However, recent works have shown that neural networks are susceptible to adversarial examples, indicating possible flaws…

Machine Learning · Computer Science 2018-06-08 Fuxun Yu , Zirui Xu , Yanzhi Wang , Chenchen Liu , Xiang Chen

Deep learning models are intrinsically sensitive to distribution shifts in the input data. In particular, small, barely perceivable perturbations to the input data can force models to make wrong predictions with high confidence. An common…

Computer Vision and Pattern Recognition · Computer Science 2022-10-26 Paul Gavrikov , Janis Keuper

Entropy regularization is known to improve exploration in sequential decision-making problems. We show that this same mechanism can also lead to nearly unbiased and lower-variance estimates of the mean reward in the optimize-and-estimate…

Machine Learning · Computer Science 2022-08-26 Ben Chugg , Peter Henderson , Jacob Goldin , Daniel E. Ho

Adversarial attacks are widely used to identify model vulnerabilities; however, their validity as proxies for robustness to random perturbations remains debated. We ask whether an adversarial example provides a representative estimate of…

Machine Learning · Computer Science 2026-01-27 Giulio Rossolini

The problem of adversarial examples has shown that modern Neural Network (NN) models could be rather fragile. Among the more established techniques to solve the problem, one is to require the model to be {\it $\epsilon$-adversarially…

Machine Learning · Computer Science 2020-11-17 Yuxin Wen , Shuai Li , Kui Jia

While $\mathcal{H}_\infty$ methods can introduce robustness against worst-case perturbations, their nominal performance under conventional stochastic disturbances is often drastically reduced. Though this fundamental tradeoff between…

Systems and Control · Electrical Eng. & Systems 2022-03-22 Bruce D. Lee , Thomas T. C. K. Zhang , Hamed Hassani , Nikolai Matni

An optimal feedback controller for a given Markov decision process (MDP) can in principle be synthesized by value or policy iteration. However, if the system dynamics and the reward function are unknown, a learning agent must discover an…

Machine Learning · Computer Science 2019-07-19 Boris Belousov , Jan Peters

Autonomous systems are increasingly expected to operate in the presence of adversaries, though adversaries may infer sensitive information simply by observing a system. Therefore, present a deceptive sequential decision-making framework…

It is commonly believed that optimizing the reverse KL divergence results in "mode seeking", while optimizing forward KL results in "mass covering", with the latter being preferred if the goal is to sample from multiple diverse modes. We…

Machine Learning · Computer Science 2025-10-24 Anthony GX-Chen , Jatin Prakash , Jeff Guo , Rob Fergus , Rajesh Ranganath

Dealing with high variance is a significant challenge in model-free reinforcement learning (RL). Existing methods are unreliable, exhibiting high variance in performance from run to run using different initializations/seeds. Focusing on…

Machine Learning · Computer Science 2019-05-15 Richard Cheng , Abhinav Verma , Gabor Orosz , Swarat Chaudhuri , Yisong Yue , Joel W. Burdick