Q-greedyUCB: a New Exploration Policy to Learn Resource-Efficient Scheduling

Zhao, Y; Lee, J; Chen, W

Lee, J (corresponding author), Hanyang Univ, Dept Elect & Elect Engn, Ansan 15588, South Korea.

CHINA COMMUNICATIONS, 2021; 18 (6): 12

Abstract

This paper proposes a Reinforcement learning (RL) algorithm to find an optimal scheduling policy to minimize the delay for a given energy constraint i......

Full Text Link