direkt zum Inhalt springen

direkt zum Hauptnavigationsmenü

Sie sind hier

TU Berlin

Inhalt des Dokuments

Book Chapters

Autonomous Learning of State Representations for Control: An Emerging Field Aims to Autonomously Learn State Representations for Reinforcement Learning Agents from Their Real-World Sensor Observations
Citation key Boehmer2015c
Author Böhmer, W. and Springenberg, J. T. and Boedecker, J. and Riedmiller, M. and Obermayer, K.
Title of Book Künstliche Intelligenz
Pages 353-362
Year 2015
ISSN 0933-1875, 1610-1987
DOI 10.1007/s13218-015-0356-1
Volume 29
Number 4
Publisher Springer Berlin Heidelberg
Series Technical Contribution
Abstract This article reviews an emerging field that aims for autonomous reinforcement learning (RL) directly on sensor-observations. Straightforward end-to-end RL has recently shown remarkable success, but relies on large amounts of samples. As this is not feasible in robotics, we review two approaches to learn intermediate state representations from previous experiences: deep auto-encoders and slow-feature analysis. We analyze theoretical properties of the representations and point to potential improvements.
Link to original publication Download Bibtex entry

Zusatzinformationen / Extras

Quick Access:

Schnellnavigation zur Seite über Nummerneingabe

Auxiliary Functions