collaborators

6 papers

cs.LG2025

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…

eess.SY2025

Existence and Synthesis of Multi-Resolution Approximate Bisimulations for Continuous-State Dynamical Systems

Rudi Coppola, Yannik Schnitzer, Mirco Giacobbe +2

We present a fully automatic framework for synthesising compact, finite-state deterministic abstractions of deterministic, continuous-state autonomous systems under locally specifi…

cs.LO2025

Branching Bisimulation Learning

Alessandro Abate, Mirco Giacobbe, Christian Micheletti +1

We introduce a bisimulation learning algorithm for non-deterministic transition systems. We generalise bisimulation learning to systems with bounded branching and extend its applic…

cs.LO2025

Quantitative Supermartingale Certificates

Alessandro Abate, Mirco Giacobbe, Diptarko Roy

We introduce a general methodology for quantitative model checking and control synthesis with supermartingale certificates. We show that every specification that is invariant to ti…

eess.SY2025

Certified Approximate Reachability (CARe): Formal Error Bounds on Deep Learning of Reachable Sets

Prashant Solanki, Nikolaus Vertovec, Yannik Schnitzer +3

Recent approaches to leveraging deep learning for computing reachable sets of continuous-time dynamical systems have gained popularity over traditional level-set methods, as they o…

cs.LG2025

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…