Skip to main content
. 2020 Nov 26;14:565702. doi: 10.3389/fnbot.2020.565702

Figure 4.

Figure 4

Summary of simulation results over a constrained iteration of 3000. (A) Comparison of single reward mechanism and our proposed reward shaping function. (B) Effect of various learning rates to the overall performance (normalized root mean squared error, NRMSE). (C) Comparison of cumulative reward over iteration by each of the simulated learning rates.