5 papers
Geometry of Uncertainty: Learning Metric Spaces for Multimodal State Estimation in RL
Alfredo Reichlin, Adriano Pacciarelli, Danica Kragic +1
Estimating the state of an environment from high-dimensional, multimodal, and noisy observations is a fundamental challenge in reinforcement learning (RL). Traditional approaches r…
Goal-Conditioned Reinforcement Learning from Sub-Optimal Data on Metric Spaces
Alfredo Reichlin, Miguel Vasco, Hang Yin +1
We study the problem of learning optimal behavior from sub-optimal datasets for goal-conditioned offline reinforcement learning under sparse rewards, invertible actions and determi…
Walking on the Fiber: A Simple Geometric Approximation for Bayesian Neural Networks
Alfredo Reichlin, Miguel Vasco, Danica Kragic
Bayesian Neural Networks provide a principled framework for uncertainty quantification by modeling the posterior distribution of network parameters. However, exact posterior infere…
EDO-Net: Learning Elastic Properties of Deformable Objects from Graph Dynamics
Alberta Longhini, Marco Moletta, Alfredo Reichlin +4
We study the problem of learning graph dynamics of deformable objects that generalizes to unknown physical properties. Our key insight is to leverage a latent representation of ela…
Reducing Variance in Meta-Learning via Laplace Approximation for Regression Tasks
Alfredo Reichlin, Gustaf Tegnér, Miguel Vasco +3
Given a finite set of sample points, meta-learning algorithms aim to learn an optimal adaptation strategy for new, unseen tasks. Often, this data can be ambiguous as it might belon…