Energy Informatics

Table 2 Hyper-parameters of the PPO model

From: A stochastic deep reinforcement learning agent for grid-friendly electric vehicle charging management

Hyper-parameter Value
Layers and layer dims.	Figure 1
Activation functions	Figure 1
Learning rate	Actor: \(1\times 10^{-6}\)
	Critic: \(1\times 10^{-5}\)
Loss function	Actor: Eq. 2
	Critic: MSE
Optimizer	Adam
\(\epsilon\)	0.2
Batch size	64
Soft update rate	0.001

Back to article page