Showing cs.LGShow all
2 papers · 1 filter
cs.LG2023
Distributionally Safe Reinforcement Learning under Model Uncertainty: A Single-Level Approach by Differentiable Convex Programming
Alaa Eddine Chriat, Chuangchuang Sun
Safety assurance is uncompromisable for safety-critical environments with the presence of drastic model uncertainties (e.g., distributional shift), especially with humans in the lo…
cs.LG2023
On the Optimality, Stability, and Feasibility of Control Barrier Functions: An Adaptive Learning-Based Approach
Alaa Eddine Chriat, Chuangchuang Sun
Safety has been a critical issue for the deployment of learning-based approaches in real-world applications. To address this issue, control barrier function (CBF) and its variants…