English
Related papers

Related papers: Shields to Guarantee Probabilistic Safety in MDPs

200 papers

Partially observable Markov decision processes (POMDPs) have been widely used in many robotic applications for sequential decision-making under uncertainty. POMDP online planning algorithms such as Partially Observable Monte-Carlo Planning…

Artificial Intelligence · Computer Science 2024-03-05 Shili Sheng , David Parker , Lu Feng

We outline the principles of classical assurance for computer-based systems that pose significant risks. We then consider application of these principles to systems that employ Artificial Intelligence (AI) and Machine Learning (ML). A key…

Artificial Intelligence · Computer Science 2025-06-04 Robin Bloomfield , John Rushby

In this paper, we propose a method to develop trustworthy reinforcement learning systems. To ensure safety especially during exploration, we automatically synthesize a correct-by-construction runtime enforcer, called a shield, that blocks…

Logic in Computer Science · Computer Science 2020-12-18 Bettina Könighofer , Julian Rudolf , Alexander Palmisano , Martin Tappler , Roderick Bloem

Among approaches for provably safe reinforcement learning, Model Predictive Shielding (MPS) has proven effective at complex tasks in continuous, high-dimensional state spaces, by leveraging a backup policy to ensure safety when the learned…

Artificial Intelligence · Computer Science 2024-12-24 Arko Banerjee , Kia Rahmani , Joydeep Biswas , Isil Dillig

The increasing adoption of Reinforcement Learning in safety-critical systems domains such as autonomous vehicles, health, and aviation raises the need for ensuring their safety. Existing safety mechanisms such as adversarial training,…

Machine Learning · Computer Science 2021-11-11 Paulina Stevia Nouwou Mindom , Amin Nikanjam , Foutse Khomh , John Mullins

Besides the recent impressive results on reinforcement learning (RL), safety is still one of the major research challenges in RL. RL is a machine-learning approach to determine near-optimal policies in Markov decision processes (MDPs). In…

Machine Learning · Computer Science 2022-12-06 Bettina Könighofer , Julian Rudolf , Alexander Palmisano , Martin Tappler , Roderick Bloem

This thesis studies advanced probabilistic models, including both their theoretical foundations and practical applications, for different semi-supervised learning (SSL) tasks. The proposed probabilistic methods are able to improve the…

Machine Learning · Computer Science 2024-04-08 Jianfeng Wang

Embodied AI systems, comprising AI models and physical plants, are increasingly prevalent across various applications. Due to the rarity of system failures, ensuring their safety in complex operating environments remains a major challenge,…

Multi-agent systems under partial observation often struggle to maintain safety because each agent's locally chosen action does not, in general, determine the resulting joint action. Shielding addresses this by filtering actions based on…

Multiagent Systems · Computer Science 2026-04-09 Haoran Yang , Nobuko Yoshida

Agents controlled by the output of reinforcement learning (RL) algorithms often transition to unsafe states, particularly in uncertain and partially observable environments. Partially observable Markov decision processes (POMDPs) provide a…

Systems and Control · Electrical Eng. & Systems 2025-09-16 Steven Carr , Georgios Bakirtzis , Ufuk Topcu

Is there a way to design powerful AI systems based on machine learning methods that would satisfy probabilistic safety guarantees? With the long-term goal of obtaining a probabilistic guarantee that would apply in every context, we consider…

Artificial Intelligence · Computer Science 2025-06-17 Yoshua Bengio , Michael K. Cohen , Nikolay Malkin , Matt MacDermott , Damiano Fornasiere , Pietro Greiner , Younesse Kaddar

The full deployment of autonomous driving systems on a worldwide scale requires that the self-driving vehicle be operated in a provably safe manner, i.e., the vehicle must be able to avoid collisions in any possible traffic situation. In…

Robotics · Computer Science 2023-05-08 Ivo Batkovic , Ankit Gupta , Mario Zanon , Paolo Falcone

Our goal is to compute a policy that guarantees improved return over a baseline policy even when the available MDP model is inaccurate. The inaccurate model may be constructed, for example, by system identification techniques when the true…

Optimization and Control · Mathematics 2015-06-17 Yinlam Chow , Marek Petrik , Mohammad Ghavamzadeh

Model Predictive Path Integral (MPPI) control is a type of sampling-based model predictive control that simulates thousands of trajectories and uses these trajectories to synthesize optimal controls on-the-fly. In practice, however, MPPI…

Robotics · Computer Science 2023-02-24 Ji Yin , Charles Dawson , Chuchu Fan , Panagiotis Tsiotras

Shielding has emerged as a promising approach for ensuring safety of AI-controlled autonomous systems. The algorithmic goal is to compute a shield, which is a runtime safety enforcement tool that needs to monitor and intervene the AI…

Artificial Intelligence · Computer Science 2025-05-29 Davide Corsi , Kaushik Mallik , Andoni Rodriguez , Cesar Sanchez

We consider the problem of safe control in discrete autonomous agents that use learned components for imperfect perception (or more generally, state estimation) from high-dimensional observations. We propose a shield construction that…

Systems and Control · Electrical Eng. & Systems 2025-07-29 William Scarbro , Calum Imrie , Sinem Getir Yaman , Kavan Fatehi , Corina S. Pasareanu , Radu Calinescu , Ravi Mangal

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

Ensuring reliable performance in situations outside the Operational Design Domain (ODD) remains a primary challenge in devising resilient autonomous systems. We explore this challenge by introducing an approach for adapting probabilistic…

Logic in Computer Science · Computer Science 2026-04-10 Gricel Vázquez , Calum Imrie , Sepeedeh Shahbeigi , Nawshin Mannan Proma , Tian Gan , Victoria J Hodge , John Molloy , Simos Gerasimou

Achieving safe control under uncertainty is a key problem that needs to be tackled for enabling real-world autonomous robots and cyber-physical systems. This paper introduces Probabilistic Safety Programs (PSP) that embed both the…

Robotics · Computer Science 2016-10-19 Ashish Kapoor , Debadeepta Dey , Shital Shah

While Deep Reinforcement Learning (DRL) has achieved remarkable success across various domains, it remains vulnerable to occasional catastrophic failures without additional safeguards. An effective solution to prevent these failures is to…

Machine Learning · Computer Science 2024-12-03 Kyungmin Kim , Davide Corsi , Andoni Rodriguez , JB Lanier , Benjami Parellada , Pierre Baldi , Cesar Sanchez , Roy Fox