Results 11 to 20 of about 90,056 (287)
Approximate Modified Policy Iteration [PDF]
CoRR, 2012 Modified policy iteration (MPI) is a dynamic programming (DP) algorithm that contains the two celebrated policy and value iteration methods. Despite its generality, MPI has not been thoroughly studied, especially its approximation form which is used when the state and/or action spaces are large or infinite.
Scherrer, Bruno +3 more
openaire +4 more sources
Approximate and iterative methods [PDF]
Discrete Dynamics in Nature and Society, 2015 1Department of Mathematics, Pedagogical University, Podchorązych 2, 30-084 Krakow, Poland 2Faculty of Applied Mathematics, AGH University of Science and Technology, Mickiewicza 30, 30-059 Krakow, Poland 3Faculty of Management, University of Primorska, Cankarjeva 5, 6104 Koper, Slovenia 4Department of Mathematics, Technical University of Cluj-Napoca ...
Janusz Brzdęk +5 more
openaire +4 more sources
, 2022 The article is devoted to the mean-square approximation of iterated Ito and Stratonovich stochastic integrals in the context of the numerical integration of Ito stochastic differential equations.
Kuznetsov, Dmitriy F.
core +1 more source
Multiple general sigmoids based Banach space valued neural network multivariate approximation
Cubo, 2023 Here we present multivariate quantitative approximations of Banach space valued continuous multivariate functions on a box or \(\mathbb{R}^{N},\) \(N\in \mathbb{N}\), by the multivariate normalized, quasi-interpolation, Kantorovich type and quadrature ...
George A. Anastassiou
doaj +1 more source
Rollout sampling approximate policy iteration [PDF]
Machine Learning, 2008 Several researchers have recently investigated the connection between reinforcement learning and classification. We are motivated by proposals of approximate policy iteration schemes without value functions which focus on policy representation using classifiers and address policy learning as a supervised learning problem.
Dimitrakakis Christos() +2 more
openaire +7 more sources
Scale-Free Fractal Interpolation
Fractal and Fractional, 2022 An iterated function system that defines a fractal interpolation function, where ordinate scaling is replaced by a nonlinear contraction, is investigated here.
María A. Navascués +2 more
doaj +1 more source
Hyperbolic Tangent Like Relied Banach Space Valued Neural Network Multivariate Approximations
Annals of the West University of Timisoara: Mathematics and Computer Science, 2023 Here we examine the multivariate quantitative approximations of Banach space valued continuous multivariate functions on a box or ℝN , N ∈ ℕ, by the multivariate normalized, quasi-interpolation, Kantorovich type and quadrature type neural network ...
Anastassiou George A.
doaj +1 more source
Continuity of iteration and approximation of iterative roots
Journal of Computational and Applied Mathematics, 2011 Let \(I = [a,b] \subset \mathbb{R}\). We define \(C(I)\) to be the set of continuous functions \(f: I \to I\). It is proved that the operator \(T_{n}: C(I) \to C(I)\), where \(T_{n}f = f^{n}, f^{0}(x) = x, f^{k}(x) = f(f^{k-1}(x))\) for \(x \in I, f \in C(I)\) and \(k = 1, 2,\dots,n\), is continuous with respect to the supremum metric.
Wenmeng Zhang, Weinian Zhang
openaire +1 more source
Iterative Approximate Cross-Validation
, 2023 Cross-validation (CV) is one of the most popular tools for assessing and selecting predictive models. However, standard CV suffers from high computational cost when the number of folds is large. Recently, under the empirical risk minimization (ERM) framework, a line of works proposed efficient methods to approximate CV based on the solution of the ERM ...
Yuetian Luo, Zhimei Ren, Rina Barber
openaire +3 more sources
A novel iterative convex approximation method [PDF]
2015 IEEE 6th International Workshop on Computational Advances in Multi-Sensor Adaptive Processing (CAMSAP), 2015 In this paper, we propose a novel iterative algorithm based on convex approximation for a large class of possibly nonconvex optimization problems. The stationary points of the original problem are found by solving a sequence of successively refined approximate problems.
Yang Yang 0033, Marius Pesavento
openaire +3 more sources