Performance Evaluation of Multiagent Reinforcement Learning Based Training Methods for Swarm Fighting

<table class="figure-group"><tr class="fig-image" id="a"><td><object data="https://static.hindawi.com/articles/wcmc/volume-2022/5340517/figures/5340517.fig.003a.svgz" name="5340517.fig.003a" type="image/svg+xml"></object></td></tr><tr class="fig-caption"><td><b>(a) </b>Swarm fighting starts</td></tr><tr class="fig-image" id="b"><td><object data="https://static.hindawi.com/articles/wcmc/volume-2022/5340517/figures/5340517.fig.003b.svgz" name="5340517.fig.003b" type="image/svg+xml"></object></td></tr><tr class="fig-caption"><td><b>(b) </b>Green team is attacking</td></tr><tr class="fig-image" id="c"><td><object data="https://static.hindawi.com/articles/wcmc/volume-2022/5340517/figures/5340517.fig.003c.svgz" name="5340517.fig.003c" type="image/svg+xml"></object></td></tr><tr class="fig-caption"><td><b>(c) </b>Three agents are killed</td></tr><tr class="fig-image" id="d"><td><object data="https://static.hindawi.com/articles/wcmc/volume-2022/5340517/figures/5340517.fig.003d.svgz" name="5340517.fig.003d" type="image/svg+xml"></object></td></tr><tr class="fig-caption"><td><b>(d) </b>Three agents remain</td></tr><tr class="fig-image" id="e"><td><object data="https://static.hindawi.com/articles/wcmc/volume-2022/5340517/figures/5340517.fig.003e.svgz" name="5340517.fig.003e" type="image/svg+xml"></object></td></tr><tr class="fig-caption"><td><b>(e) </b>The green team surrounds the red team</td></tr><tr class="fig-image" id="f"><td><object data="https://static.hindawi.com/articles/wcmc/volume-2022/5340517/figures/5340517.fig.003f.svgz" name="5340517.fig.003f" type="image/svg+xml"></object></td></tr><tr class="fig-caption"><td><b>(f) </b>The green team wins</td></tr></table>

<div>The whole process of a single round of swarm fighting.</div>

Wireless Communications and Mobile Computing

fig3

Figure 3

Figure 3: Performance Evaluation of Multiagent Reinforcement Learning Based Training Methods for Swarm Fighting 