Zobrazeno 1 - 10
of 221
pro vyhledávání: '"P, Rozada"'
This work presents a low-rank tensor model for multi-dimensional Markov chains. A common approach to simplify the dynamical behavior of a Markov chain is to impose low-rankness on the transition probability matrix. Inspired by the success of these ma
Externí odkaz:
http://arxiv.org/abs/2411.02098
Autor:
Zhang, Xiangyi, Böhm, Fabian, Valiante, Elisabetta, Noori, Moslem, Van Vaerenbergh, Thomas, Yang, Chan-Woo, Pedretti, Giacomo, Mohseni, Masoud, Beausoleil, Raymond, Rozada, Ignacio
In-memory computing (IMC) has been shown to be a promising approach for solving binary optimization problems while significantly reducing energy and latency. Building on the advantages of parallel computation, we propose an IMC-compatible parallelism
Externí odkaz:
http://arxiv.org/abs/2409.09152
We study the problem of computing deterministic optimal policies for constrained Markov decision processes (MDPs) with continuous state and action spaces, which are widely encountered in constrained dynamical systems. Designing deterministic policy g
Externí odkaz:
http://arxiv.org/abs/2408.10015
Autor:
Rozada, Sergio, Marques, Antonio G.
The (efficient and parsimonious) decomposition of higher-order tensors is a fundamental problem with numerous applications in a variety of fields. Several methods have been proposed in the literature to that end, with the Tucker and PARAFAC decomposi
Externí odkaz:
http://arxiv.org/abs/2406.18560
Autor:
Rozada, Sergio, Marques, Antonio G.
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 achieved by estimating first the optimal (reward) value function (VF) ass
Externí odkaz:
http://arxiv.org/abs/2405.17628
Autor:
Rozada, Sergio, Marques, Antonio G.
Estimating a policy that maps states to actions is a central problem in reinforcement learning. Traditionally, policies are inferred from the so called value functions (VFs), but exact VF computation suffers from the curse of dimensionality. Policy g
Externí odkaz:
http://arxiv.org/abs/2405.17626
Autor:
Rozada, Sergio, Marques, Antonio G.
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 implement such a mapping via a neural network (NN) whose parameters are optimi
Externí odkaz:
http://arxiv.org/abs/2405.17625
Autor:
Maria H. Kjeldsen, Trinidad de Evan Rozada, Samantha J. Noel, Anna Schönherz, Anne Louise F. Hellwing, Peter Lund, Martin R. Weisbjerg
Publikováno v:
Journal of Dairy Science, Vol 107, Iss 12, Pp 10787-10810 (2024)
ABSTRACT: Limited literature is available identifying phenotypical traits related to enteric methane (CH4) production from dairy cows, despite its relevance in relation to breeding for animals with a low CH4 yield (g/kg DMI) and the derived consequen
Externí odkaz:
https://doaj.org/article/ea31f0e617394e5fbbea9d6ba8b1c15d
Autor:
Gonzalez-Rozada, Martin, Ruffo, Hernan
Unemployment insurance transfers should balance the provision of consumption to the unemployed with the disincentive effects on the search behavior. Developing countries face the additional challenge of informality. Workers can choose to hide their e
Externí odkaz:
http://arxiv.org/abs/2202.01844
Value-function (VF) approximation is a central problem in Reinforcement Learning (RL). Classical non-parametric VF estimation suffers from the curse of dimensionality. As a result, parsimonious parametric models have been adopted to approximate VFs i
Externí odkaz:
http://arxiv.org/abs/2201.09736