no code implementations • 14 Feb 2024 • Alberto Sinigaglia, Niccolò Turcato, Alberto Dalla Libera, Ruggero Carli, Gian Antonio Susto
This paper introduces innovative methods in Reinforcement Learning (RL), focusing on addressing and exploiting estimation biases in Actor-Critic methods for continuous control tasks, using Deep Double Q-Learning.
no code implementations • 10 Oct 2023 • Giulio Giacomuzzo, Alberto Dalla Libera, Diego Romeres, Ruggero Carli
First, instead of directly modeling the inverse dynamics components, we model as GPs the kinetic and potential energy of the system.
no code implementations • 30 Jan 2023 • Fabio Amadio, Alberto Dalla Libera, Daniel Nikovski, Ruggero Carli, Diego Romeres
We propose a Model-Based Reinforcement Learning (MBRL) algorithm named VF-MC-PILCO, specifically designed for application to mechanical systems where velocities cannot be directly measured.
no code implementations • 26 Apr 2021 • Alberto Dalla Libera, Fabio Amadio, Daniel Nikovski, Ruggero Carli, Diego Romeres
We tested the two strategies on a simulated manipulator with seven degrees of freedom, also varying the GP kernel choice.
no code implementations • 28 Jan 2021 • Fabio Amadio, Alberto Dalla Libera, Riccardo Antonello, Daniel Nikovski, Ruggero Carli, Diego Romeres
The algorithm relies on Gaussian Processes (GPs) to model the system dynamics and on a Monte Carlo approach to estimate the policy gradient.
no code implementations • 21 Jan 2021 • Fabio Amadio, Alberto Dalla Libera, Ruggero Carli, Daniel Nikovski, Diego Romeres
In this paper, we propose a Model-Based Reinforcement Learning (MBRL) algorithm for Partially Measurable Systems (PMS), i. e., systems where the state can not be directly measured, but must be estimated through proper state observers.
no code implementations • 24 Apr 2020 • Nicola Bastianello, Ruggero Carli, Andrea Simonetto
In this paper, we focus on the solution of online optimization problems that arise often in signal processing and machine learning, in which we have access to streaming sources of data.
1 code implementation • 26 Nov 2019 • Marco Todescato, Ruggero Carli, Luca Schenato, Grazia Barchi
We consider the problem of PMU-based state estimation combining information coming from ubiquitous power demand time series and only a limited number of PMUs.
Optimization and Control Systems and Control Systems and Control
no code implementations • 20 May 2019 • Alberto Dalla Libera, Ruggero Carli, Gianluigi Pillonetto
Volterra series are especially useful for nonlinear system identification, also thanks to their capability to approximate a broad range of input-output maps.
no code implementations • 30 Apr 2019 • Alberto Dalla Libera, Ruggero Carli
Driven by the fact that the inverse dynamics can be described as a polynomial function on a suitable input space, we propose the use of a novel kernel, called Geometrically Inspired Polynomial Kernel (GIP).
no code implementations • 3 May 2017 • Marco Todescato, Andrea Carron, Ruggero Carli, Gianluigi Pillonetto, Luca Schenato
In this work we study the non-parametric reconstruction of spatio-temporal dynamical Gaussian processes (GPs) via GP regression from sparse and noisy data.
no code implementations • 22 Jul 2014 • Andrea Carron, Marco Todescato, Ruggero Carli, Luca Schenato, Gianluigi Pillonetto
We consider a scenario where the aim of a group of agents is to perform the optimal coverage of a region according to a sensory function.