An Efficient Resource Management Optimization Scheme for Internet of Vehicles in Edge Computing Environment

Algorithm 1

Resource management algorithm based on distributed reinforcement learning.

	Input: actor network, actor target network, critical network and critical target network, learning rate , discount rate , attenuation factor .
	Output: computing task offloading policy .
	Initialize the critical network parameter and actor network parameter .
	Initialize the status of experience playback pool and task vehicle
	Fordo
	Observe the environment status and select actions based on the current policy
	Execute the action , get the reward , and transfer to the state
	Save array to experience playback pool
	If the memory bank is full, but the stop condition is not met, a small batch of arrays is randomly sampled from the experience playback pool.
	Update critical network parameters, actor network parameters, and target network parameters
	End
	End