Reinforcement Learning for Joint Channel/Subframe Selection of LTE in the Unlicensed Spectrum

Table 4

Major parameters for the proposed scheme and sensing-based scheme [22].

Parameter	Value	Unit
Learning period	50,000	Timeslot
Initial value	0.5
	0.4
	35
	2
	0.00025
Reward calculation period	50,000	Timeslot
Sensing period	4,000,000	Timeslot
Sensing time	40,000	Timeslot/period