Emergence of Prediction by Reinforcement Learning Using a Recurrent Neural Network

<table>Correlation between the number of steps until catching the object in the invisibility area and the output of the 12th hidden neuron. The output varies according to the direction of motion and velocity of the object, although the number of steps until the catch is the same.</table>

Journal of Robotics

fig15

Figure 15

Figure 15: Emergence of Prediction by Reinforcement Learning Using a Recurrent Neural Network 