Learn how to balance the complexity and interpretability of your function approximation methods, such as linear, nonlinear, or deep neural networks, in reinforcement learning.

In this paper an incremental learning algorithm for function approximation is presented. The algorithm utilizes the current training pattern to generate an approximately learned function with minimum ...

A constructive function approximation approach is proposed for adaptive learning control which handles finite interval tracking problems. Unlike the well established adaptive neural control which uses ...

This project evaluates and compares different value function approximation methods in Reinforcement Learning using a range of parametric and non-parametric function approximation models. The ...

Keywords: deep learning, function approximation, manifold learning, neural networks, local approximation Citation: Chui CK and Mhaskar HN (2018) Deep Nets for Local Manifold Learning.

Reinforcement Learning with Function Approximation Overview This repository contains the implementation of an agent designed to complete an episodic Markov Decision Process (MDP) task within the ...

We present a fully implemented instantiation of evolutionary function approximation which combines NEAT, a neuroevolutionary optimization technique, with Q-learning, a popular TD method. The resulting ...