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

Zusammenfassung
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.
  • Vollständige Referenz
  • BibTeX
Böhmer, W., Springenberg, J. T., Boedecker, J., Riedmiller, M. & Obermayer, K., (2015). 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.   KI - Künstliche Intelligenz: Vol. 29, No. 4. Springer. (S. 353-362). DOI: 10.1007/s13218-015-0356-1
@article{mci/Böhmer2015,
author = {Böhmer, Wendelin AND Springenberg, Jost Tobias AND Boedecker, Joschka AND Riedmiller, Martin AND Obermayer, Klaus},
title = {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},
journal = {KI - Künstliche Intelligenz},
volume = {29},
number = {4},
year = {2015},
,
pages = { 353-362 } ,
doi = { 10.1007/s13218-015-0356-1 }
}

Sollte hier kein Volltext (PDF) verlinkt sein, dann kann es sein, dass dieser aus verschiedenen Gruenden (z.B. Lizenzen oder Copyright) nur in einer anderen Digital Library verfuegbar ist. Versuchen Sie in diesem Fall einen Zugriff ueber die verlinkte DOI: 10.1007/s13218-015-0356-1

Haben Sie fehlerhafte Angaben entdeckt? Sagen Sie uns Bescheid: Feedback abschicken