Matthijs T.J. Spaan — accepted AI-conference papers

2025

VeRecycle: Reclaiming Guarantees from Probabilistic Certificates for Stochastic Dynamical Systems after Change

Sterre Lutz, Matthijs T.J. Spaan, Anna Lukina

IJCAI 2025

Autonomous systems operating in the real world encounter a range of uncertainties. Probabilistic neural Lyapunov certification is a powerful approach to proving safety of nonlinear stochastic dynamical systems. When faced with changes beyond the modeled uncertainties, e.g., unidentified obstacles, p

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗

2023

CEM: Constrained Entropy Maximization for Task-Agnostic Safe Exploration

Qisong Yang, Matthijs T.J. Spaan

AAAI 2023technical

In the absence of assigned tasks, a learning agent typically seeks to explore its environment efficiently. However, the pursuit of exploration will bring more safety risks. An under-explored aspect of reinforcement learning is how to achieve safe efficient exploration when the task is unknown. In th…

Cited by 20 Source ↗PDF ↗Scholar ↗