Intrinsic Motivation and Mental Replay enable Efficient Online Adaptation in Stochastic Recurrent Networks

Type of publication:  Artikel
Publikationsstatus: Veröffentlicht
Zeitschrift: Neural Networks - Elsevier
Band: 109
Jahr: 2019
Seiten: 67-80
Notiz: Impact Factor of 7.197 (2017)
ISSN: 0893-6080
DOI: 10.1016/j.neunet.2018.10.005
Abriss: 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.
Schlagworte: Autonomous robots, Experience replay, Intrinsic motivation, Neural sampling, Online learning, Spiking recurrent networks
Autoren: Tanneberg, Daniel
Peters, Jan
Rueckert, Elmar