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

Simple item page
dc.creatorZhumatiy, Viktor
dc.creatorGomez, Faustino
dc.creatorHutter, Marcus
dc.creatorSchmidhuber, Juergen
dc.date2006-03-07
dc.date.accessioned2026-07-07T07:05:47Z
dc.date.available2026-07-07T07:05:47Z
dc.descriptionWe 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 the environment and learns directly on a mobile robot without using a hand-made computer model as an intermediate step, (b) does not require manual discretization of the sensor input space, (c) works in piecewise continuous perceptual spaces, and (d) copes with partial observability. Together this allows learning from much less experience compared to previous methods.
dc.description14 pages, 8 figures
dc.identifierhttps://arxiv.org/abs/cs/0603023
dc.identifierhttp://arxiv.org/abs/cs/0603023
dc.identifierProc. 9th International Conf. on Intelligent Autonomous Systems (IAS 2006) pages 272-281
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/109791
dc.subjectRobotics
dc.subjectMachine Learning
dc.titleMetric State Space Reinforcement Learning for a Vision-Capable Mobile Robot
dc.typetext

Files

Collections

arXiv