Neural reinforcement learning for behaviour synthesis - Aix-Marseille Université Access content directly
Journal Articles Robotics and Autonomous Systems Year : 1997

Neural reinforcement learning for behaviour synthesis

Abstract

We present the results of a research aimed at improving the Q-learning method through the use of artificial neural networks. Neural implementations are interesting due to their generalisation ability. Two implementations are proposed: one with a competitive multilayer perceptron and the other with a self-organising map. Results obtained on a task of learning an obstacle avoidance behaviour for the mobile miniature robot Khepera show that this last implementation is very effective, learning more than 40 times faster than the basic Q-learning implementation. These neural implementations are also compared with several Q-learning enhancements, like the Q-learning with Hamming distance, Q-learning with statistical clustering and Dyna-Q.
Fichier principal
Vignette du fichier
Jars_97(1).pdf (472.86 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01337989 , version 1 (27-06-2016)

Identifiers

Cite

Claude Touzet. Neural reinforcement learning for behaviour synthesis. Robotics and Autonomous Systems, 1997, ⟨10.1016/S0921-8890(97)00042-0⟩. ⟨hal-01337989⟩

Collections

CNRS UNIV-AMU LNIA
88 View
649 Download

Altmetric

Share

Gmail Facebook X LinkedIn More