7 papers
Universal Formulas for Safe Control and Their Neural Network Approximations
Pol Mestres, Jorge Cortés, Eduardo D. Sontag
We study the problem of designing a controller that satisfies an arbitrary number of affine inequalities at every point in the state space. This is motivated by the fact that a var…
Anytime Safe Reinforcement Learning
Pol Mestres, Arnau Marzabal, Jorge Cortés
This paper considers the problem of solving constrained reinforcement learning problems with anytime guarantees, meaning that the algorithmic solution returns a safe policy regardl…
Data-Driven Stabilization of Unknown Linear-Threshold Network Dynamics
Xuan Wang, Duy Duong-Tran, Jorge Cortés
This paper studies the data-driven control of unknown linear-threshold network dynamics to stabilize the state to a reference value. We consider two types of controllers: (i) a sta…
Feedback Optimization with State Constraints through Control Barrier Functions
Giannis Delimpaltadakis, Pol Mestres, Jorge Cortés +1
Recently, there has been a surge of research on a class of methods called feedback optimization. These are methods to steer the state of a control system to an equilibrium that ari…
Back to Base: Towards Hands-Off Learning via Safe Resets with Reach-Avoid Safety Filters
Azra BegzadiÄ, Nikhil Uday Shinde, Sander Tonkens +5
Designing controllers that accomplish tasks while guaranteeing safety constraints remains a significant challenge. We often want an agent to perform well in a nominal task, such as…
Controller Design for Bilinear Neural Feedback Loops
Dhruv Shah, Jorge Cortés
This paper considers a class of bilinear systems with a neural network in the loop. These arise naturally when employing machine learning techniques to approximate general, non-aff…