Making use of unelaborated advice to improve reinforcement learning: a mobile robotics approach

Authors:
David L. Moreno;Carlos V. Regueiro;Roberto Iglesias;Senén Barro
Affiliations:
Dpto. Electrónica y Computación, Universidad de Santiago de Compostela, Santiago de Compostela, Spain;Departamento Electrónica y Sistemas, Universidad de A Coruña, A Coruña, Spain;Dpto. Electrónica y Computación, Universidad de Santiago de Compostela, Santiago de Compostela, Spain;Dpto. Electrónica y Computación, Universidad de Santiago de Compostela, Santiago de Compostela, Spain
Venue:
ICAPR'05 Proceedings of the Third international conference on Advances in Pattern Recognition - Volume Part I
Year:
2005

Citing 5
Cited 0

Training stochastic model recognition algorithms as networks can lead to maximum mutual information estimation of parameters

Advances in neural information processing systems 2
Self-Improving Reactive Agents Based on Reinforcement Learning, Planning and Teaching

Machine Learning
A teaching method for reinforcement learning

ML92 Proceedings of the ninth international workshop on Machine learning
Continuous-Action Q-Learning

Machine Learning
Supervised Reinforcement Learning: Application to a Wall Following Behaviour in a Mobile Robot

IEA/AIE '98 Proceedings of the 11th International Conference on Industrial and Engineering Applications of Artificial In telligence and Expert Systems: Tasks and Methods in Applied Artificial Intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

Reinforcement Learning (RL) is thought to be an appropriate paradigm for acquiring control policies in mobile robotics. However, in its standard formulation (tabula rasa) RL must explore and learn everything from scratch, which is neither realistic nor effective in real-world tasks. In this article we use a new strategy, called Supervised Reinforcement Learning (SRL), that allows the inclusion of external knowledge within this type of learning. We validate it by learning a wall-following behaviour and testing it on a Nomad 200 robot. We show that SRL is able to take advantage of multiple sources of knowledge and even from partially erroneous advice, features that allow a SRL agent to make use of a wide range of prior knowledge without the need for a complex or time-consuming elaboration.