Informatics Report Series



Related Pages

Report (by Number) Index
Report (by Date) Index
Author Index
Institute Index

Title:Could Active Perception Aid Navigation of Partially Observable Grid Worlds?
Authors: Paul Crook ; Gillian Hayes
Date:Sep 2003
Publication Title:Proceedings of ECML 2003 (European Conference on Machine Learning)
Publication Type:Conference Paper Publication Status:Published
Volume No:# 2837 Page Nos:72-83
Due to the unavoidable fact that a robot's sensors will be limited in some manner, it is entirely possible that it can find itself unable to distinguish between differing states of the world (the world is in effect partially observable). If reinforcement learning is used to train the robot, then this confounding of states can have a serious effect on its ability to learn optimal and stable policies. Good results have been achieved by enhancing reinforcement learning algorithms through the addition of memory or the use of internal models. In our work we take a different approach and consider whether active perception could be used instead. We test this using omniscient oracles, who play the role of a robot's active perceptual system, in a simple grid world navigation problem. Our results indicate that simple reinforcement learning algorithms can learn when to consult these oracles, and as a result learn optimal policies.
2003 by Springer-Verlag; publication rights retained by University of Edinburgh for academic and research purposes
Links To Paper
No links available
Bibtex format
author = { Paul Crook and Gillian Hayes },
title = {Could Active Perception Aid Navigation of Partially Observable Grid Worlds?},
book title = {Proceedings of ECML 2003 (European Conference on Machine Learning)},
publisher = {Springer},
year = 2003,
month = {Sep},
volume = {# 2837},
pages = {72-83},

Home : Publications : Report 

Please mail <> with any changes or corrections.
Unless explicitly stated otherwise, all material is copyright The University of Edinburgh