Frank, Mikhail Alexander and Leitner, Juergen and Stollenga, Marijn and Foerster, Alexander Uwe and Schmidhuber, Juergen (2014) Curiosity driven reinforcement learning for motion planning on humanoids. Frontiers in Neurorobotics, 7 (25). ISSN 1662-5218
|
Text
fnbot-07-00025.pdf - Published Version Download (1MB) | Preview |
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.
| Item Type: | Scientific journal article, Newspaper article or Magazine article |
|---|---|
| Uncontrolled Keywords: | artificial curiosity; embodied AI; humanoid; iCub; intrinsic motivation; reinforcement learning |
| Subjects: | Engineering > Electronic & electrical engineering > Robotics & cybernetics > Robotics Computer sciences > Artificial intelligence |
| Department/unit: | Dipartimento tecnologie innovative > Istituto Dalle Molle di studi sull’intelligenza artificiale USI-SUPSI |
| Depositing User: | Juergen Leitner |
| Date Deposited: | 14 Mar 2014 07:46 |
| Last Modified: | 19 May 2016 12:49 |
| URI: | http://repository.supsi.ch/id/eprint/4254 |
Actions (login required)
 |
View Item |