G	Generator network
C	Critic network
${\theta }_G,{\theta }_R$	Parameters of generator or discriminator
$\alpha ,{\beta }_1,{\beta }_2$	Parameters of Adam optimizer
$S_t$	State captured by the agent at time-slot t
$A_t$	Possible actions taken by the agent at time-slot t
$R_t$	Reward returned to the agent at time-slot t
$P_a$	Transaction of state probability matrix
$\gamma$	Discount factor, where $0<\gamma <1$
$\tau$	Bellman operator
X	Original Data
M	Replay memory data set
z	Random noise vector
$\lambda$	Coefficient of penalty