Nature

Function Approximation and Sobolev Spaces

Function approximation, a central theme in numerical analysis and applied mathematics, seeks to represent complex functions through simpler or more computationally tractable forms. In this context, ...
IEEE

Nonlinear Value Function Approximation Method with Easy Hyperparameter Tuning and Convergence Guarantee

Abstract: Reinforcement Learning is a branch of machine learning to learn control strategies that achieve a given objective through trial-and-error in the environment ...
GitHub

Function-approximation-with-the-help-of-genetic-programming

One of the issues raised in mathematical sciences and engineering is function approximation. Approximation of the function means to approximate the mathematical rule of the said function by having the ...
IEEE

Toward General Function Approximation in Nonstationary Reinforcement Learning

Abstract: Function approximation has experienced significant success in the field of reinforcement learning (RL). Despite a handful of progress on developing theory for nonstationary RL with function ...
GitHub

Gaussian-Process-Regression-and-Bayesian-Optimization-for-Function-Approximation

Polynomial Regression and Non-Parametric Prediction,Gaussian Process Regression and Bayesian Optimization,Enhanced Bayesian Optimization,,RBF Kernel and Invertibility Check, This project involves four ...
www.cs.utexas.edu

Function Approximation via Tile Coding: Automating Parameter Choice (2005)

Reinforcement learning (RL) is a powerful abstraction of sequential decision making that has an established theoretical foundation and has proven effective in a variety of small, simulated domains.