English
Related papers

Related papers: Probabilistic Guarantees for Safe Deep Reinforceme…

200 papers

Safe reinforcement learning (RL) is crucial for real-world applications, and multi-agent interactions introduce additional safety challenges. While Probabilistic Logic Shields (PLS) has been a powerful proposal to enforce safety in…

Artificial Intelligence · Computer Science 2025-08-28 Satchit Chatterji , Erman Acar

When learning policies for robotic systems from data, safety is a major concern, as violation of safety constraints may cause hardware damage. SafeOpt is an efficient Bayesian optimization (BO) algorithm that can learn policies while…

Robotics · Computer Science 2021-05-28 Dominik Baumann , Alonso Marco , Matteo Turchetta , Sebastian Trimpe

Cyber-physical systems (CPSs) are now widely deployed in many industrial domains, e.g., manufacturing systems and autonomous vehicles. To further enhance the capability and applicability of CPSs, there comes a recent trend from both…

Software Engineering · Computer Science 2023-05-09 Xuan Xie , Jiayang Song , Zhehua Zhou , Fuyuan Zhang , Lei Ma

This paper concerns the risk-aware control of stochastic systems with temporal logic specifications dynamically assigned during runtime. Conventional risk-aware control typically assumes that all specifications are predefined and remain…

Systems and Control · Electrical Eng. & Systems 2024-05-01 Maico H. W. Engelaar , Zengjie Zhang , Mircea Lazar , Sofie Haesaert

With the increasing complexity of real-world systems and varying environmental uncertainties, it is difficult to build an accurate dynamic model, which poses challenges especially for safety-critical control. In this paper, a learning-based…

Systems and Control · Electrical Eng. & Systems 2024-08-13 Sihua Zhang , Di-Hua Zhai , Xiaobing Dai , Tzu-yuan Huang , Yuanqing Xia , Sandra Hirche

Safe motion planning in uncertain, time-varying environments is challenging because the safe region can change unpredictably across planning steps, often causing a loss of recursive feasibility. In this work, we present a Probabilistic…

Systems and Control · Electrical Eng. & Systems 2026-05-20 Hyeontae Sung , Hyeongchan Ham , Junyoung Park , Kai Ren , Heejin Ahn

This paper studies the problem of enforcing safety of a stochastic dynamical system over a finite time horizon. We use stochastic barrier functions as a means to quantify the probability that a system exits a given safe region of the state…

Systems and Control · Computer Science 2019-05-30 Cesar Santoyo , Maxence Dutreix , Samuel Coogan

Safety is a primary concern when applying reinforcement learning to real-world control tasks, especially in the presence of external disturbances. However, existing safe reinforcement learning algorithms rarely account for external…

Machine Learning · Computer Science 2023-10-12 Zeyang Li , Chuxiong Hu , Shengbo Eben Li , Jia Cheng , Yunan Wang

In the sequential decision making setting, an agent aims to achieve systematic generalization over a large, possibly infinite, set of environments. Such environments are modeled as discrete Markov decision processes with both states and…

Machine Learning · Computer Science 2023-03-31 Mirco Mutti , Riccardo De Santi , Emanuele Rossi , Juan Felipe Calderon , Michael Bronstein , Marcello Restelli

Accurate quantification of safety is essential for the design of autonomous systems. In this paper, we present a methodology to characterize the exact probabilities associated with invariance and recovery in safe control. We consider a…

Optimization and Control · Mathematics 2021-04-22 Albert Chern , Xiang Wang , Abhiram Iyer , Yorie Nakahira

We consider the problem of learning the optimal policy for Markov decision processes with safety constraints. We formulate the problem in a reach-avoid setup. Our goal is to design online reinforcement learning algorithms that ensure safety…

Machine Learning · Computer Science 2026-01-21 Abhijit Mazumdar , Rafal Wisniewski , Manuela L. Bujorianu

Learning is usually performed by observing real robot executions. Physics-based simulators are a good alternative for providing highly valuable information while avoiding costly and potentially destructive robot executions. We present a…

This article proposes an improved trajectory optimization approach for stochastic optimal control of dynamical systems affected by measurement noise by combining optimal control with maximum likelihood techniques to improve the reduction of…

Systems and Control · Electrical Eng. & Systems 2023-12-25 Prakash Mallick , Zhiyong Chen

The rapid evolution to autonomous, agentic AI systems introduces significant risks due to their inherent unpredictability and emergent behaviors; this also renders traditional verification methods inadequate and necessitates a shift towards…

Artificial Intelligence · Computer Science 2025-09-30 Roham Koohestani

Traditional controllers have limitations as they rely on prior knowledge about the physics of the problem, require modeling of dynamics, and struggle to adapt to abnormal situations. Deep reinforcement learning has the potential to address…

Machine Learning · Computer Science 2023-10-24 Ammar N. Abbas , Georgios C. Chasparis , John D. Kelleher

This paper proposes a model predictive controller for discrete-time linear systems with additive, possibly unbounded, stochastic disturbances and subject to chance constraints. By computing a polytopic probabilistic positively invariant set…

Optimization and Control · Mathematics 2024-09-23 Kai Wang , Kiet Tuan Hoang , Sébastien Gros

We introduce a method to verify stochastic reinforcement learning (RL) policies. This approach is compatible with any RL algorithm as long as the algorithm and its corresponding environment collectively adhere to the Markov property. In…

Artificial Intelligence · Computer Science 2024-03-28 Dennis Gross , Helge Spieker

Multi-Agent reinforcement learning has received lot of attention in recent years and have applications in many different areas. Existing methods involving Centralized Training and Decentralized execution, attempts to train the agents…

Machine Learning · Computer Science 2021-09-15 Satheesh K. Perepu , Kaushik Dey

Learning-based techniques are increasingly effective at controlling complex systems using data-driven models. However, most work done so far has focused on learning individual tasks or control laws. Hence, it is still a largely unaddressed…

Systems and Control · Electrical Eng. & Systems 2020-05-08 Alexandre Capone , Armin Lederer , Jonas Umlauft , Sandra Hirche

Deep reinforcement learning (RL) has shown promising results in the motion planning of manipulators. However, no method guarantees the safety of highly dynamic obstacles, such as humans, in RL-based manipulator control. This lack of formal…

Robotics · Computer Science 2022-05-16 Jakob Thumm , Matthias Althoff