S
Sergio Valcarcel Macua
Researcher at Technical University of Madrid
Publications - 37
Citations - 505
Sergio Valcarcel Macua is an academic researcher from Technical University of Madrid. The author has contributed to research in topics: Reinforcement learning & Distributed algorithm. The author has an hindex of 11, co-authored 36 publications receiving 388 citations.
Papers
More filters
Journal ArticleDOI
Distributed Policy Evaluation Under Multiple Behavior Strategies
TL;DR: In this paper, the authors apply diffusion strategies to develop a fully-distributed cooperative reinforcement learning algorithm in which agents in a network communicate only with their immediate neighbors to improve predictions about their environment.
Proceedings ArticleDOI
Consensus-based distributed principal component analysis in wireless sensor networks
TL;DR: This work presents two fully distributed consensus-based algorithms that are guaranteed to converge to the global results, using only local communications among neighbors, regardless of the data distribution or the sparsity of the network.
Journal ArticleDOI
Dynamic Potential Games With Constraints: Fundamentals and Applications in Communications
TL;DR: This work applies the analysis and provides numerical methods to solve four example problems, named dynamic potential games, whose solution can be found through a single multivariate optimal control problem.
Posted Content
Diff-DAC: Distributed Actor-Critic for Average Multitask Deep Reinforcement Learning
Sergio Valcarcel Macua,Aleksi Tukiainen,Daniel García-Ocaña Hernández,David Baldazo,Enrique Munoz de Cote,Santiago Zazo +5 more
TL;DR: A multiagent distributed actor-critic algorithm for multitask reinforcement learning (MRL), named Diff-DAC, which is actually an instance of the dual ascent method to approximate the solution of a linear program.
Journal ArticleDOI
Robust Worst-Case Analysis of Demand-Side Management in Smart Grids
TL;DR: In this paper, the authors proposed a realistic model that accounts for uncertainty in real demand variations and calculates a robust price for all users in the smart grid, and analyzed the existence of solutions for this novel scenario, propose convergent distributed algorithms to find them, and perform simulations considering energy expenditure.