Autonomous agents are playing an ever-increasing role, including in automated driving
vehicles or house-care robots. When an autonomous agent interacts with humans, one of …

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 …

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 …

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 …

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 …

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 …

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 …