Q-value Additional Updating Method for Reducing Learning Time

In this paper, an update method of Q-value is proposed to increase the learning rate of Q-learning. When Q-value of executed action is small, even if it is an optimal action, the learning becomes longer because the frequency to be executed again becomes lower. The proposed method increased the execution frequency of optimal action by forcefully increasing the Q-value through the Q-value update method. In the test, up to 60% higher goal achievement rate was shown at a maximum.