A k-NN based perception scheme for reinforcement learning

Authors:
H. José Antonio Martín;Javier De Lope
Affiliations:
Dep. Sistemas Informáticos y Computación, Universidad Complutense de Madrid;Dept. of Applied Intelligent Systems, Universidad Politécnica de Madrid
Venue:
EUROCAST'07 Proceedings of the 11th international conference on Computer aided systems theory
Year:
2007

Citing 2
Cited 2

Technical Note: \cal Q-Learning

Machine Learning
Introduction to Reinforcement Learning

Introduction to Reinforcement Learning

The kNN-TD Reinforcement Learning Algorithm

IWINAC '09 Proceedings of the 3rd International Work-Conference on The Interplay Between Natural and Artificial Computation: Part I: Methods and Models in Artificial and Natural Computation. A Homage to Professor Mira's Scientific Legacy
Robust high performance reinforcement learning through weighted k-nearest neighbors

Neurocomputing

Quantified Score

Hi-index	0.00

Visualization

Abstract

A perception scheme for Reinforcement Learning (RL) is developed as a function approximator. The main motivation for the development of this scheme is the need for generalization when the problem to be solved has continuous state variables. We propose a solution to the generalization problem in RL algorithms using a k-nearest-neighbor pattern classification (k-NN). By means of the k-NN technique we investigate the effect of collective decision making as a mechanism of perception and actionselection and a sort of back-propagation of its proportional influence in the action-selection process as the factor thatmoderate the learning of each decision making unit. Avery well known problemis presented as a case study to illustrate the results of this k-NN based perception scheme.