Search · four archives
Search · four archives
23 papers · ranked by Valyu relevance
Daniel Bethell, Simos Gerasimou, Radu Călinescu, Calum Imrie
Ensuring the safe exploration of reinforcement learning (RL) agents is critical for deployment in real-world systems. Yet existing approaches struggle to strike the right balance: methods that tightly enforce safety often cripple task performance, while those that prioritise reward leave safety constraints frequently…
Dongjie Yu, Wenjun Zou, Yujie Yang, Haitong Ma + 3 more
'Jingliang Duan' 'Jianyu Chen'] Abstract—Safe reinforcement learning (RL) that solves constraint-satisfactory policies provides a promising way to the broader safety-critical applications of RL in real-world problems such as robotics. Among all safe RL approaches, model-based methods reduce training time violations…
Lukas Brunke, Melissa Greeff, Adam W. Hall, Zhaocong Yuan + 3 more
'Siqi Zhou' 'Jacopo Panerati' 'Angela P. Schoellig'] The last half-decade has seen a steep rise in the number of contributions on safe learning methods for real-world robotic deployments from both the control and reinforcement learning communities. This article provides a concise but holistic review of the recent…
Artur Eisele, Bernd Frauenknecht, Friedrich Solowjow, Sebastian Trimpe
Safety remains an open problem in reinforcement learning (RL), especially during training. While safety filters are promising to address safe exploration, they are generally poorly suited for high-dimensional systems with unknown dynamics. We propose Dyna-style Safety Augmented Reinforcement Learning (Dyna-SAuR), a…
Authors not listed
Realizing the promise of artificial intelligence (AI) to accelerate scientific progress and deliver technological impact depends on how effectively AI can be integrated into real-world decision- making processes. As Peter Norvig states, “Somewhat remarkably, almost all AI research until very recently has assumed that…
Kai–Chieh Hsu, Haimin Hu, Jaime Fernández Fisac
Recent years have seen significant progress in the realm of robot autonomy, accompanied by the expanding reach of robotic technologies. However, the emergence of new deployment domains brings unprecedented challenges in ensuring safe operation of these systems, which remains as crucial as ever. While traditional…
Heba G. Mohamed, Muhammad Nasir Khan, Fawad Naseer, Muhammad Tahir + 1 more
Introduction Telepresence robots (TPRs) must co-navigate with humans in constrained hospital environments, where safety depends on anticipating rather than merely reacting to human motion. Existing approaches rarely integrate short-horizon human-motion forecasting with safety-constrained control, which reduces…
Camilla Kao, Russell Furr
Conveying safety information to researchers is challenging. A list of rules and best practices often is not remembered thoroughly even by individuals who want to remember everything. Researchers in science thinking according to principles: mathematical, physical, and chemical laws; biological paradigms. They use…
Camilla Kao, Russell Furr
Conveying safety information to researchers is challenging. A list of rules and best practices often is not remembered thoroughly even by individuals who want to remember everything. Researchers in science thinking according to principles: mathematical, physical, and chemical laws; biological paradigms. They use…
Toby Wise, Raymond J Dolan
Aversive learning processes are a candidate source of dysfunction in psychiatric disorders. Here symptom expression in a range of conditions is linked to altered threat perception, manifesting particularly in uncertain environments. How precise computational mechanisms that support aversive learning, and uncertainty…
Pranav Mahajan, Shuangyi Tong, Sang Wan Lee, Ben Seymour
The safety-efficiency dilemma describes the problem of maintaining safety during efficient exploration, and is a special case of the exploration-exploitation dilemma in the face of potentially catastrophic dangers. Conventional exploration-exploitation solutions collapse punishment and reward into a single signal…
Song Qi, Logan Cross, Toby Wise, Xin Sui + 2 more
Humans, like many other animals, pre-empt danger by moving to locations that maximize their success at escaping future threats. We test the idea that spatial margin of safety (MOS) decisions, a form of pre-emptive avoidance, results in participants placing themselves closer to safer locations when facing more…
Chunbin Qin, Kaijun Jiang, Jishi Zhang, Tianzeng Zhu + 1 more
'Mohammad Reza Rahimi Tabar'] In this paper, the safe optimal control method for continuous-time (CT) nonlinear safety-critical systems with asymmetric input constraints and unmatched disturbances based on the adaptive dynamic programming (ADP) is investigated. Initially, a new non-quadratic form function is…
De-Tian Chu, Lin-Yuan Bai, Jia-Nuo Huang, Zhen-Long Fang + 4 more
'Peng Zhang' 'Wei Kang' 'Hai-Feng Ling' 'Wenling Li'] Ensuring safety in autonomous driving is crucial for effective motion planning and navigation. However, most end-to-end planning methodologies lack sufficient safety measures. This study tackles this issue by formulating the control optimization problem in…
Jun Ye, Xiaowei Zhao, Yougang Bian, Manjiang Hu + 1 more
This paper introduces a multi-step, off-policy adaptive dynamic programming approach, in both model-free and model-based variants, intending to solve optimal control problems under disturbances and safety constraints. To provide a more accurate estimation of the performance function in the policy evaluation step, we…
Subin Huh, Insoon Yang
— Emerging applications in robotic 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, we propose a model-free safety specification method that learns the maximal…
Camilla Kao, Che-I Kao
Recently we proposed that mission statements incorporating the concept of reducing uncertainty could provide a framework for learning the bread and depth of information that exists about health and safety. We briefly explained the definition of uncertainty in the context of health and safety, with the unifying…
Camilla Kao, Che-I Kao, Russell Furr
In science, safety can seem unfashionable. Satisfying safety requirements can slow the pace of research, make it cumbersome, or cost significant amounts of money. The logic of rules can seem unclear. Compliance can feel like a negative incentive. So besides the obvious benefit that safety keeps one safe, why do some…
Kim P. Wabersich, Melanie N. Zeilinger
The transfer of reinforcement learning (RL) techniques into real-world applications is challenged by safety requirements in the presence of physical limitations. Most RL methods, in particular the most popular algorithms, do not support explicit consideration of state and input constraints. In this paper, we address…
Mohammad Ali Labbaf Khaniki, Morteza Mirzaee, Elahe Moradi
Non-stationary environments pose significant challenges for reinforcement learning (RL), particularly in safety-critical applications like robotics and energy systems, where adaptability, stability, and robustness to uncertainty are essential. This paper introduces Lyapunov-Guided Distributional Reinforcement Learning…
Sarah M. Tashjian, Joseph Cussen, Wenning Deng, Bo Zhang + 1 more
Pivotal to self-preservation is the ability to identify when we are safe and when we are in danger. Previous studies have focused on safety estimations based on the features of external threats and do not consider how the brain integrates other key factors, including estimates about our ability to protect ourselves.…
Sampo Kuutti, Richard Bowden, Saber Fallah, Enrico Meli
The use of neural networks and reinforcement learning has become increasingly popular in autonomous vehicle control. However, the opaqueness of the resulting control policies presents a significant barrier to deploying neural network-based control in autonomous vehicles. In this paper, we present a reinforcement…
Authors not listed
Early prediction of drug-induced organ toxicity remains a major bottleneck in drug discovery and clinical pharmacotherapy. Most data-driven toxicity models behave as endpoint predictors: they output a label but provide limited transparency about why a compound is risky or which evidence channel dominated the decision.…