This paper presents a risk-informed data-driven safe control design approach for a class of
stochastic uncertain nonlinear discrete-time systems. The nonlinear system is modeled …

Safe reinforcement learning (RL) has shown great potential for building safe general-
purpose robotic systems. While many existing works have focused on post-training policy …

This paper proposes a safety modulator actor-critic (SMAC) method to address safety
constraint and overestimation mitigation in model-free safe reinforcement learning (RL). A …

The development of intelligent robots requires control policies that can handle dynamic
environments and evolving tasks. Pre-training reinforcement learning has emerged as an …

This paper introduces a data-based safe control design for stochastic nonlinear systems.
The controller consists of two parts: a linear component that ensures set invariance, and a …

Reinforcement learning (RL) has become a prominent research area in recent years due to
its ability to address decision-making problems by maximizing cumulative rewards in …