English
Related papers

Related papers: Criticality and Safety Margins for Reinforcement L…

200 papers

Any autonomous controller will be unsafe in some situations. The ability to quantitatively identify when these unsafe situations are about to occur is crucial for drawing timely human oversight in, e.g., freight transportation applications.…

Machine Learning · Computer Science 2024-10-10 Alexander Grushin , Walt Woods , Alvaro Velasquez , Simon Khan

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

Physical systems experience nonlinear disturbances which have the potential to disrupt desired behavior. For a particular disturbance, whether or not the system recovers from the disturbance to a desired stable equilibrium point depends on…

Systems and Control · Electrical Eng. & Systems 2025-01-14 Michael W. Fisher

Designing hierarchical reinforcement learning algorithms that exhibit safe behaviour is not only vital for practical applications but also, facilitates a better understanding of an agent's decisions. We tackle this problem in the options…

Artificial Intelligence · Computer Science 2021-07-01 Arushi Jain , Khimya Khetarpal , Doina Precup

Recent advances in learning techniques have garnered attention for their applicability to a diverse range of real-world sequential decision-making problems. Yet, many practical applications have critical constraints for operation in real…

Machine Learning · Computer Science 2024-05-06 Jose A. Ayala-Romero , Andres Garcia-Saavedra , Xavier Costa-Perez

This paper outlines a methodological approach for designing adaptive agents driving themselves near points of criticality. Using a synthetic approach we construct a conceptual model that, instead of specifying mechanistic requirements to…

Adaptation and Self-Organizing Systems · Physics 2017-12-14 Miguel Aguilera , Manuel G. Bedia

This paper proposes a suite of rationality measures and associated theory for reinforcement learning agents, a property increasingly critical yet rarely explored. We define an action in deployment to be perfectly rational if it maximises…

Machine Learning · Computer Science 2026-05-05 Kejiang Qian , Amos Storkey , Fengxiang He

Although Reinforcement Learning (RL) is effective for sequential decision-making problems under uncertainty, it still fails to thrive in real-world systems where risk or safety is a binding constraint. In this paper, we formulate the RL…

Machine Learning · Computer Science 2022-07-07 Yannis Flet-Berliac , Debabrota Basu

This paper investigates the critical-time criteria as a security metric for controlled systems subject to sharp input anomalies (attack, fault), characterized by having high impact in a reduced amount of time (e.g. denial-of-service, attack…

Systems and Control · Electrical Eng. & Systems 2023-07-26 Arthur Perodou , Christophe Combastel , Ali Zolghadri

In safety-critical applications, autonomous agents may need to learn in an environment where mistakes can be very costly. In such settings, the agent needs to behave safely not only after but also while learning. To achieve this, existing…

Machine Learning · Computer Science 2021-01-22 Matteo Turchetta , Andrey Kolobov , Shital Shah , Andreas Krause , Alekh Agarwal

Agentic systems are evaluated on benchmarks where agents interact with environments to solve tasks. Most papers report a pass@1 score computed from a single run per task, assuming this gives a reliable performance estimate. We test this…

Machine Learning · Computer Science 2026-03-26 Bjarni Haukur Bjarnason , André Silva , Martin Monperrus

Safe navigation in real-time is challenging because engineers need to work with uncertain vehicle dynamics, variable external disturbances, and imperfect controllers. A common safety strategy is to inflate obstacles by hand-defined margins.…

Robotics · Computer Science 2021-10-08 Cherie Ho , Jay Patrikar , Rogerio Bonatti , Sebastian Scherer

Credible safety plans for advanced AI development require methods to verify agent behavior and detect potential control deficiencies early. A fundamental aspect is ensuring agents adhere to safety-critical principles, especially when these…

Machine Learning · Computer Science 2025-07-11 Ram Potham

Asynchronous Advantage Actor Critic (A3C) is an effective Reinforcement Learning (RL) algorithm for a wide range of tasks, such as Atari games and robot control. The agent learns policies and value function through trial-and-error…

Machine Learning · Computer Science 2019-12-03 Zhaoyuan Gu , Zhenzhong Jia , Howie Choset

This paper addresses the problem of maintaining safety during training in Reinforcement Learning (RL), such that the safety constraint violations are bounded at any point during learning. In a variety of RL applications the safety of the…

Machine Learning · Computer Science 2023-12-19 Rohan Mitta , Hosein Hasanbeig , Jun Wang , Daniel Kroening , Yiannis Kantaros , Alessandro Abate

This paper proposes a reversible learning framework to improve the robustness and efficiency of value based Reinforcement Learning agents, addressing vulnerability to value overestimation and instability in partially irreversible…

Machine Learning · Computer Science 2025-10-17 Andrejs Sorstkins , Omer Tariq , Muhammad Bilal

Intelligent systems are increasingly integral to our daily lives, yet rare safety-critical events present significant latent threats to their practical deployment. Addressing this challenge hinges on accurately predicting the probability of…

Machine Learning · Computer Science 2024-04-08 Ruoxuan Bai , Jingxuan Yang , Weiduo Gong , Yi Zhang , Qiujing Lu , Shuo Feng

Safety evaluation for advanced AI systems assumes that behavior observed under evaluation predicts behavior in deployment. This assumption weakens for agents with situational awareness, which may exploit regime leakage, cues distinguishing…

Artificial Intelligence · Computer Science 2026-02-17 Igor Santos-Grueiro

Ensuring safety in autonomous driving requires precise, real-time risk assessment and adaptive behavior. Prior work on risk estimation either outputs coarse, global scene-level metrics lacking interpretability, proposes indicators without…

Robotics · Computer Science 2025-08-06 Boyang Tian , Weisong Shi

In reinforcement learning for partially observable environments, many successful algorithms have been developed within the asymmetric learning paradigm. This paradigm leverages additional state information available at training time for…

Machine Learning · Computer Science 2025-09-09 Gaspard Lambrechts , Damien Ernst , Aditya Mahajan
‹ Prev 1 2 3 10 Next ›