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 …

AI systems empowered by reinforcement learning (RL) algorithms harbor the immense
potential to catalyze societal advancement, yet their deployment is often impeded by …

Safe reinforcement learning (RL) aims to learn policies that satisfy certain constraints before
deploying them to safety-critical applications. Previous primal-dual style approaches suffer …

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

As shown by recent studies, machine intelligence-enabled systems are vulnerable to test
cases resulting from either adversarial manipulation or natural distribution shifts. This has …

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 …

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 …

Reinforcement Learning (RL) agents in the real world must satisfy safety constraints in
addition to maximizing a reward objective. Model-based RL algorithms hold promise for …

Reinforcement learning (RL) in low-data and risk-sensitive domains requires performant and
flexible deployment policies that can readily incorporate constraints during deployment. One …

Previous work demonstrates that the optimal safe reinforcement learning policy in a noise-
free environment is vulnerable and could be unsafe under observational attacks. While …