output
20092025
most citedActive Learning of Inverse Models with Intrinsically Motivated Goal Exploration in Robots

451 citations

researchers with a paper here

Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.

collaborating institutions
Showing 2023Show all

5 papers · 1 filter

stat.ML2023★ 1 cited

A Symmetry-Aware Exploration of Bayesian Neural Network Posteriors

Olivier Laurent, Emanuel Aldea, Gianni Franchi

The distribution of the weights of modern deep neural networks (DNNs) - crucial for uncertainty quantification and robustness - is an eminently complex object due to its extremely…

math.OC2023

An entropy penalized approach for stochastic control problems. Complete version

Thibaut Bourdais, Nadia Oudjane, Francesco Russo

In this paper, we propose an original approach to stochastic control problems. We consider a weak formulation that is written as an optimization (minimization) problem on the space…

cs.CV2023

Discretization-Induced Dirichlet Posterior for Robust Uncertainty Quantification on Regression

Xuanlong Yu, Gianni Franchi, Jindong Gu +1

Uncertainty quantification is critical for deploying deep neural networks (DNNs) in real-world applications. An Auxiliary Uncertainty Estimator (AuxUE) is one of the most effective…

math.NA2023★ 26 cited

Direct parametrisation of invariant manifolds for non-autonomous forced systems including superharmonic resonances

Alessandra Vizzaccaro, Giorgio Gobat, Attilio Frangi +1

The direct parametrisation method for invariant manifold is a model-order reduction technique that can be applied to nonlinear systems described by PDEs and discretised e.g. with a…

math.OC2023

Contributions on complexity bounds for Deterministic Partially Observed Markov Decision Process

Cyrille Vessaire, Jean-Philippe Chancelier, Michel de Lara +2

Markov Decision Processes (Mdps) form a versatile framework used to model a wide range of optimization problems. The Mdp model consists of sets of states, actions, time steps, rewa…