An Empirical Investigation of Transfer Effects for Reinforcement Learning

<table class="table-group" id="tab5"><tr><td><table class="table"><tr><td class="thead-hr" colspan="5"><hr/></td></tr><tr class="thead"><td class="align_left">Average item</td><td class="align_center"><i>n</i> = 5</td><td class="align_center"><i>n</i> = 6</td><td class="align_center"><i>n</i> = 7</td><td class="align_center"><i>n</i> = 8</td></tr><tr><td class="thead-hr" colspan="5"><hr/></td></tr><tr><td class="align_left">Ratio_Tr_Steps</td><td class="align_center">4.12</td><td class="align_center">2.26</td><td class="align_center">2.07</td><td class="align_center">1.65</td></tr><tr><td class="align_left">Ratio_Br_Capacity</td><td class="align_center">1.08</td><td class="align_center">1.18</td><td class="align_center">1.06</td><td class="align_center">0.85</td></tr><tr class="table-tr"><td colspan="5"><hr class="tbody-hr"/></td></tr></table></td></tr></table>

<div>The averages of Ratio_Tr_Steps and Ratio_Br_Capacity for different <i>n</i>.</div>

Computational Intelligence and Neuroscience

tab5

Table 5

Table 5: An Empirical Investigation of Transfer Effects for Reinforcement Learning 