A Deep Reinforcement Learning Based Model Supporting Object Familiarization

Panzner M, Cimiano P (2017)
In: Proceedings of the 7th Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics. Lisbon, Portugal.

Download
OA
Conference Paper | Published | English
Abstract
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.
Publishing Year
Conference
International Conference on Development and Learning and on Epigenetic Robotics
Location
Instituto Superior Tecnico (IST), Lisbon, Portugal
Conference Date
2017-09-18 – 2017-09-21
PUB-ID

Cite this

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.
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.
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).
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.
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.
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).
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.
All files available under the following license(s):
Copyright Statement:
This Item is protected by copyright and/or related rights. [...]
Main File(s)
File Name
Access Level
OA Open Access
Last Uploaded
2017-10-02T08:37:25Z

This data publication is cited in the following publications:
This publication cites the following data publications:

Export

0 Marked Publications

Open Data PUB

Search this title in

Google Scholar