TU Darmstadt / ULB / TUprints

Intrinsic motivation and mental replay enable efficient online adaptation in stochastic recurrent networks

Tanneberg, Daniel ; Peters, Jan ; Rueckert, Elmar (2022)
Intrinsic motivation and mental replay enable efficient online adaptation in stochastic recurrent networks.
In: Neural Networks, 2022, 109
doi: 10.26083/tuprints-00020537
Article, Secondary publication, Postprint

[img] Text
1802.08013.pdf
Copyright Information: CC BY-NC-ND 4.0 International - Creative Commons, Attribution NonCommercial, NoDerivs.

Download (4MB)
Item Type: Article
Type of entry: Secondary publication
Title: Intrinsic motivation and mental replay enable efficient online adaptation in stochastic recurrent networks
Language: English
Date: 2022
Place of Publication: Darmstadt
Year of primary publication: 2022
Publisher: Elsevier
Journal or Publication Title: Neural Networks
Volume of the journal: 109
Collation: 18 Seiten
DOI: 10.26083/tuprints-00020537
Corresponding Links:
Origin: Secondary publication service
Abstract:

Autonomous robots need to interact with unknown, unstructured and changing environments, constantly facing novel challenges. Therefore, continuous online adaptation for lifelong-learning and the need of sample-efficient mechanisms to adapt to changes in the environment, the constraints, the tasks, or the robot itself are crucial. In this work, we propose a novel framework for probabilistic online motion planning with online adaptation based on a bio-inspired stochastic recurrent neural network. By using learning signals which mimic the intrinsic motivation signal cognitive dissonance in addition with a mental replay strategy to intensify experiences, the stochastic recurrent network can learn from few physical interactions and adapts to novel environments in seconds. We evaluate our online planning and adaptation framework on an anthropomorphic KUKA LWR arm. The rapid online adaptation is shown by learning unknown workspace constraints sample-efficiently from few physical interactions while following given way points.

Uncontrolled Keywords: Intrinsic motivation, Online learning, Experience replay, Autonomous robots, Spiking recurrent networks, Neural sampling
Status: Postprint
URN: urn:nbn:de:tuda-tuprints-205376
Classification DDC: 000 Generalities, computers, information > 004 Computer science
600 Technology, medicine, applied sciences > 620 Engineering and machine engineering
Divisions: 20 Department of Computer Science > Intelligent Autonomous Systems
TU-Projects: EC/H2020|640554|SKILLS4ROBOTS
Date Deposited: 18 Nov 2022 13:46
Last Modified: 24 Mar 2023 07:35
URI: https://tuprints.ulb.tu-darmstadt.de/id/eprint/20537
PPN: 506259595
Export:
Actions (login required)
View Item View Item