activity
20182022
most citedAutomated and Sound Synthesis of Lyapunov Functions with SMT Solvers

39 citations · 55 across the 11 of their papers we have counts for

collaborators
Showing cs.LGShow all

10 papers · 1 filter

cs.LG2022

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…

cs.LG20212 cited

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…

cs.LG2020

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…

cs.LG2020

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…

cs.LG2020

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…

cs.LG2020

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…