PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Policy Learning for Motor Skills
Jan Peters and Stefan Schaal
In: 14th International Conference on Neural Information Processing (ICONIP), 13-16. November, 2007, Kitakyushu, Japan.

Abstract

Policy learning which allows autonomous robots to adapt to novel situations has been a long standing vision of robotics, artificial intelligence, and cognitive sciences. However, to date, learning techniques have yet to fulfill this promise as only few methods manage to scale into the high-dimensional domains of manipulator robotics, or even the new upcoming trend of humanoid robotics, and usually scaling was only achieved in precisely pre-structured domains. In this paper, we investigate the ingredients for a general approach policy learning with the goal of an application to motor skill refinement in order to get one step closer towards human-like performance. For doing so, we study two major components for such an approach, i.e., firstly, we study policy learning algorithms which can be applied in the general setting of motor skill learning, and, secondly, we study a theoretically well-founded general approach to representing the required control structures for task representation and execution.

EPrint Type:Conference or Workshop Item (Paper)
Project Keyword:Foo Project
Subjects:Learning/Statistics & Optimisation
Haptics
ID Code:3587
Deposited By:Jan Peters
Deposited On:13 February 2008