Table 1.

Description of hyperparameters for $\mathcal{A}$ and their respective values.

Hyperparameter	Description	Value 1	Value 2
Alpha ($\alpha$)	Learning rate that controls how much the agent learns from each new experience. A higher value accelerates learning but may lead to unstable convergence.	$0.01$	$0.5$
Gamma ($\gamma$)	Discount factor that determines the importance of future rewards. A higher value prioritizes long-term rewards.	$0.9$	$0.5$
Epsilon ($ϵ$)	Exploration rate that controls the probability of the agent taking a random action instead of following its policy. A higher value encourages exploration.	$0.2$	$0.015$
Epsilon Decay (${ϵ}_{decay}$)	Decay rate for the exploration rate ($ϵ$), which controls how $ϵ$ decreases over time, allowing the agent to reduce exploration as it learns.	$0.999$	$0.9$