Single- versus Multiobjective Optimization for Evolution of Neural Controllers in Ms. Pac-Man

<table class="table-group" id="tab3"><tr><td><table class="table"><tr><td class="thead-hr" colspan="2"><hr/></td></tr><tr class="thead"><td align="left">Proposed algorithm</td><td align="center">Number of hidden neurons</td></tr><tr><td class="thead-hr" colspan="2"><hr/></td></tr><tr><td align="left">PAESNet_F</td><td align="center">20</td></tr><tr><td align="left">PAESNet_V</td><td align="center">13</td></tr><tr><td align="left">PAESNet_M</td><td align="center">7</td></tr><tr class="table-tr"><td colspan="2"><hr class="tbody-hr"/></td></tr></table></td></tr></table>

The best evolved networks from proposed algorithms.

International Journal of Computer Games Technology

tab3

Table 3

Table 3: Single- versus Multiobjective Optimization for Evolution of Neural Controllers in Ms. Pac-Man 