activity
20162025
most citedConstrained Reinforcement Learning Has Zero Duality Gap

10 citations · 24 across the 13 of their papers we have counts for

collaborators
Showing 2019Show all

8 papers · 1 filter

eess.SY2019★ 5 cited

A Prediction-Correction Algorithm for Real-Time Model Predictive Control

Santiago Paternain, Manfred Morari, Alejandro Ribeiro

In this work we adapt a prediction-correction algorithm for continuous time-varying convex optimization problems to solve dynamic programs arising from Model Predictive Control. In…

eess.SY2019

Safe Policies for Reinforcement Learning via Primal-Dual Methods

Santiago Paternain, Miguel Calvo-Fullana, Luiz F. O. Chamon +1

In this paper, we study the learning of safe policies in the setting of reinforcement learning problems. This is, we aim to control a Markov Decision Process (MDP) of which we do n…

cs.LG2019★ 10 cited

Constrained Reinforcement Learning Has Zero Duality Gap

Santiago Paternain, Luiz F. O. Chamon, Miguel Calvo-Fullana +1

Autonomous agents must often deal with conflicting requirements, such as completing tasks using the least amount of time/energy, learning multiple tasks, or dealing with multiple o…

math.OC2019

Source Seeking in Unknown Environments with Convex Obstacles

Bruno A. Angélico, Luiz F. O. Chamon, Santiago Paternain +2

Navigation tasks often cannot be defined in terms of a target, either because global position information is unavailable or unreliable or because target location is not explicitly…

math.OC2019

Navigation of a Quadratic Potential with Ellipsoidal Obstacles

Harshat Kumar, Santiago Paternain, Alejandro Ribeiro

Given a convex quadratic potential of which its minimum is the agent's goal and a Euclidean space populated with ellipsoidal obstacles, one can construct a Rimon-Koditschek (RK) ar…

eess.SP2019

Sparse multiresolution representations with adaptive kernels

Maria Peifer, Luiz. F. O. Chamon, Santiago Paternain +1

Reproducing kernel Hilbert spaces (RKHSs) are key elements of many non-parametric tools successfully used in signal processing, statistics, and machine learning. In this work, we a…