IoT-Based Reinforcement Learning Using Probabilistic Model for Determining Extensive Exploration through Computational Intelligence for Next-Generation Techniques

Table 1

Hyperparameters.

Hyperparameters	Value
Discount parameters	0.99
Batch size	128
Memory pool capacity	100
Number of learners	10
Parameter prior mean	0
Parameter prior variance	10
Sampling interval	20
Target network update interval	20