Federated Reinforcement Learning-Based UAV Swarm System for Aerial Remote Sensing

Table 2

Variables used for determining the reward.

Notation	Description
	Set of nearby objects
	Nearest object
	Target object
	Distance to
	Radius size of UAV
	Distance to the target
	Threshold of distance to the target where the agent is deemed to arrive at the target
	Normalized vector to target
	Normalized vector of action
	Clip value for determining reward