The University of Edinburgh -
Division of Informatics
Forrest Hill & 80 South Bridge

MSc Thesis #93104

Title:Connectionist Reinforcement Learning in a Real Robot
Date: 1993
Abstract:This paper describes the design and implementation of an adaptive controller, based on the back-propagation algorithm, to solve a simple reinforcement learning task for a real robot vehicle. One neural network (the 'model') is trained to predict how the robot's sensor readings will change if it performs a given action; another learns, with the aid of the model, to evaluate sensory states according to how close the robot is to receiving a reward when it experiences them. The results of the project confirm that backprop can provide the learning mechanism needed to solve simple adaptive control tasks, and point up the main problems that will have to be faced before they are able to support more complicated skills. In the last chapter, I make some suggestions as to how these problems might be tackled.

[Search These Pages] [DAI Home Page] [Comment]