Q-learning, a most widely used reinforcement learning method, normally needs well-deffined quantized state and action spaces
to con- verge. This makes it difficult to be applied to real robot tasks because of poor performance of learned behavior and
further a new problem of state space construction. We have proposed Continuous Valued Q-learning for real robot applications,
which calculates contribution values to estimate a continuous action value in order to make motion smooth and effective
This paper proposes an improvement of the previous work, which shows a better performance of desired behavior than the previous
one, with roughly quantized state and action. To show the validity of the method, we applied the method to a vision-guided
mobile robot of which task is to chase a ball.
Acknowledgments We would like to thank Shoichi Noda (Displays, Hitachi Ltd., Japan) for fruitful discussions about modification of the CVQ-learning.