Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
2577006 | International Congress Series | 2006 | 4 Pages |
Abstract
Q-learning in the reinforcement learning (RL) field is a powerful and attractive tool to make robots generate autonomous behaviour. To generate a smooth trajectory with less computational cost, we propose two ingredients for Q-learning. We applied Q-learning to a simulated two-wheeled robot in order to generate trajectory for goal scoring task in robot soccer.
Related Topics
Life Sciences
Biochemistry, Genetics and Molecular Biology
Molecular Biology
Authors
Masaki Shimizu, Makoto Fujita, Hiroyuki Miyamoto,