English
Related papers

Related papers: Safety-Critical Reinforcement Learning with Viabil…

200 papers

Identifying uncertainty and taking mitigating actions is crucial for safe and trustworthy reinforcement learning agents, especially when deployed in high-risk environments. In this paper, risk sensitivity is promoted in a model-based…

Machine Learning · Computer Science 2021-11-10 Stefan Radic Webster , Peter Flach

This paper aims to examine the potential of using the emerging deep reinforcement learning techniques in flight control. Instead of learning from scratch, we suggest to leverage domain knowledge available in learning to improve learning…

Artificial Intelligence · Computer Science 2024-10-30 Hyo-Sang Shin , Shaoming He , Antonios Tsourdos

As reinforcement learning (RL) deployments expand into safety-critical domains, existing evaluation methods fail to systematically identify hazards arising from the black-box nature of neural network enabled policies and distributional…

Shielding is widely used to enforce safety in reinforcement learning (RL), ensuring that an agent's actions remain compliant with formal specifications. Classical shielding approaches, however, are often static, in the sense that they…

Artificial Intelligence · Computer Science 2026-02-23 Tiberiu-Andrei Georgescu , Alexander W. Goodall , Dalal Alrajeh , Francesco Belardinelli , Sebastian Uchitel

Safely exploring an unknown dynamical system is critical to the deployment of reinforcement learning (RL) in physical systems where failures may have catastrophic consequences. In scenarios where one knows little about the dynamics, diverse…

Machine Learning · Computer Science 2017-12-01 Tyler Lu , Martin Zinkevich , Craig Boutilier , Binz Roy , Dale Schuurmans

The inability to naturally enforce safety in Reinforcement Learning (RL), with limited failures, is a core challenge impeding its use in real-world applications. One notion of safety of vast practical relevance is the ability to avoid…

Machine Learning · Computer Science 2024-01-24 Agustin Castellano , Hancheng Min , Juan Andrés Bazerque , Enrique Mallada

Goal-Conditioned Reinforcement Learning (GCRL) provides a versatile framework for developing unified controllers capable of handling wide ranges of tasks, exploring environments, and adapting behaviors. However, its reliance on…

Machine Learning · Computer Science 2025-02-20 Charly Pecqueux-Guézénec , Stéphane Doncieux , Nicolas Perrin-Gilbert

Long-horizon contact-rich tasks are challenging to learn with reinforcement learning, due to ineffective exploration of high-dimensional state spaces with sparse rewards. The learning process often gets stuck in local optimum and demands…

Robotics · Computer Science 2025-02-24 Xiaofeng Mao , Yucheng Xu , Zhaole Sun , Elle Miller , Daniel Layeghi , Michael Mistry

Reinforcement learning has demonstrated significant potential in the field of autonomous driving. However, it suffers from defects such as training instability and unsafe action outputs when faced with autonomous racing environments…

Robotics · Computer Science 2026-03-09 Bo Leng , Weiqi Zhang , Zhuoren Li , Lu Xiong , Guizhe Jin , Ran Yu , Chen Lv

Reinforcement learning algorithms discover policies that maximize reward, but do not necessarily guarantee safety during learning or execution phases. We introduce a new approach to learn optimal policies while enforcing properties…

Logic in Computer Science · Computer Science 2017-09-05 Mohammed Alshiekh , Roderick Bloem , Ruediger Ehlers , Bettina Könighofer , Scott Niekum , Ufuk Topcu

This paper proposes an on-policy reinforcement learning (RL) control algorithm that solves the optimal regulation problem for a class of uncertain continuous-time nonlinear systems under user-defined state constraints. We formulate the safe…

Systems and Control · Electrical Eng. & Systems 2022-09-20 Soutrik Bandyopadhyay , Shubhendu Bhasin

Imitation learning (IL) has shown great success in learning complex robot manipulation tasks. However, there remains a need for practical safety methods to justify widespread deployment. In particular, it is important to certify that a…

Ensuring safety in the sense of constraint satisfaction for learning-based control is a critical challenge, especially in the model-free case. While safety filters address this challenge in the model-based setting by modifying unsafe…

Systems and Control · Electrical Eng. & Systems 2026-01-15 Kanghui He , Shengling Shi , Ton van den Boom , Bart De Schutter

Safe exploration is a common problem in reinforcement learning (RL) that aims to prevent agents from making disastrous decisions while exploring their environment. A family of approaches to this problem assume domain knowledge in the form…

Artificial Intelligence · Computer Science 2022-08-24 Steven Carr , Nils Jansen , Sebastian Junges , Ufuk Topcu

We propose a novel adaptive reinforcement learning control approach for fault tolerant control of degrading systems that is not preceded by a fault detection and diagnosis step. Therefore, \textit{a priori} knowledge of faults that may…

Systems and Control · Electrical Eng. & Systems 2020-08-12 Ibrahim Ahmed , Marcos Quiñones-Grueiro , Gautam Biswas

This work developed a meta-learning approach that adapts the control policy on the fly to different changing conditions for robust locomotion. The proposed method constantly updates the interaction model, samples feasible sequences of…

Robotics · Computer Science 2021-01-20 Timothée Anne , Jack Wilkinson , Zhibin Li

Learning-based control with safety guarantees usually requires real-time safety certification and modifications of possibly unsafe learning-based policies. The control barrier function (CBF) method uses a safety filter containing a…

Systems and Control · Electrical Eng. & Systems 2024-10-25 Kanghui He , Shengling Shi , Ton van den Boom , Bart De Schutter

Despite advances in hierarchical reinforcement learning, its applications to path planning in autonomous driving on highways are challenging. One reason is that conventional hierarchical reinforcement learning approaches are not amenable to…

Machine Learning · Computer Science 2021-11-11 Jaehyun Kim , Jaeseung Jeong

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…

Systems and Control · Electrical Eng. & Systems 2024-12-10 Pedram Rabiee , Amirsaeid Safari

Reinforcement learning (RL) in real-world safety-critical target settings like urban driving is hazardous, imperiling the RL agent, other agents, and the environment. To overcome this difficulty, we propose a "safety-critical adaptation"…

Machine Learning · Computer Science 2021-01-19 Jesse Zhang , Brian Cheung , Chelsea Finn , Sergey Levine , Dinesh Jayaraman