Constructing Temporally Extended Actions through Incremental Community Detection

<table class="figure-group"><tr class="fig-image" id="a"><td><object data="https://static.hindawi.com/articles/cin/volume-2018/2085721/figures/2085721.fig.005a.svgz" name="2085721.fig.005a" type="image/svg+xml"></object></td></tr><tr class="fig-caption"><td><b>(a) </b>Modularity changes in Pac-Directional</td></tr><tr class="fig-image" id="b"><td><object data="https://static.hindawi.com/articles/cin/volume-2018/2085721/figures/2085721.fig.005b.svgz" name="2085721.fig.005b" type="image/svg+xml"></object></td></tr><tr class="fig-caption"><td><b>(b) </b>Modularity changes in Pac-Random</td></tr></table>

<div>Modularity changes of incremental-option learning in small-scale Pac-Man problem. Comparison of the presented rule-based revision method with iteratively calling Louvain algorithm. Shadow areas denote standard deviation value.</div>

Computational Intelligence and Neuroscience

fig5

Figure 5

Figure 5: Constructing Temporally Extended Actions through Incremental Community Detection 