Community Research and Development Information Service - CORDIS

Abstract

A connectionist approach to robot path finding has been devised so as to avoid some of the bottlenecks of algebraic and heuristic approaches, namely construction of configuration space, discretisation and step predetermination. The approach relies on reinforcement learning. In order to identify the learning rule within this paradigm that best suits the problem at hand, an experimental comparison of 13 different such rules has been carried out. The most promising rule has been shown to be that using predicted comparison as reinforcement baseline, and the Hebbian formula as eligibility factor.

Additional information

Authors: MILLAN J DEL R, JRC Ispra (IT);TORRAS C, Institut de Cibernètica, Barcelona (ES)
Bibliographic Reference: Paper presented: Cognitiva-90, Madrid (ES), Nov. 21-23, 1990
Availability: Available from (1) as Paper EN 35869 ORA
Record Number: 199110136 / Last updated on: 1994-12-02
Category: PUBLICATION
Original language: en
Available languages: en