中文
相关论文

相关论文: SoK: The Pitfalls of Deep Reinforcement Learning f…

200 篇论文

Deep reinforcement learning has recently made significant progress in solving computer games and robotic control tasks. A known problem, though, is that policies overfit to the training environment and may not avoid rare, catastrophic…

机器学习 · 计算机科学 2019-04-02 Xinlei Pan , Daniel Seita , Yang Gao , John Canny

Deep reinforcement learning (RL) has brought many successes for autonomous robot navigation. However, there still exists important limitations that prevent real-world use of RL-based navigation systems. For example, most learning approaches…

机器人学 · 计算机科学 2023-06-28 Zifan Xu , Bo Liu , Xuesu Xiao , Anirudh Nair , Peter Stone

Ensuring strict safety guarantees is the paramount challenge for emerging 5G/6G wireless systems, particularly as they increasingly govern mission-critical applications ranging from autonomous UAV swarms to industrial automation. While deep…

信号处理 · 电气工程与系统科学 2026-04-21 Haoran Peng , Tong Wu , Hang Liu , Weijia Zheng , Ying-Jun Angela Zhang , Anna Scaglione

This paper investigates the threat of backdoors in Deep Reinforcement Learning (DRL) agent policies and proposes a novel method for their detection at runtime. Our study focuses on elusive in-distribution backdoor triggers. Such triggers…

机器学习 · 计算机科学 2024-07-23 Sanyam Vyas , Chris Hicks , Vasilios Mavroudis

Deep reinforcement learning (DRL) breaks through the bottlenecks of traditional reinforcement learning (RL) with the help of the perception capability of deep learning and has been widely applied in real-world problems.While model-free RL,…

机器学习 · 计算机科学 2022-11-28 Tingting Zhao , Ying Wang , Wei Sun , Yarui Chen , Gang Niub , Masashi Sugiyama

Radio frequency (RF) fingerprinting, which extracts unique hardware imperfections of radio devices, has emerged as a promising physical-layer device identification mechanism in zero trust architectures and beyond 5G networks. In particular,…

密码学与安全 · 计算机科学 2026-05-28 Xinyu Cao , Bimal Adhikari , Shangqing Zhao , Jingxian Wu , Yanjun Pan

Offline reinforcement learning proposes to learn policies from large collected datasets without interacting with the physical environment. These algorithms have made it possible to learn useful skills from data that can then be deployed in…

机器学习 · 计算机科学 2021-07-06 Samarth Sinha , Ajay Mandlekar , Animesh Garg

Reinforcement Learning (RL) or Deep Reinforcement Learning (DRL) is a powerful approach to solving Markov Decision Processes (MDPs) when the model of the environment is not known a priori. However, RL models are still faced with challenges…

系统与控制 · 电气工程与系统科学 2024-06-04 Kabirat Olayemi , Mien Van , Luke Maguire , Sean McLoone

Deep reinforcement learning (DRL) is poised to revolutionise the field of artificial intelligence (AI) by endowing autonomous systems with high levels of understanding of the real world. Currently, deep learning (DL) is enabling DRL to…

Deep reinforcement learning (DRL) has demonstrated remarkable performance in many continuous control tasks. However, a significant obstacle to the real-world application of DRL is the lack of safety guarantees. Although DRL agents can…

机器人学 · 计算机科学 2025-08-15 Weiye Zhao , Feihan Li , Changliu Liu

In Wireless Networked Control Systems (WNCSs), control and communication systems must be co-designed due to their strong interdependence. This paper presents a novel optimization theory-based safe deep reinforcement learning (DRL) framework…

信号处理 · 电气工程与系统科学 2025-07-14 Berire Gunes Reyhan , Sinem Coleri

The offline reinforcement learning (RL) setting (also known as full batch RL), where a policy is learned from a static dataset, is compelling as progress enables RL methods to take advantage of large, previously-collected datasets, much…

机器学习 · 计算机科学 2021-02-09 Justin Fu , Aviral Kumar , Ofir Nachum , George Tucker , Sergey Levine

In the rapidly changing healthcare landscape, the implementation of offline reinforcement learning (RL) in dynamic treatment regimes (DTRs) presents a mix of unprecedented opportunities and challenges. This position paper offers a critical…

机器学习 · 计算机科学 2024-06-05 Zhiyao Luo , Yangchen Pan , Peter Watkinson , Tingting Zhu

Reinforcement learning (RL) struggles to scale to large, combinatorial action spaces common in many real-world problems. This paper introduces a novel framework for training discrete diffusion models as highly effective policies in these…

机器学习 · 计算机科学 2026-05-21 Haitong Ma , Ofir Nabati , Aviv Rosenberg , Bo Dai , Oran Lang , Craig Boutilier , Na Li , Shie Mannor , Lior Shani , Guy Tenneholtz

Deep Reinforcement Learning (DRL) connects the classic Reinforcement Learning algorithms with Deep Neural Networks. A problem in DRL is that CNNs are black-boxes and it is hard to understand the decision-making process of agents. In order…

机器学习 · 计算机科学 2020-12-03 Matthias Rosynski , Frank Kirchner , Matias Valdenegro-Toro

Deep Reinforcement Learning (DRL) has become a popular method for solving control problems in power systems. Conventional DRL encourages the agent to explore various policies encoded in a neural network (NN) with the goal of maximizing the…

系统与控制 · 电气工程与系统科学 2024-10-28 Tong Wu , Anna Scaglione , Daniel Arnold

Cost functions are commonly employed in Safe Deep Reinforcement Learning (DRL). However, the cost is typically encoded as an indicator function due to the difficulty of quantifying the risk of policy decisions in the state space. Such an…

人工智能 · 计算机科学 2023-02-21 Enrico Marchesini , Luca Marzari , Alessandro Farinelli , Christopher Amato

Deep reinforcement learning (DRL) algorithms have achieved great success on sequential decision-making problems, yet is criticized for the lack of data-efficiency and explainability. Especially, explainability of subtasks is critical in…

人工智能 · 计算机科学 2020-05-20 Daoming Lyu

Combining data-driven applications with control systems plays a key role in recent Autonomous Car research. This thesis offers a structured review of the latest literature on Deep Reinforcement Learning (DRL) within the realm of autonomous…

机器人学 · 计算机科学 2024-04-02 Yiyang Chen , Chao Ji , Yunrui Cai , Tong Yan , Bo Su

In the past few years, Deep Reinforcement Learning (DRL) has become a valuable solution to automatically learn efficient resource management strategies in complex networks. In many scenarios, the learning task is performed in the Cloud,…

网络与互联网体系结构 · 计算机科学 2022-12-01 Seyyidahmed Lahmer , Federico Chiariotti , Andrea Zanella