Reinforcement Learning Guided by Double Replay Memory

<table class="figure-group"><tr class="fig-image" id="a"><td><object data="https://static.hindawi.com/articles/js/volume-2021/6652042/figures/6652042.fig.002a.svgz" name="6652042.fig.002a" type="image/svg+xml"></object></td></tr><tr class="fig-caption"><td><b>(a) </b>TD-error</td></tr><tr class="fig-image" id="b"><td><object data="https://static.hindawi.com/articles/js/volume-2021/6652042/figures/6652042.fig.002b.svgz" name="6652042.fig.002b" type="image/svg+xml"></object></td></tr><tr class="fig-caption"><td><b>(b) </b>Sample weight</td></tr></table>

<div>Absolute value of TD-error (a) and sample weight (b) in CartPole.</div>

Journal of Sensors

fig2

Figure 2

Figure 2: Reinforcement Learning Guided by Double Replay Memory 