Safe reinforcement learning (RL) trains a constraint satisfaction policy by interacting with the
environment. We aim to tackle a more challenging problem: learning a safe policy from an …

A trustworthy reinforcement learning algorithm should be competent in solving challenging
real-world problems, including {robustly} handling uncertainties, satisfying {safety} …

Offline safe reinforcement learning (RL) algorithms promise to learn policies that satisfy
safety constraints directly in offline datasets without interacting with the environment. This …

Safe reinforcement learning (RL) focuses on training reward-maximizing agents subject to
pre-defined safety constraints. Yet, learning versatile safe policies that can adapt to varying …

Multi-constraint offline reinforcement learning (RL) promises to learn policies that satisfy
both cumulative and state-wise costs from offline datasets. This arrangement provides an …

This paper presents a comprehensive benchmarking suite tailored to offline safe
reinforcement learning (RL) challenges, aiming to foster progress in the development and …

Ensuring safety is critical when applying reinforcement learning (RL) to real-world problems.
Consequently, safe RL emerges as a fundamental and powerful paradigm for safely …

We consider the safe reinforcement learning (RL) problem of maximizing utility with
extremely low constraint violation rates. Assuming no prior knowledge or pre-training of the …

Safe reinforcement learning (RL) trains a policy to maximize the task reward while satisfying
safety constraints. While prior works focus on the performance optimality, we find that the …

Offline reinforcement learning (RL) aims to learn a policy using only pre-collected and fixed
data. Although avoiding the time-consuming online interactions in RL, it poses challenges …