Reinforcement learning (RL) is capable of sophisticated motion planning and control for robots in uncertain environments. However, state-of-the-art deep RL approaches typically …
Safety remains a central obstacle preventing widespread use of RL in the real world: learning new tasks in uncertain environments requires extensive exploration, but safety …
Reinforcement Learning (RL) has been shown to be effective in many scenarios. However, it typically requires the exploration of a sufficiently large number of state-action pairs, some of …
AK Akametalu, JF Fisac, JH Gillula… - … IEEE Conference on …, 2014 - ieeexplore.ieee.org
Reinforcement learning for robotic applications faces the challenge of constraint satisfaction, which currently impedes its application to safety critical systems. Recent approaches …
Safety comes first in many real-world applications involving autonomous agents. Despite a large number of reinforcement learning (RL) methods focusing on safety-critical tasks, there …
Y Yang, Y Jiang, Y Liu, J Chen… - IEEE Robotics and …, 2023 - ieeexplore.ieee.org
Safety is a critical concern when applying reinforcement learning (RL) to real-world control tasks. However, existing safe RL works either only consider expected safety constraint …
R Cheng, G Orosz, RM Murray, JW Burdick - Proceedings of the AAAI …, 2019 - aaai.org
Reinforcement Learning (RL) algorithms have found limited success beyond simulated applications, and one main reason is the absence of safety guarantees during the learning …
Reinforcement Learning (RL) is a widely employed machine learning architecture that has been applied to a variety of decision-making problems, from resource management to robot …
Due to the trial-and-error nature, it is typically challenging to apply RL algorithms to safety- critical real-world applications, such as autonomous driving, human-robot interaction, robot …