Hybrid Online and Offline Reinforcement Learning for Tibetan Jiu Chess

<table class="table-group" id="tab3"><tr><td><table class="table"><tr><td class="thead-hr" colspan="3"><hr/></td></tr><tr class="thead"><td class="align_left"> </td><td class="align_center">2D normalization off</td><td class="align_center">2D normalization on</td></tr><tr><td class="thead-hr" colspan="3"><hr/></td></tr><tr><td class="align_left">Sum</td><td class="align_center">1524</td><td class="align_center">5005</td></tr><tr><td class="align_left">Average</td><td class="align_center">13</td><td class="align_center">45</td></tr><tr class="table-tr"><td colspan="3"><hr class="tbody-hr"/></td></tr></table></td></tr></table>

<div>The number of squares with 2D normalization on or off.</div>

Complexity

tab3

Table 3

Table 3: Hybrid Online and Offline Reinforcement Learning for Tibetan Jiu Chess 