Reinforcement Learning (RL) has achieved tremendous success in many complex decision-
making tasks. However, safety concerns are raised during deploying RL in real-world …

Reinforcement Learning (RL) has achieved tremendous success in many complex decision-
making tasks. However, safety concerns are raised during deploying RL in real-world …

Lagrangian methods are widely used algorithms for constrained optimization problems, but
their learning dynamics exhibit oscillations and overshoot which, when applied to safe …

We study sequential decision-making problems in which each agent aims to maximize the
expected total reward while satisfying a constraint on the expected total utility. We employ …

Reinforcement Learning (RL) algorithms have had tremendous success in simulated
domains. These algorithms, however, often cannot be directly applied to physical systems …

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

In safe reinforcement learning (SRL) problems, an agent explores the environment to
maximize an expected total reward and meanwhile avoids violation of certain constraints on …

We study the safe reinforcement learning problem using the constrained Markov decision
processes in which an agent aims to maximize the expected total reward subject to a safety …

Safe reinforcement learning (RL) studies problems where an intelligent agent has to not only
maximize reward but also avoid exploring unsafe areas. In this study, we propose CUP, a …

Several earlier studies have shown impressive control performance in complex robotic
systems by designing the controller using a neural network and training it with model-free …