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

Table 6

Some hyperparameters used in the study.

Hyperparameters	Value assigned
Number of qubits	4
Number of layers	2, 3, 5
Epsilon	1
Batch size	5
Maximum time step	3000
Maximum episode	1000
Gamma	0.99
Alpha	0.1, 0.2, 0.3, 0.4
Learning rate	0.01
eps	1e − 08