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

Daniel Tanneberg, Jan Peters, Elmar Rueckert

Research output: Contribution to journalArticleResearchpeer-review

5 Citations (Scopus)


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.
Original languageEnglish
Pages (from-to)67-80
Number of pages14
JournalNeural networks
Issue numberJanuary
Early online date22 Oct 2018
Publication statusPublished - Jan 2019
Externally publishedYes

Bibliographical note

Publisher Copyright: © 2018 Elsevier Ltd


  • Autonomous robots
  • Experience replay
  • Intrinsic motivation
  • Neural sampling
  • Online learning
  • Spiking recurrent networks

Cite this