39 citations · 55 across the 11 of their papers we have counts for
10 papers · 1 filter
LCRL: Certified Policy Synthesis via Logically-Constrained Reinforcement Learning
Hosein Hasanbeig, Daniel Kroening, Alessandro Abate
LCRL is a software tool that implements model-free Reinforcement Learning (RL) algorithms over unknown Markov Decision Processes (MDPs), synthesising policies that satisfy a given…
Certification of Iterative Predictions in Bayesian Neural Networks
Matthew Wicker, Luca Laurenti, Andrea Patane +3
We consider the problem of computing reach-avoid probabilities for iterative predictions made with Bayesian neural network (BNN) models. Specifically, we leverage bound propagation…
SafePILCO: a software tool for safe and data-efficient policy synthesis
Kyriakos Polymenakos, Nikitas Rontsis, Alessandro Abate +1
SafePILCO is a software tool for safe and data-efficient policy search with reinforcement learning. It extends the known PILCO algorithm, originally written in MATLAB, to support s…
Carathéodory Sampling for Stochastic Gradient Descent
Francesco Cosentino, Harald Oberhauser, Alessandro Abate
Many problems require to optimize empirical risk functions over large data sets. Gradient descent methods that calculate the full gradient in every descent step do not scale to suc…
A Randomized Algorithm to Reduce the Support of Discrete Measures
Francesco Cosentino, Harald Oberhauser, Alessandro Abate
Given a discrete probability measure supported on atoms and a set of real-valued functions, there exists a probability measure that is supported on a subset of of the…
Cautious Reinforcement Learning with Logical Constraints
Mohammadhosein Hasanbeig, Alessandro Abate, Daniel Kroening
This paper presents the concept of an adaptive safe padding that forces Reinforcement Learning (RL) to synthesise optimal control policies while ensuring safety during the learning…