Integrating robots in complex everyday environments requires a multitude of problems to be
solved. One crucial feature among those is to equip robots with a mechanism for teaching …

We propose an efficient inference method for switching nonlinear dynamical systems. The
key idea is to learn an inference network which can be used as a proposal distribution for …

We consider the challenge of policy simplification and verification in the context of policies
learned through reinforcement learning (RL) in continuous environments. In well-behaved …

Learning low-dimensional latent state space dynamics models has proven powerful for
enabling vision-based planning and learning for control. We introduce a latent dynamics …

Evidence from empirical literature suggests that explainable complex behaviors can be built
from structured compositions of explainable component behaviors with known properties …

Recurrent neural networks (RNN) are being extensively exploited in industry to address
complex predictive tasks by leveraging on the increased availability of data from processes …

Control of nonlinear systems with unknown dynamics is a major challenge on the road to
fully autonomous agents. Current trends in reinforcement learning (RL) focus on complex …

The availability of advanced hybrid system identification techniques is fundamental to extract
knowledge in form of models from data streams. Starting from the current state of the art, we …

Critical robotic systems are systems whose functioning is critical to both ensuring the
accomplishment of a given mission and preventing the endangerment of life and the …

Optimal control of general nonlinear systems is a central challenge in automation. Enabled
by powerful function approximators, data-driven approaches to control have recently …