Skip to main content
EURASIP Journal on Wireless Communications and Networking
Fig. 2 | EURASIP Journal on Wireless Communications and Networking

Fig. 2

From: Reinforcement learning-based hybrid spectrum resource allocation scheme for the high load of URLLC services

Fig. 2

The RL-based hybrid spectrum and power resource allocation model for URLLC. The overall framework of figure is an RL framework. There are control procedures (control flow) and data processing procedures (data flow) in this framework. The bottom of figure is the data flow in the external environment. Each step of the data flow is specifically completed according to the RL agent at the top of figure. The external environment processes data information into Status and Rewards and feeds back to the Agent. The Agent gets the Action after learning with the DNN and returns it to the environment

Back to article page