Reinforcement learning for robot soccer |
| |
Authors: | Martin Riedmiller Thomas Gabel Roland Hafner Sascha Lange |
| |
Affiliation: | 1.Department of Computer Science,Albert-Ludwigs-Universit?t Freiburg,Freiburg,Germany |
| |
Abstract: | Batch reinforcement learning methods provide a powerful framework for learning efficiently and effectively in autonomous robots.
The paper reviews some recent work of the authors aiming at the successful application of reinforcement learning in a challenging
and complex domain. It discusses several variants of the general batch learning framework, particularly tailored to the use
of multilayer perceptrons to approximate value functions over continuous state spaces. The batch learning framework is successfully
used to learn crucial skills in our soccer-playing robots participating in the RoboCup competitions. This is demonstrated
on three different case studies.
|
| |
Keywords: | Learning mobile robots Autonomous learning robots Neural control RoboCup Batch reinforcement learning |
本文献已被 SpringerLink 等数据库收录! |