8 papers · 1 filter
A Contraction Framework for Stochastic Operators with Bootstrapping: Application to TD Learning
Ids van der Werf, Sergio Rozada, Antonio G. Marques
Many iterative algorithms rely on bootstrapping. A variable is updated using a second, frozen copy as a target, which is periodically replaced with the updated variable. Majorize-m…
Graph Convolutional Attention: A Spectral Perspective on Graph Denoising and Diffusion
Shervin Khalafi, Igor Krawczuk, Sergio Rozada +3
Denoising graphs is a fundamental problem in graph learning and the core operation of graph diffusion models. Attention-based architectures such as graph transformers have shown pr…
Graph-Aware Diffusion for Signal Generation
Sergio Rozada, Vimal K. B., Andrea Cavallo +3
We study the problem of generating graph signals from unknown distributions defined over given graphs, relevant to domains such as recommender systems or sensor networks. Our appro…
A Tensor Low-Rank Approximation for Value Functions in Multi-Task Reinforcement Learning
Sergio Rozada, Santiago Paternain, Juan Andres Bazerque +1
In pursuit of reinforcement learning systems that could train in physical environments, we investigate multi-task approaches as a means to alleviate the need for massive data acqui…
Multilinear Tensor Low-Rank Approximation for Policy-Gradient Methods in Reinforcement Learning
Sergio Rozada, Hoi-To Wai, Antonio G. Marques
Reinforcement learning (RL) aims to estimate the action to take given a (time-varying) state, with the goal of maximizing a cumulative reward function. Predominantly, there are two…
Addressing Finite-Horizon MDPs via Low-Rank Tensor Value Approximation
Sergio Rozada, Jose Luis Orejuela, Antonio G. Marques
We study the problem of learning optimal policies in finite-horizon Markov Decision Processes (MDPs) using low-rank reinforcement learning (RL) methods. In finite-horizon MDPs, the…
Tensor Low-rank Approximation of Finite-horizon Value Functions
Sergio Rozada, Antonio G. Marques
The goal of reinforcement learning is estimating a policy that maps states to actions and maximizes the cumulative reward of a Markov Decision Process (MDP). This is oftentimes ach…
Matrix Low-Rank Trust Region Policy Optimization
Sergio Rozada, Antonio G. Marques
Most methods in reinforcement learning use a Policy Gradient (PG) approach to learn a parametric stochastic policy that maps states to actions. The standard approach is to implemen…