English
Related papers

Related papers: When Critics Disagree: Adaptive Reward Poisoning A…

200 papers

Many currently deployed Reinforcement Learning agents work in an environment shared with humans, be them co-workers, users or clients. It is desirable that these agents adjust to people's preferences, learn faster thanks to their help, and…

Machine Learning · Computer Science 2018-08-14 Hélène Plisnier , Denis Steckelmacher , Tim Brys , Diederik M. Roijers , Ann Nowé

To improve policy robustness of deep reinforcement learning agents, a line of recent works focus on producing disturbances of the environment. Existing approaches of the literature to generate meaningful disturbances of the environment are…

Machine Learning · Computer Science 2022-10-04 Lucas Schott , Hatem Hajri , Sylvain Lamprier

We study reward poisoning attacks on online deep reinforcement learning (DRL), where the attacker is oblivious to the learning algorithm used by the agent and the dynamics of the environment. We demonstrate the intrinsic vulnerability of…

Machine Learning · Computer Science 2023-07-18 Yinglun Xu , Qi Zeng , Gagandeep Singh

Reinforcement learning from verifiable rewards (RLVR) produces strong reasoning models, yet they can fail catastrophically when the conditioning context is fallible (e.g., corrupted chain-of-thought, misleading partial solutions, or mild…

Active Reconfigurable Intelligent Surfaces (RIS) are a promising technology for 6G wireless networks. This paper investigates a novel hybrid deep reinforcement learning (DRL) framework for resource allocation in a multi-user uplink system…

Signal Processing · Electrical Eng. & Systems 2025-12-29 Mohamed Shalma , Engy Aly Maher , Ahmed El-Mahdy

Deep reinforcement learning (RL) has achieved remarkable success, yet its deployment in real-world scenarios is often limited by vulnerability to environmental uncertainties. Distributionally robust RL (DR-RL) algorithms have been proposed…

Machine Learning · Computer Science 2026-04-21 Mingxuan Cui , Duo Zhou , Yuxuan Han , Grani A. Hanasusanto , Qiong Wang , Huan Zhang , Zhengyuan Zhou

Reinforcement learning (RL) agents are vulnerable to adversarial disturbances, which can deteriorate task performance or compromise safety specifications. Existing methods either address safety requirements under the assumption of no…

Machine Learning · Computer Science 2023-09-14 Zeyang Li , Chuxiong Hu , Yunan Wang , Yujie Yang , Shengbo Eben Li

This paper investigates a futuristic spectrum sharing paradigm for heterogeneous wireless networks with imperfect channels. In the heterogeneous networks, multiple wireless networks adopt different medium access control (MAC) protocols to…

Networking and Internet Architecture · Computer Science 2020-03-26 Yiding Yu , Soung Chang Liew , Taotao Wang

Reinforcement learning (RL) has shown remarkable success in solving complex decision-making and control tasks. However, many model-free RL algorithms experience performance degradation due to inaccurate value estimation, particularly the…

Machine Learning · Computer Science 2025-08-07 Jingliang Duan , Wenxuan Wang , Liming Xiao , Jiaxin Gao , Shengbo Eben Li , Chang Liu , Ya-Qin Zhang , Bo Cheng , Keqiang Li

In the domain of continuous control, deep reinforcement learning (DRL) demonstrates promising results. However, the dependence of DRL on deep neural networks (DNNs) results in the demand for extensive data and increased computational cost.…

Machine Learning · Computer Science 2025-04-15 Shiron Thalagala , Pak Kin Wong , Xiaozheng Wang , Tianang Sun

We study the corruption-robustness of in-context reinforcement learning (ICRL), focusing on the Decision-Pretrained Transformer (DPT, Lee et al., 2023). To address the challenge of reward poisoning attacks targeting the DPT, we propose a…

Machine Learning · Computer Science 2025-09-30 Paulius Sasnauskas , Yiğit Yalın , Goran Radanović

Reconfigurable intelligent surface (RIS) technology enhances wireless communication performance, but it also introduces new vulnerabilities that can be exploited by adversaries. This paper investigates channel reciprocity attack (CRACK)…

Signal Processing · Electrical Eng. & Systems 2025-09-16 Haoyu Wang , Jiawei Hu , Jiaqi Xu , Ying Ju , A. Lee Swindlehurst

Deep reinforcement learning (DRL) has recently been used to perform efficient resource allocation in wireless communications. In this paper, the vulnerabilities of such DRL agents to adversarial attacks is studied. In particular, we…

Machine Learning · Computer Science 2021-05-13 Feng Wang , M. Cenk Gursoy , Senem Velipasalar

Adversarial inverse reinforcement learning (AIRL) stands as a cornerstone approach in imitation learning, yet it faces criticisms from prior studies. In this paper, we rethink AIRL and respond to these criticisms. Criticism 1 lies in…

Machine Learning · Computer Science 2024-10-29 Yangchun Zhang , Qiang Liu , Weiming Li , Yirui Zhou

Sequential recommender systems (SRSs) excel in capturing users' dynamic interests, thus playing a key role in various industrial applications. The popularity of SRSs has also driven emerging research on their security aspects, where data…

Information Retrieval · Computer Science 2025-04-10 Yuchuan Zhao , Tong Chen , Junliang Yu , Kai Zheng , Lizhen Cui , Hongzhi Yin

Recent deep neural networks based techniques, especially those equipped with the ability of self-adaptation in the system level such as deep reinforcement learning (DRL), are shown to possess many advantages of optimizing robot learning…

Machine Learning · Computer Science 2021-10-11 Chao-Han Huck Yang , Jun Qi , Pin-Yu Chen , Yi Ouyang , I-Te Danny Hung , Chin-Hui Lee , Xiaoli Ma

This paper considers a joint communication and sensing technique for enhancing situational awareness in practical battlefield scenarios. In particular, we propose an aerial reconfigurable intelligent surface (ARIS)-assisted integrated…

Systems and Control · Electrical Eng. & Systems 2025-02-04 Hyunsang Cho , Seonghoon Yoo , Bang Chul Jung , Joonhyuk Kang

In this work, we explore UAV-assisted reconfigurable intelligent surface (RIS) technology to enhance downlink communications in wireless networks. By integrating RIS on both UAVs and ground infrastructure, we aim to boost network coverage,…

Signal Processing · Electrical Eng. & Systems 2024-11-19 Abuzar B. M. Adam , Elhadj Moustapha Diallo , Mohammed A. M. Elhassan

Balancing reward and safety in constrained reinforcement learning remains challenging due to poor generalization from sharp value minima and inadequate handling of heavy-tailed risk distribution. We introduce Safe Langevin Soft Actor-Critic…

Machine Learning · Computer Science 2026-02-03 Mahesh Keswani , Samyak Jain , Raunak P. Bhattacharyya

Deep reinforcement learning (RL) policies are known to be vulnerable to adversarial perturbations to their observations, similar to adversarial examples for classifiers. However, an attacker is not usually able to directly modify another…

Machine Learning · Computer Science 2021-01-19 Adam Gleave , Michael Dennis , Cody Wild , Neel Kant , Sergey Levine , Stuart Russell