5 papers
Robust Parameter Learning for Uncertain MDPs
Yannik Schnitzer, Alessandro Abate, David Parker
Learning-based approaches to verifying unknown Markov decision processes (MDPs) often employ uncertain MDPs. These models use, for example, confidence intervals to capture transiti…
Probabilistic Performance Guarantees for Multi-Task Reinforcement Learning
Yannik Schnitzer, Mathias Jackermeier, Alessandro Abate +1
Multi-task reinforcement learning trains generalist policies that can execute multiple tasks. While recent years have seen significant progress, existing approaches rarely provide…
Multi-Property Synthesis
Christoph Weinhuber, Yannik Schnitzer, Alessandro Abate +3
We study LTLf synthesis with multiple properties, where satisfying all properties may be impossible. Instead of enumerating subsets of properties, we compute in one fixed-point com…
Efficient Solution and Learning of Robust Factored MDPs
Yannik Schnitzer, Alessandro Abate, David Parker
Robust Markov decision processes (r-MDPs) extend MDPs by explicitly modelling epistemic uncertainty about transition dynamics. Learning r-MDPs from interactions with an unknown env…
Certifiably Robust Policies for Uncertain Parametric Environments
Yannik Schnitzer, Alessandro Abate, David Parker
We present a data-driven approach for producing policies that are provably robust across unknown stochastic environments. Existing approaches can learn models of a single environme…