Enhanced Route Discovery Mechanism Using Improved CH Selection Using Q-Learning to Minimize Delay

Table 1

Notations used.

	Delay efficacy
	Policies
A(r)	Action
RREQ	Route request
S (t)	State function
T {A(r), S(r)}	Transition function
WD	Act as a destination node
WN	Number of nodes
WS	Act as a source node
WSN–FR	Final route from WS to WD