Author
Kober, J., Wilhelm, A., Öztop, Erhan, Peters, J.
Publication Date
2012-11
Publication Place
-
Springer Science+Business Media
Subject
Skill learning, Motor primitives, Reinforcement learning, Meta-parameters, Policy learning
Type
Periodical
Language
English
Digital
Yes
Manuscript
No
Library
Özyeğin University
Library Asset ID
1573-7527
Record ID
1a72cfbd-4fb3-4174-8e3b-f2865b40443d
Library Location
Computer Science
Date
2012-11
Notes
European Community
Sample Text
Humans manage to adapt learned movements very quickly to new situations by generalizing learned behaviors from similar situations. In contrast, robots currently often need to re-learn the complete movement. In this paper, we propose a method that learns to generalize parametrized motor plans by adapting a small set of global parameters, called meta-parameters. We employ reinforcement learning to learn the required meta-parameters to deal with the current situation, described by states. We introduce an appropriate reinforcement learning algorithm based on a kernelized version of the reward-weighted regression. To show its feasibility, we evaluate this algorithm on a toy example and compare it to several previous approaches. Subsequently, we apply the approach to three robot tasks, i.e., the generalization of throwing movements in darts, of hitting movements in table tennis, and of throwing balls where the tasks are learned on several different real physical robots, i.e., a Barrett WAM, a BioRob, the JST-ICORP/SARCOS CBi and a Kuka KR 6.
DOI
10.1007/s10514-012-9290-3
Cilt
33
