A Sarsa(<i>λ</i>) Algorithm Based on Double-Layer Fuzzy Reasoning

<table>Changes of the pole angle <svg height="12.4375" id="M305" style="vertical-align:-0.1638pt" version="1.1" viewbox="0 0 8.5874996 12.4375" width="8.5874996" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink">
<g transform="matrix(.017,-0,0,-.017,.062,12.162)"><path d="M475 507q0 -83 -20 -172t-56 -167.5t-93.5 -129t-125.5 -50.5q-157 0 -157 227q0 78 21.5 164t59 161t96.5 123.5t126 48.5q79 0 114 -58t35 -147zM391 522q0 155 -81 155q-62 0 -111 -82.5t-73 -200.5h253q12 81 12 128zM373 346h-255q-12 -91 -12 -150q0 -72 20 -123
t63 -51q34 0 64 28.5t52.5 77t39 103t28.5 115.5z" id="x1D703"></path></g>
</svg> when using the two mentioned algorithms, respectively.</table>

Mathematical Problems in Engineering

A Sarsa(λ) Algorithm Based on Double-Layer Fuzzy Reasoning

Figure 8