Safety is critical when applying reinforcement learning (RL) to real-world problems. As a
result, safe RL has emerged as a fundamental and powerful paradigm for optimizing an …

The large-scale integration of intermittent renewable energy resources introduces increased
uncertainty and volatility to the supply side of power systems, thereby complicating system …

Safe offline RL is a promising way to bypass risky online interactions towards safe policy
learning. Most existing methods only enforce soft constraints, ie, constraining safety …

Autonomous Driving (AD) encounters significant safety hurdles in long-tail unforeseen
driving scenarios, largely stemming from the non-interpretability and poor generalization of …

Ensuring safety is important for the practical deployment of reinforcement learning (RL).
Various challenges must be addressed, such as handling stochasticity in the environments …

Reinforcement learning has shown promising results in learning neural network policies for
complicated control tasks. However, the lack of formal guarantees about the behavior of …

Safe exploration is essential for the practical use of reinforcement learning (RL) in many real-
world scenarios. In this paper, we present a generalized safe exploration (GSE) problem as …

Neural networks (NNs) playing the role of controllers have demonstrated impressive
empirical performance on challenging control problems. However, the potential adoption of …

In the context of safe exploration, Reinforcement Learning (RL) has long grappled with the
challenges of balancing the tradeoff between maximizing rewards and minimizing safety …

In this paper, we seek to learn a robot policy guaranteed to satisfy state constraints. To
encourage constraint satisfaction, existing RL algorithms typically rely on Constrained …