Investigating the Effects of Hyperparameters in Quantum-Enhanced Deep Reinforcement Learning

Figure 5

The timestep comparison for different learning rates: (a) time step with 0.1 alpha value, (b) time step with 0.2 alpha value, (c) time step with 0.3 alpha value, and (d) time step with 0.4 alpha value.

(a)

(b)

(c)

(d)