Curiosity driven reinforcement learning for motion planning on humanoids

Mikhail Frank, Jurgen Leitner, Marijn Stollenga, Alexander Forster, Jurgen Schmidhuber

Research output: Contribution to journalArticlepeer-review

46 Scopus citations

Abstract

Most previous work on artificial curiosity (AC) and intrinsic motivation focuses on basic concepts and theory. Experimental results are generally limited to toy scenarios, such as navigation in a simulated maze, or control of a simple mechanical system with one or two degrees of freedom. To study AC in a more realistic setting, we embody a curious agent in the complex iCub humanoid robot. Our novel reinforcement learning (RL) framework consists of a state-of-the-art, low-level, reactive control layer, which controls the iCub while respecting constraints, and a high-level curious agent, which explores the iCub's state-action space through information gain maximization, learning a world model from experience, controlling the actual iCub hardware in real-time. To the best of our knowledge, this is the first ever embodied, curious agent for real-time motion planning on a humanoid. We demonstrate that it can learn compact Markov models to represent large regions of the iCub's configuration space, and that the iCub explores intelligently, showing interest in its physical constraints as well as in objects it finds in its environment.
Original languageEnglish (US)
JournalFrontiers in Neurorobotics
Volume7
Issue numberJAN
DOIs
StatePublished - Jan 1 2014
Externally publishedYes

ASJC Scopus subject areas

  • Biomedical Engineering
  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'Curiosity driven reinforcement learning for motion planning on humanoids'. Together they form a unique fingerprint.

Cite this