10 papers
Robust Shielding for Safe Reinforcement Learning
Edwin Hamel-De le Court, Thom Badings, Alessandro Abate +2
Shielding is an effective approach to formally guarantee the safety of reinforcement learning agents in Markov decision processes (MDPs). However, existing shielding techniques typ…
Scalable Verification of Neural Control Barrier Functions Using Linear Bound Propagation
Nikolaus Vertovec, Frederik Baymler Mathiesen, Thom Badings +2
Control barrier functions (CBFs) are a popular tool for safety certification of nonlinear dynamical control systems. Recently, CBFs represented as neural networks have shown great…
Temporal Logic Control of Nonlinear Stochastic Systems with Online Performance Optimization
Alessandro Riccardi, Thom Badings, Luca Laurenti +2
The deployment of autonomous systems in safety-critical environments requires control policies that guarantee satisfaction of complex control specifications. These systems are comm…
Best-Effort Policies for Robust Markov Decision Processes
Alessandro Abate, Thom Badings, Giuseppe De Giacomo +1
We study the common generalization of Markov decision processes (MDPs) with sets of transition probabilities, known as robust MDPs (RMDPs). A standard goal in RMDPs is to compute a…
Data-Driven Abstraction and Synthesis for Stochastic Systems with Unknown Dynamics
Mahdi Nazeri, Thom Badings, Anne-Kathrin Schmuck +2
We study the automated abstraction-based synthesis of correct-by-construction control policies for stochastic dynamical systems with unknown dynamics. Our approach is to learn an a…
Data-Driven Yet Formal Policy Synthesis for Stochastic Nonlinear Dynamical Systems
Mahdi Nazeri, Thom Badings, Sadegh Soudjani +1
The automated synthesis of control policies for stochastic dynamical systems presents significant challenges. A standard approach is to construct a finite-state abstraction of the…