Skip navigation
Skip navigation

Metric State Space Reinforcement Learning for a Vision-Capable Mobile Robot

Zhumatiy, Viktor; Gomez, Faustino; Hutter, Marcus; Schmidhuber, Jürgen

Description

We address the problem of autonomously learning controllers for vision-capable mobile robots. We extend McCallum's (1995) Nearest-Sequence Memory algorithm to allow for general metrics over state-action trajectories. We demonstrate the feasibility of our approach by successfully running our algorithm on a real mobile robot. The algorithm is novel and unique in that it (a) explores...[Show more]

CollectionsANU Research Publications
Date published: 2006-03
Type: Conference paper
URI: http://hdl.handle.net/1885/15033

Download

There are no files associated with this item.


Items in Open Research are protected by copyright, with all rights reserved, unless otherwise indicated.

Updated:  12 November 2018/ Responsible Officer:  University Librarian/ Page Contact:  Library Systems & Web Coordinator