@article{oai:mie-u.repo.nii.ac.jp:00006445,
 author = {Shibata, Nobuo and Matsui, Hirokazu},
 issue = {2},
 journal = {Proceedings of the Second International Workshop on Regional Innovation Studies :  (IWRIS2010)},
 month = {Oct},
 note = {application/pdf, The reduction on the trial frequency is
important for reinforcement learning under an actual
environment.
We propose the Q-learning method that selects proper
actions of robot in unknown environment by using the Self-
Instruction based on the experience in known environment.
Concretely, it has two Q-tables, one is smaller, based on a
partial space of the environment, the other is larger, based on
the whole space of the environment. At each learning step, Qvalues
of these Q-tables are updated at the same time, but an
action is selected by using Q-table that has smaller entropy of
Q-values at the situation. We think that the smaller Q-table is
used for the knowledge storing as self-instructing. The larger is
used for the experiment storing.
We experimented the proposed method with using an actual
mobile robot. In the experimental environment, exist a mobile
robot, two goals and one of a red, a green, a yellow and a blue
object. The robot has a task to carry a colored object into the
corresponding goal. In this experiment, the Q-table for the
whole has a state for the view of the object and the goals with
the colors, the Q-table for the partial has the state without
color information. We verified that the proposed method is
more effective than the ordinaries in an actual environment.},
 pages = {71--74},
 title = {Reinforcement Learning with dual tables for a partial and a whole space},
 year = {2011}
}