The advent of advanced computational technologies and artificial intelligence has ushered in a new era of complex systems and applications, notably in the realms of autonomous …
H Cao, Z Cai, H Wei, W Lu, L Zhang… - arXiv preprint arXiv …, 2022 - arxiv.org
Reinforcement Learning (RL) algorithms show amazing performance in recent years, but placing RL in real-world applications such as self-driven vehicles may suffer safety …
Reinforcement learning (RL) algorithms can achieve state-of-the-art performance in decision- making and continuous control tasks. However, applying RL algorithms on safety-critical …
Learning an agent's policy in a dynamic multi-agent environment presents numerous challenges due to the interactions with entities beyond the agent's control. In such settings …
M Naderi, K Borna - Authorea Preprints, 2024 - advance.sagepub.com
Safe reinforcement learning is an emerging research area that focuses on developing algorithms and techniques to train reinforcement learning agents to act safely in real-world …
X Zhang, H Zhang, H Zhou, C Huang… - IEEE Robotics and …, 2023 - ieeexplore.ieee.org
Safety is one of the main challenges in applying reinforcement learning to tasks in realistic environments. To ensure safety during and after the training process, existing methods tend …
A big challenge in implementing autonomous systems using reinforcement learning in a way to be used in the real world is to make them dependable, ie, explainable and reliable …
W Xue-Song, W Rong-Rong, C Yu-Hu - Acta Automat-ica Sinica, 2023 - aas.net.cn
Reinforcement learning (RL) has proved a prominent success in the game of Go, video games, navigation, recommendation systems and other fields. However, a large number of …
C Rana, M Dahiya - 2023 International Conference on …, 2023 - ieeexplore.ieee.org
The safety of autonomous systems has become an important concern in recent years. A new mechanism for developing safe and reliable autonomous systems is a very challenging task …