G
Gabriel A. D. Lopes
Researcher at Delft University of Technology
Publications - 57
Citations - 1738
Gabriel A. D. Lopes is an academic researcher from Delft University of Technology. The author has contributed to research in topics: Reinforcement learning & Visual servoing. The author has an hindex of 15, co-authored 57 publications receiving 1366 citations. Previous affiliations of Gabriel A. D. Lopes include Instituto Superior Técnico & University of Michigan.
Papers
More filters
Journal ArticleDOI
A Survey of Actor-Critic Reinforcement Learning: Standard and Natural Policy Gradients
TL;DR: The workings of the natural gradient is described, which has made its way into many actor-critic algorithms over the past few years, and a review of several standard and natural actor-Critic algorithms is given.
Proceedings ArticleDOI
Automated gait adaptation for legged robots
TL;DR: This paper presents a system for gait adaptation in the RHex series of hexapedal robots that renders this arduous process nearly autonomous, by recourse to a modified version of Nelder-Mead descent.
Journal ArticleDOI
Optimal model-free output synchronization of heterogeneous systems using off-policy reinforcement learning
TL;DR: This paper considers optimal output synchronization of heterogeneous linear multi-agent systems and shows that this optimal distributed approach implicitly solves the output regulation equations without actually doing so.
Journal ArticleDOI
Port-Hamiltonian Systems in Adaptive and Learning Control: A Survey
TL;DR: A comprehensive review of the current learning and adaptive control methodologies that have been adapted specifically to PH systems, and highlights the changes from the general setting due to PH model, followed by a detailed presentation of the respective control algorithm.
Journal ArticleDOI
A fast sampling method for estimating the domain of attraction
TL;DR: In this paper, a sampling approach is proposed to estimate the domain of attraction (DoA) of nonlinear systems in real time, which is validated to approximate the DoAs of stable equilibria.