中文
相关论文

相关论文: Safe Reinforcement Learning Using Black-Box Reacha…

200 篇论文

Implementing intelligent control of robots is a difficult task, especially when dealing with complex black-box systems, because of the lack of visibility and understanding of how these robots work internally. This paper proposes an…

人工智能 · 计算机科学 2023-11-14 Xubo Yang , Jian Gao , Ting Wang , Yaozhen He

Deep reinforcement learning (DRL) has achieved groundbreaking successes in a wide variety of robotic applications. A natural consequence is the adoption of this paradigm for safety-critical tasks, where human safety and expensive hardware…

机器人学 · 计算机科学 2022-06-22 Davide Corsi , Raz Yerushalmi , Guy Amir , Alessandro Farinelli , David Harel , Guy Katz

Manipulating the interaction trajectories between the intelligent agent and the environment can control the agent's training and behavior, exposing the potential vulnerabilities of reinforcement learning (RL). For example, in Cyber-Physical…

机器学习 · 计算机科学 2024-11-21 Zhi Luo , Xiyuan Yang , Pan Zhou , Di Wang

Groundbreaking successes have been achieved by Deep Reinforcement Learning (DRL) in solving practical decision-making problems. Robotics, in particular, can involve high-cost hardware and human interactions. Hence, scrupulous evaluations of…

人工智能 · 计算机科学 2020-10-20 Davide Corsi , Enrico Marchesini , Alessandro Farinelli

We examine five setups where an agent (or two agents) seeks to explore unknown environment without any prior information. Although seemingly very different, all of them can be formalized as Reinforcement Learning (RL) problems in hyperbolic…

机器学习 · 计算机科学 2024-10-15 Vladimir Jaćimović , Zinaid Kapić , Aladin Crnkić

Complex high-dimensional spaces with high Degree-of-Freedom and complicated action spaces, such as humanoid robots equipped with dexterous hands, pose significant challenges for reinforcement learning (RL) algorithms, which need to wisely…

机器人学 · 计算机科学 2025-02-25 Zifeng Zhuang , Diyuan Shi , Runze Suo , Xiao He , Hongyin Zhang , Ting Wang , Shangke Lyu , Donglin Wang

It is quite challenging to ensure the safety of reinforcement learning (RL) agents in an unknown and stochastic environment under hard constraints that require the system state not to reach certain specified unsafe regions. Many popular…

系统与控制 · 电气工程与系统科学 2023-06-14 Yixuan Wang , Simon Sinong Zhan , Ruochen Jiao , Zhilu Wang , Wanxin Jin , Zhuoran Yang , Zhaoran Wang , Chao Huang , Qi Zhu

Current state-of-the-art crowd navigation approaches are mainly deep reinforcement learning (DRL)-based. However, DRL-based methods suffer from the issues of generalization and scalability. To overcome these challenges, we propose a method…

机器人学 · 计算机科学 2023-09-26 Hafiq Anas , Ong Wee Hong , Owais Ahmed Malik

Reinforcement learning (RL) agents need to explore their environment to learn optimal behaviors and achieve maximum rewards. However, exploration can be risky when training RL directly on real systems, while simulation-based training…

机器人学 · 计算机科学 2024-10-10 Dvij Kalaria , Qin Lin , John M. Dolan

In this paper, we develop a method for learning a control policy guaranteed to satisfy an affine state constraint of high relative degree in closed loop with a black-box system. Previous reinforcement learning (RL) approaches to satisfy…

系统与控制 · 电气工程与系统科学 2024-07-31 Jean-Baptiste Bouvier , Kartik Nagpal , Negar Mehr

Reinforcement Learning (RL) is a machine learning framework for artificially intelligent systems to solve a variety of complex problems. Recent years has seen a surge of successes solving challenging games and smaller domain problems,…

机器人学 · 计算机科学 2020-01-28 Florian Richter , Ryan K. Orosco , Michael C. Yip

This paper introduces the reinforcement learning backup shield (RLBUS), an algorithm that guarantees safe exploration in reinforcement learning (RL) by incorporating backup control barrier functions (BCBFs). RLBUS constructs an implicit…

系统与控制 · 电气工程与系统科学 2024-12-10 Pedram Rabiee , Amirsaeid Safari

While reinforcement learning (RL) has the potential to enable robots to autonomously acquire a wide range of skills, in practice, RL usually requires manual, per-task engineering of reward functions, especially in real world settings where…

机器人学 · 计算机科学 2019-02-15 Tianhe Yu , Gleb Shevchuk , Dorsa Sadigh , Chelsea Finn

Some of the threats in the dynamic environment include the unpredictability of the motion of objects and interferences to the robotic grasp. In such conditions the traditional supervised and reinforcement learning approaches are ill suited…

机器人学 · 计算机科学 2024-10-18 Ankit Shaw

We present a generic Reinforcement Learning (RL) framework optimized for crafting adversarial attacks on different model types spanning from ECG signal analysis (1D), image classification (2D), and video classification (3D). The framework…

The emerging field of Reinforcement Learning (RL) has led to impressive results in varied domains like strategy games, robotics, etc. This handout aims to give a simple introduction to RL from control perspective and discuss three possible…

机器学习 · 计算机科学 2021-03-09 Farnaz Adib Yaghmaie , Lennart Ljung

Reinforcement learning (RL) agents with pre-specified reward functions cannot provide guaranteed safety across variety of circumstances that an uncertain system might encounter. To guarantee performance while assuring satisfaction of safety…

人工智能 · 计算机科学 2021-04-20 Aquib Mustafa , Majid Mazouchi , Subramanya Nageshrao , Hamidreza Modares

The large-scale integration of intermittent renewable energy resources introduces increased uncertainty and volatility to the supply side of power systems, thereby complicating system operation and control. Recently, data-driven approaches,…

系统与控制 · 电气工程与系统科学 2024-07-02 Peipei Yu , Zhenyi Wang , Hongcai Zhang , Yonghua Song

Emerging applications in robotics and autonomous systems, such as autonomous driving and robotic surgery, often involve critical safety constraints that must be satisfied even when information about system models is limited. In this regard,…

机器人学 · 计算机科学 2020-02-25 Subin Huh , Insoon Yang

Generating safe motion plans in real-time is a key requirement for deploying robot manipulators to assist humans in collaborative settings. In particular, robots must satisfy strict safety requirements to avoid self-damage or harming nearby…

机器人学 · 计算机科学 2023-02-16 Jonathan Michaux , Qingyi Chen , Yongseok Kwon , Ram Vasudevan