MACC'97 Session: RoboCup
- Applying Reinforcement Learning to a Soccer Agents' Position Problem
- Tomohito Andou
- Tokyo Institute of Technology
- Contact to: andou@is.titech.ac.jp
- Abstract
Applying reinforcement learning to a high-level and cooperative
action problem causes the following problems: 1) An agent needs to
follow its best policy for acquiring a cooperative action in spite
of the fact that the agent must reinforce various policies to leave
its local optimal policy. 2) Practicable policies of high-level
actions tend to be very few because a high-level action is much
restricted compared with a low-level action. In order to solve these
problems, this paper proposes ``observational reinforcement'' method
in which an agent guesses the optimal policy from observation and
reinforces it. This method enables an agent to reinforce various
policies while it follows its best policy, and to reinforce a
hopeful policy which is impracticable currently. We ascertained the
effectiveness of this method from experiments in the RoboCup agents'
position problem.
- keywords
reinforcement learning, multiagent, neural networks, RoboCup
-
PS
file(+gzip) (in Japanese)
Return to top page
Wed Jan 21 09:37:36 JST 1998