Research Article
Joint Resource Allocation and Power Control Based on Vehicle’s Motion Characteristics in NOMA-Based V2V Systems
Algorithm 4
Q-learning based power control algorithm.
(1) | initialize Q-table to zeros | (2) | for do | (3) | if then | (4) | select action randomly | (5) | else | (6) | choose action | (7) | end if | (8) | calculate reward value as (9) | (9) | update Q-table as (10) | (10) | | (11) | end for | (12) | choose |
|