Konferenzpaper | 2017 | Peer reviewed

A Deep Reinforcement Learning Based Model Supporting Object Familiarization

Autor(en)

Panzner, Maximilian ; Cimiano, Philipp

Titel des Konferenzbandes

Proceedings of the 7th Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics

Name der Konferenz

International Conference on Development and Learning and on Epigenetic Robotics

DOI

10.1109/DEVLRN.2017.8329828

URN

urn:nbn:de:0070-pub-29119749

URL

https://pub.uni-bielefeld.de/record/2911974

Weitere Details

Sprache

englisch

Darstellungsform

Text

Link zum Volltext (intern)

https://pub.uni-bielefeld.de/record/2911974

DDC

000

An important ability of cognitive systems is the ability to familiarize themselves with the properties of objects and their environment as well as to develop an understanding of the consequences of their own actions on physical objects. Developing developmental approaches that allow cognitive systems to familiarize with objects in this sense via guided self-exploration is an important challenge within the field of developmental robotics.
In this paper we present a novel approach that allows cognitive systems to familiarize themselves with the properties of objects and the effects of their actions on them in a self-exploration fashion. Our approach is inspired by developmental studies that hypothesize that infants have a propensity to systematically explore the connection between their own actions and the perceptual consequences in order to support inter-modal calibration of their bodies.
We propose a reinforcement-based approach operating in a continuous state space in which the function predicting cumulated future rewards is learned via a deep Q-network. We investigate the impact of the structure of rewards, the impact of different regularization approaches as well as the impact of different exploration strategies.

Zitierstile

Panzner M, Cimiano P. A Deep Reinforcement Learning Based Model Supporting Object Familiarization. In: Proceedings of the 7th Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics. Lisbon, Portugal; 2017.

In die Zwischenablage einfügen

Panzner, M., & Cimiano, P. (2017). A Deep Reinforcement Learning Based Model Supporting Object Familiarization. Proceedings of the 7th Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics Lisbon, Portugal. doi:10.1109/DEVLRN.2017.8329828

In die Zwischenablage einfügen

Panzner, Maximilian, and Cimiano, Philipp. 2017. “A Deep Reinforcement Learning Based Model Supporting Object Familiarization”. In Proceedings of the 7th Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics. Lisbon, Portugal.

In die Zwischenablage einfügen

Panzner, M., and Cimiano, P. (2017). “A Deep Reinforcement Learning Based Model Supporting Object Familiarization” in Proceedings of the 7th Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics (Lisbon, Portugal).

In die Zwischenablage einfügen

Panzner, M., & Cimiano, P., 2017. A Deep Reinforcement Learning Based Model Supporting Object Familiarization. In Proceedings of the 7th Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics. Lisbon, Portugal.

In die Zwischenablage einfügen

M. Panzner and P. Cimiano, “A Deep Reinforcement Learning Based Model Supporting Object Familiarization”, Proceedings of the 7th Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics, Lisbon, Portugal: 2017.

In die Zwischenablage einfügen

Panzner, M., Cimiano, P.: A Deep Reinforcement Learning Based Model Supporting Object Familiarization. Proceedings of the 7th Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics. Lisbon, Portugal (2017).

In die Zwischenablage einfügen

Panzner, Maximilian, and Cimiano, Philipp. “A Deep Reinforcement Learning Based Model Supporting Object Familiarization”. Proceedings of the 7th Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics. Lisbon, Portugal, 2017.

AMA

APA (6th ed.)

Chicago

Frontiers

Harvard

IEEE

LNCS

MLA