Reducing Entropy Overestimation in Soft Actor Critic Using Dual Policy Network

<table class="figure-group"><tr class="fig-image" id="a"><td><object data="https://static.hindawi.com/articles/wcmc/volume-2021/9920591/figures/9920591.fig.003a.svgz" name="9920591.fig.003a" type="image/svg+xml"></object></td></tr><tr class="fig-caption"><td><b>(a) </b>Ant-v2 image</td></tr><tr class="fig-image" id="b"><td><object data="https://static.hindawi.com/articles/wcmc/volume-2021/9920591/figures/9920591.fig.003b.svgz" name="9920591.fig.003b" type="image/svg+xml"></object></td></tr><tr class="fig-caption"><td><b>(b) </b>HalfCheetah-v2 image</td></tr><tr class="fig-image" id="c"><td><object data="https://static.hindawi.com/articles/wcmc/volume-2021/9920591/figures/9920591.fig.003c.svgz" name="9920591.fig.003c" type="image/svg+xml"></object></td></tr><tr class="fig-caption"><td><b>(c) </b>Hopper-v2 image</td></tr><tr class="fig-image" id="d"><td><object data="https://static.hindawi.com/articles/wcmc/volume-2021/9920591/figures/9920591.fig.003d.svgz" name="9920591.fig.003d" type="image/svg+xml"></object></td></tr><tr class="fig-caption"><td><b>(d) </b>Walker-v2 image</td></tr></table>

<div>Four environments used in our experiments.</div>

Wireless Communications and Mobile Computing

fig3

Figure 3

Figure 3: Reducing Entropy Overestimation in Soft Actor Critic Using Dual Policy Network 